Artificial intelligence and machine learning in electronic fetal monitoring

Vol.:(0123456789) Archives of Computational Methods in Engineering (2024) 31:2557–2588 https://doi.org/10.1007/s11831-023-10055-6 REVIEW ARTICLE Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring KaterinaBarnova1· RadekMartinek1· RadanaVilimkovaKahankova1· ReneJaros1 · VaclavSnasel2· SeyedaliMirjalili3 Received: 25 February 2022 / Accepted: 20 December 2023 / Published online: 31 January 2024 © The Author(s) 2024 Abstract Electronic fetal monitoring is used to evaluate fetal well-being by assessing fetal heart activity. The signals produced by the fetal heart carry valuable information about fetal health, but due to non-stationarity and present interference, their processing, analysis and interpretation is considered to be very challenging. Therefore, medical technologies equipped with Artificial Intelligence algorithms are rapidly evolving into clinical practice and provide solutions in the key application areas: noise suppression, feature detection and fetal state classification. The use of artificial intelligence and machine learning in the field of electronic fetal monitoring has demonstrated the efficiency and superiority of such techniques compared to conventional algorithms, especially due to their ability to predict, learn and efficiently handle dynamic Big data. Combining multiple algorithms and optimizing them for given purpose enables timely and accurate diagnosis of fetal health state. This review summarizes the currently used algorithms based on artificial intelligence and machine learning in the field of electronic fetal monitoring, outlines its advantages and limitations, as well as future challenges which remain to be solved. Abbreviations ACC Accuracy ADALINE Adaptive linear neuron AE Autoencoder aECG Abdominal electrocardiography AI Artificial intelligence ANFIS Adaptive neuro-fuzzy inference system ANN Artificial neural network BMI Body mass index BP Back propagation CNN Convolutional neural network CTG Cardiotocography CWT Continuous wavelet transform DE Differential evolution EBBA Enhanced binary bat algorithm EFM Electronic fetal monitoring EKS Extended Kalman smoother EMD Empirical mode decomposition ES Evolution strategy ESN Echo state network FA Firefly algorithm fECG Fetal electrocardiography fHR Fetal heart rate fHS Fetal heart sound FIGO The International Federation of Gynaecology and Obstetrics fMCG Fetal magnetocardiography fPCG Fetal phonocardioraphy fQRS Fetal QRS * Rene Jaros [email protected] Katerina Barnova katerina.barnov[email protected] Radek Martinek [email protected] Radana Vilimkova Kahankova radana.vilimkova.kahankov[email protected] Vaclav Snasel [email protected] Seyedali Mirjalili [email protected] 1 Department ofCybernetics andBiomedical Engineering, Faculty ofElectrical Engineering andComputer Science, VSB–Technical University ofOstrava, 17. listopadu 2172/15, 70800Ostrava, Czechia 2 Department ofComputer Science, Faculty ofElectrical Engineering andComputer Science, VSB–Technical University ofOstrava, 17. listopadu 2172/15, 70800Ostrava, Czechia 3 Centre forArtificial Intelligence Research andOptimisation, Torrens University Australia, 90 Bowen Terrace, Brisbane, QLD4006, Australia 2558 K.Barnova et al. FURIA Fuzzy unordered rule induction algorithm GA Genetic algorithm GLCM Grey-level co-occurrence matrix GWO Grey wolf optimizer HT Hilbert transform ICA Independent component analysis IMF Intrinsic mode function K-NN K-nearest neighbor LMS Least mean square LS-SVM Least squares singular value decomposition LSTM Long short-term memory mECG Maternal electrocardiography MFO Moth-flame optimization mHS Maternal heart sound ML Machine learning MLP Multilayer perceptron mQRS Maternal QRS MS Magnetometer system NI-fECG Non-invasive fetal electrocardiography NLMS Normalized least mean square NPV Negative predictive value PPA Positive predictive agreement PPV Positive predictive value PS Phonocardiographic sensor PSO Particle swarm optimization RLS Recursive least squares RNN Recurrent neural network SE Sensitivity SNR Signal-to-noise ratio SNR imp Signal-to-noise ratio improvement SP Specificity STFT Short-time Fourier transform SVD Singular value decomposition SVM Support vector machines TS Toco sensor UT Ultrasound transducer WT Wavelet transform 1 Introduction The electronic fetal monitoring (EFM) is used nowadays particularly for monitoring the heart activity of fetus and assessing its well-being. The main objective of monitoring is an early detection of life-threatening fetal hypoxia. If the fetal hypoxia is not detected and rectified on time, the oxygen saturation of blood becomes extremely low and the fetal hypoxia progresses to asphyxia. The consequence of a serious asphyxia is a hypoxic-ischemic damage of organs which may, inter alia, lead to a brain and heart damage and a nervous system failure [1, 2]. An accurate and reliable fetal monitoring during pregnancy and birth may lead to an early detection of states which may adversely affect the health of fetus or cause perinatal death. The fetal heart monitoring has its origins in the first half of the 19th century when fetal heart sounds (fHSs) were detected thanks to the invention of stethoscope. The assessment of fetal well-being was based on intermittent auscultation of fHSs and subsequent determination of fetal heart rate (fHR) [3]. The EFM became the basis of prenatal care and a common part of clinical practice as late as in the 1960s when the first cardiotocograph (CTG), which was supposed to help doctors in detecting fetal hypoxia, was introduced thanks to the development in science and technology [4]. Nevertheless, some studies in the past [5–7] argued that the number of executed caesarian sections had increased after introducing the CTG equipment to delivery rooms but at the same time there had been no decrease in perinatal mortality caused by the influence of hypoxia. This was attributed to a difficult interpretation of CTG data influenced by subjective assessment and experience of doctors which led to a high false positivity when determining the hypoxia leading to a high number of unnecessarily executed caesarian sections [4, 5]. This tendency from the past persists and the numbers of caesarian sections are still high. The numbers of caesarian sections should move within 10–15% [8] according to the World Health Organization statement on caesarean section rates, however the world average ranges around 21.1% according to the data from 2015. In some countries (Dominican Republic, Egypt or Brazil for instance), the numbers of caesarian sections are exceeding 55% [9], which is alarming. Since the caesarian section is an invasive procedure after which the incidence of complications is more frequent than after a spontaneous delivery [10], the current research is focused on the development of both the classical CTG [11–13], and alternative techniques for non-invasive EFM such as fetal electrocardiography (fECG) [14, 15], fetal phonocardiography (fPCG) [16] or fetal magnetocardiography (fMCG) [17]. Such alternative techniques bring very important clinical information about the fetal health and have a great potential to become complement to the conventional CTG or substitute the CTG entirely thanks to its non-invasiveness and absence of ultrasound radiation. Nevertheless, the processing, analysis and interpretation of these biological signals is a challenging task, because it is rather difficult and computationally demanding to model a function of human body with classical mathematics [18]. This is mainly due to the nonlinear and non-stationary nature of these biological signals and the presence of many types of interference. In addition, useful signal and interference often overlap in the time and frequency domains, causing conventional algorithms to fail to process these signals [18]. According to the latest research [19–22] the algorithms based on artificial intelligence (AI) have appeared to be very promising for the processing and 2559Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring analysis of these real-world signals, especially due to their ability to predict and learn. 1.1 Structure oftheReview This review focuses on the use of AI in the field of noninvasive electronic monitoring of fetal heart activity, provides the summary of advantages and limitations of presented methods, and also the list of future challenges. The structure of the contribution includes Sect.2 which provides a general overview of both the non-invasive techniques for EFM and AI-based approaches used in these fields. Section3 describes three main application areas of AI in EFM (noise suppression, feature detection and fetal state classification). Section4 summarizes the efficiency of presented algorithms, highlights the most important findings and outlines directions for further research. In Sect.5, the remaining challenges associated with the fetal monitoring and AI are discussed. The conclusion of the contribution is in Sect.6. 1.2 Literature Search Strategy To find relevant literature for this review, Google Scholar, PubMed, and the Scopus search engines were used. The search used phrases combining terms from the field of artificial intelligence: “Artificial intelligence”, “Machine learning”, “Artificial neural networks”, “Fuzzy logic”, “Natureinspired optimization” combined with fetal monitoring techniques: “Cardiotocography”, “Fetal electrocardiography”, “Fetal phonocardiography”, “Fetal magnetocardiography”. A total of 20 queries were used for the search, see Fig.1. All results found were inspected and evaluated. Only studies that were published after 2000 were selected. A large part of the conference papers was excluded. 2 Background In the field of EFM, as in other areas, there is a rapid development with the advancement of science and technology. The goal of scientists and obstetricians is to develop a highly reliable system, using the most modern approaches and technologies, through which it would be possible to detect fetal hypoxia with a high accuracy and decrease the number of unnecessarily executed caesarian sections. AI technologies, which excels in solving complex tasks and processing of great number of data, appear to be promising for the processing and interpretation of fetal signals [23]. This section gives an overview of basic techniques for EFM and AI-based approaches used in these fields. 2.1 Electronic Fetal Monitoring The term EFM was used in the past exclusively as a synonym for the CTG technique. It turned out to be misleading and since 2015, based on the consensus of The International Federation of Gynecology and Obstetrics, only the term CTG has been reserved for this monitoring technique. The term EFM will be used in this article only as a general term [4] comprising more methods of fetal monitoring, for example: 1. Cardiotocography CTG is based on the simultaneous measuring of uterine contractions and fHR (see Fig.2). The trace of fHR is obtained by scanning the movements of fetal heart recorded with Doppler-based ultrasound transducer [4]. Subsequently, the recorded signal passes through the modulation and the autocorrelation to ensure its sufficient quality. This process leads to the approximation of the true fHR intervals. Uterine contractions are scanned by a pressure sensor. Nevertheless, the quality of records strongly depends on the sensor placement and belt tightening [1]. However, this method is associated with a number of disadvantages which include, in particular, an important influence of the examining doctor’s experience upon the interpretation of CTG records (commonly leading to an inaccurate detection of fetal hypoxia), an influence of sensor placement on the quality of signals, a sensitivity to the movements of fetus as well as the mother and a lower sensitivity of women with higher values of body mass index (BMI) [24]. 2. Fetal Electrocardiography The non-invasive fECG (NI-fECG), based on recording electrical signals from the mother’s abdominal area, appears to be the most PubMed Google Scholar Search engines Queries Literature selection Articles published by year 2000-2021 Journal articles or high-ranked conference papers Final list of literature “Fetal magnetocardiography” “Nature-inspired optimization” AND “Artificial intelligence” “Machine learning” “Artificial neural networks” “Fuzzy logic” “Cardiotocography” “Fetal electrocardiography” “Fetal phonocardiography” Scopus Fig. 1 Principle of literature search strategy for finding relevant literature 2560 K.Barnova et al. promising technique of fetal monitoring. At present, the invasive variant (the so-called direct fECG), measuring fECG signal by means of scalp electrode directly from the fetal head. This makes it highly accurate, but many critics disparage its contributions due to the negatives related to its invasiveness (for example the mother’s discomfort or the risk of infection). Apart from the fHR, the fECG signal provides also additional information about pathological states connected in particular with fetal hypoxia or metabolic acidosis [4, 25]. They manifest as changes in the morphology of fECG traces, such as changes of T:QRS ratio or QT interval [26, 27]. It has been demonstrated that during the simultaneous recording of fHR and T:QRS ratio (known as ST analysis or STAN) there has been both an early detection of acidosis and a decrease in the number of unnecessary caesarian sections [25, 28], thus eliminating the main aspects for which the CTG has been criticized [5, 29]. Due to these reasons, NI-fECG has a huge potential to become a complementary method to the CTG or to replace it completely in clinical practice. Moreover, in case of NIfECG, neither the mother nor the fetus are exposed to ultrasound radiation which allows a continual recording, even within the framework of home monitoring. An advantage is its use for women who have higher values of BMI. The main obstacle of NI-fECG recording is the presence of other disturbing signals, in particular the maternal electrocardiographic signal (mECG), which must be eliminated in order to obtain clinical information from NI-fECG [4, 25]. In Fig.2 there is a schematic example of the electrode placement and recorded abdominal signals (aECG) containing a mixture of mECG and fECG. 3. Fetal Phonocardiography The method of fPCG is low-cost and a completely passive technique based on the monitoring of fHSs, cardiac acoustic vibrations and murmurs by means of microphone-transducer [30, 31]. The attention has been recently paid to understanding the nature and the origin of this signal, especially because the fPCG signal recorded in high quality may provide more information about cardiac pathologies than commonly used CTG [32]. According to the research focused on the development of fPCG [33], this technique might become a complement of the classical CTG. The fPCG could find its use especially in a long-term monitoring and home monitoring which might lead to a reduction in the number of physical visits to the doctor [34]. In contrary to CTG, additional information TS UT AE2 AE0 N AE1PS 0 Time (s) AE1 AE2 0 Time (s) 123 fffffff m mmmm fffffff mmm PS 012 Time (s) S1S2S1S2 S1S2 S1 S2S1S2 S1S2S1S2 UT TS 0510 Time (min) PS m mmmm mmm fffffff fffffff S1 S2S1S2 S1S2S1S2 S1S2 S1S2S1S2 Fetal electrocardiography Fetal magnetocardiography Cardiotocography Fetal phonocardiography MS MS MS 123 3 Fig. 2 Illustration of different monitoring methods, their signals and placement of sensing electrodes and sensors. In CTG monitoring, uterine contractions are measured using a toco sensor (TS) and the fHR trace is obtained using an ultrasound transducer (UT). In the case of fECG measurements, aECG signals are obtained using AE 1 and AE 2 electrodes. AE 0 refers to the reference electrode and N refers to the active ground. The placement of the sensing electrodes was inspired by Matonia etal. [38] and examples of aECG signals from the Fetal electrocardiograms, direct and abdominal with reference heartbeat annotations dataset were used. The fMCG signals are measured using a magnetometer system (MS). In examples of fECG and fMCG signals, the maternal and fetal components are labeled with m and f, respectively. The fPCG signal is measured by phonocardiographic sensor (PS). The diagram shows ideal fPCG signal (upper trace) and fPCG signal with ambient interference (lower trace) with S 1 and S 2 sounds labeled 2561Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring about the fetal health state could be obtained through a complex analysis of heart murmurs. Unfortunately, the main disadvantage of fPCG is a high sensitivity to the disturbing signals and necessity of proper placement of the recording sensor [32, 33]. When fPCG signals from maternal abdominal area are recorded, the useful signal is contaminated especially with ambient noise (e.g. speech, cough, radio, air conditioning, door closings or alarms). Moreover, maternal as well as fetal movement artifacts, such as breathing artifacts, uterine contractions, bowel sounds and maternal heart sounds (mHSs) are also considered to be disturbing [32]. In Fig.2 there is a schematic example of the recording sensor placement, ideal fPCG signal and fPCG signal disturbed by ambient noise. 4. Fetal Magnetocardiography The fMCG is an alternative method based on recording magnetic fields created by conduction currents in the fetal heart. The fMCG signal shows the same information as the fECG (i.e. the electrical activity of the fetal heart in the form of the PQRST complex) [35]. Figure2 shows a schematic diagram of magnetometer system and the recorded fMCG signals. The magnetic field produced by the fetal heart is sensed by magnetometer system from outside the maternal abdomen above the fetal heart [36]. The fMCG signals have much higher value of signal-to-noise ratio (SNR) than the NI-fECG signals since the propagation of magnetic fields is not that affected by surrounding tissue as in the case of NI-fECG [35]. Moreover, the NI-fECG is almost impossible to be recorded between the 28th and 32nd weeks of pregnancy due to the fetal coverage with the layer of vernix caseosa, which isolates the fetal electrical cardiac activity [25]. However, this very promising method is not often used in clinical practice due to high financial costs and the complexity of the measuring device. The superconducting quantum interference device technology is used for recording which requires cooling by liquid helium and measuring must be conducted in a large and magnetically shielded room [17, 37]. Moreover, the fMCG must be measured by an experienced doctor and a skilled technical support must be available [4]. Nevertheless, the current research focuses on the development of new magneto-metric technologies, such as optically pumped magnetometers [17], which are less costly and their use is more practical and simple. This progress in the development might allow the fMCG to become a part of common clinical practice and the priceless information about the fetal health could be obtained from it [17]. All four of the above-mentioned EFM techniques are of great benefit to clinical practice. However, in order to obtain all important information regarding fetal and maternal health state, further research and development is needed, especially in the field of signal-processing algorithms. There is a great need to design and implement reliable and intelligent methods that can improve the processing, analysis and interpretation of fetal and maternal heart 2.2 Artificial Intelligence Methods The function of most real systems, including human body, is represented by non-linear dynamic behaviour with a certain degree of variability and uncertainty. The processing of such data is difficult and computationally demanding for conventional algorithms [18]. AI-based algorithms are able to deal with this inaccuracy and uncertainty. In addition to that, these algorithms can use these properties to create an adaptive low-cost solution [18, 39]. AI-based algorithms generally imitate human intelligence to solve complex tasks and, at the same time, improve iteratively on the basis of obtained information [23]. There are many partial sub-areas of AI using scientific findings, in particular from the fields of mathematics, statistics or biology. With respect to EFM, it is possible to encounter algorithms based on machine learning (ML), artificial neural networks (ANNs), fuzzy logic or nature-inspired optimization techniques. This section and Fig.3 provide a basic overview of these sub-areas. 1. Machine Learning ML-based algorithms are able to learn and automatically increase their efficiency through experience based on data they work with [40]. According to learning methods, ML algorithms can be divided into four categories: supervised learning, unsupervised learning, semi-supervised learning and reinforcement learning. In case of supervised learning, a mathematical model of a data set, containing both inputs and outputs (a class for classification or a value for regression) assigned by human experts, is created [40, 41]. According to [39, 42], we can include, for example, decision trees (random forest [12] or C4.5 algorithm [43]), support vector machines (SVM) [11, 44], regressive analysis [45], k-nearest neighbor (k-NN) [11] or naive Bayes [46] into this category. As for unsupervised learning, an algorithm has only input (unlabeled) data and the output is unknown to the ML technique. The algorithm learns to recognize complex processes and formulas and usually creates a proper and simpler representation of input data which it subsequently clusters into groups without the possibility to assess the correctness of clustering [40]. According to [39, 42], some of the most wellregarded algorithms in this category are k-means [47, 48], k-medoids [47, 49], hierarchical clustering [47] or fuzzy c-means [47]. The semi-supervised learning combines both approaches described above in such a way that a part of the input data also contains the required 2562 K.Barnova et al. output, but the other part of the data (usually larger) does not contain the required output [40]. Reinforcement learning is based on rewarding the required behaviour and, vice-versa, punishing the non-required behaviour [41]. Thus, the learning functions on the basis of the trial and error principle because there are no training data available. Nevertheless, neither the semi-supervised learning nor the reinforcement learning are very widespread in the field of EFM. 2. Artificial Neural Networks ANNs-based algorithms are computing models inspired by biological structures behaviour. Such techniques mimic the learning and adapting mechanisms of biological neurons in brains [39, 50]. The basic network unit is the neuron which may have a random number of inputs but only one output. Neurons forming ANNs are mutually connected and transmit signals which are transformed by means of transfer functions. According to the topology (structure) of network, ANNs may be divided into feed-forward networks and recurrent neural networks (RNNs) [50]. The simplest model of feed-forward network for binary classification composed of a single neuron is called a perceptron or a more powerful adaptive linear neuron (ADALINE) [51, 52]. Due to the limited use of perceptron, this model was expanded to a multilayer perceptron (MLP), which represents a special type of multilayer network where each layer is fully connected (each layer neuron is connected with all neurons in the preceding layer) [52]. Multilayer networks are usually organized in several layers composed of an input layer, intermediate hidden layers and an output layer [50]. ANNs with a large number of layers (tens of layers) are called deep ANNs and form a basis for deep learning to solve very complex linear and non-linear problems. In order to estimate the parameters (training) of ANNs, the back propagation (BP) algorithm is of the most popular techniques [39]. This group of networks may include, for example, convolutional neural networks (CNNs) [12, 19, 53], probabilistic ANNs [54], polynomial ANNs [55, 56], deep belief ANNs [57]. Adaptive neuro-fuzzy inference system (ANFIS) [58–60] is also used very often in this field. As far as RNNs are concerned, there is also a reverse transmission of information from higher layers back to lower layers in addition to signal propagation from the input layer in the direction of the output layer, which is in contradiction with multilayer ANNs [50]. Within the framework of EFM, it is possible to encounter especially an echo state network (ESN) [61, 62] or a long short-term memory (LSTM) [22]. 3. Fuzzy Logic Fuzzy logic is a powerful tool for solving tasks where a solution cannot be found through classical statement logic using only two logic values 1 a 0. Fuzzy logic allows to work with all values in the interval ⟨ 0;1 ⟩ , and the number of values is infinite [63]. It allows to catch an approximate reasoning better which is characteristic of human reasoning and environment full of uncertainties and inaccuracies [64]. The fuzzy model is usually created on the basis of fuzzy rules implemented Artificial intelligence Nature-inspired computational techniques Supervised learning Unsupervised learning Evolutionary algorithms Swarm-based algorithms FURIA Recurrent Feed-forward Hierarchical clustering Decision trees Random forest C4.5 algorithm SVM Logistic regression Naive Bayes K-NN K-means K-medoids Fuzzy c-means ESN LSTM GA DE PSO FA MFO CNN Probabilistic ANN Legendre ANN Polynomial ANN MLP Deep belief ANN ADALINE ANFIS Fuzzy logic Artificial neural networks Machine learning ES Fig. 3 An overview of AI-based approaches used in EFM 2563Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring as a series of if-then rules. Since the fuzzy concept is based on the qualitative rather than the quantitative expression, it is easier to connect mathematics with real-world applications [63, 64]. In the field of EFM, we may also encounter, for example, a fuzzy unordered rule induction algorithm (FURIA) [65] in addition to the classical fuzzy logic [66–68]. 4. Nature-Inspired Optimization Techniques Natureinspired algorithms are often inspired by the evolution, biological systems or chemical or physical processes. Such approaches have been demonstrated to be very flexible and effective for solving highly non-linear problems and their use is appropriate especially for challenging optimization tasks [69, 70]. In order to find an optimal solution effectively (or a solution close to being optimal), they use iterative processes and intelligent learning strategies for the exploration and exploitation of the search space [42]. Within the framework of EFM we may encounter, in particular, evolutionary algorithms which are inspired by biological evolution, such as genetic algorithms (GA) [71, 72], differential evolution (DE) [73, 74], or evolution strategy (ES) [75]. The second large group of algorithms are swarm-based algorithms inspired by the behaviour of biological swarms, such as particle swarm optimization (PSO) [76, 77], firefly algorithm (FA) [78] or moth-flame optimization algorithm (MFO) [79]. 3 Application Areas ofArtificial Intelligence In the field of EFM, we may come across three main areas in which AI-based algorithms are used. The first area is the suppression of noise especially in fECG signals (the elimination of mECG) [19, 22, 57, 61, 80], but also in the processing of fPCG [60]. The second area is represented by the feature detection which includes the detection of fetal QRS (fQRS) complexes [47, 49, 53, 81–85] and the estimate of fHR without the necessity to detect R peaks [20] in fECG signals. Similarly, in fPCG signals, AI-based algorithms were used to detect fHSs [45, 48]. The last area is the classification of fetal health using signals recorded by means of CTG [11, 43, 86–89], but also by means of alternative techniques of fPCG [66, 90, 91] or fMCG [44]. Figure4 illustrates the areas where the AI was used in the past marked by the red frame. 3.1 Noise Suppression It is essential to have a quality signal for a precise signal analysis and obtaining correct clinical information. In case of CTG or fMCG, signal filtration is not such a difficult task as in the case of fECG or fPCG. The extraction of fECG is a challenging task due to a relatively low SNR of the useful signal (fetal component) which is overlapped by mECG and other noise both in temporal and frequency domains [4, 25]. Therefore, the past research in the field of fECG extraction focused on testing especially advanced signal processing methods such as blind source separation methods [92, 93], wavelet transform (WT) [14], empirical mode decomposition (EMD) based algorithms [94, 95] or adaptive filters [15, 96]. Hybrid methods combining adaptive and non-adaptive algorithms turned out to be the most promising [97]. However, in low quality recordings, even these algorithms failed to provide satisfactory results. A number of authors (e.g. in [21, 98]) have recently shown that non-linear fECG domain could be modelled more accurately by means of AI approaches. In case of fPCG signal extraction, an effective suppression of most types of interference was achieved by means of the modified finite impulse response filter [99] or WT [100]. A more difficult task arises in suppressing mHSs where there is a room for using AI-based algorithms as in case of fECG. The AI-based methods for fetal component extraction (both in fPCG and fECG) work on the same principle as adaptive algorithms. The principle will be illustrated on the fECG extraction fPCG extraction Noise suppression fQRS detection fHR estimation Feature detection fHS detection fHR estimation Murmurs detection fQRS detection fHR estimation Feature extraction and selection fHR T/QRS; QT interval Uterine contractions fHR Murmurs fHR Uterine contractions fHR T/QRS; QT interval Uterine contractions Pathological Suspect Normal Classification Fetal state classification Clinical management No intervention necessary Close monitoring Immediate intervention Preprocessing Preprocessing CTG fECG fPCG fMCG Modulation Autocorrelation Preprocessing Preprocessing Signals acquisition and preprocessing fMCG extraction Fig. 4 A schematic illustration of individual steps for obtaining, processing and classifying the fetal health by means of CTG, fECG, fPCG, and fMCG signals. Red frames indicate three areas where the AI was already used in the past 2564 K.Barnova et al. fECG extraction example, see Fig.5. These methods use the following inputs: (1) composed aECG signal, i.e. mixture of maternal and fetal components (mECG A , fECG) and noise, and (2) reference thoracic mECG T . The thoracic mECG T is adapted by AI-based algorithm into the form of mECG A included in the aECG input. The distortion of mECG A is caused by measuring this signal far from the source (the heart of mother) and non-linear transformation of the signal passing through different layers and tissues in the abdominal area [55]. The mECG T signal adapted by the algorithm into the form of mECG A is finally subtracted from aECG to obtain the fECG. 3.1.1 Artificial Neural Networks inNoise Suppression Different types of ANNs are appropriate for fECG extraction especially due to their adaptability to the non-linear and time-varying features of fECG signal [101]. Thanks to their ability to learn and predict, ANNs are able to separate useful signal (i.e. fECG) and noise (i.e. mECG), which overlap in time and frequency domain and reach higher accuracy in fECG extraction in comparison with classical adaptive algorithms, such as the least mean squares (LMS) [102], the normalized LMS (NLMS) [103] or the recursive least squares (RLS) [104]. Moreover, a lower number of calculations is necessary as demonstrated in [21]. • Polynomial Neural Networks Polynomial ANNs are multilayer networks using polynomial exponentiation activation function [105]. Although, according to Ayat etal. [56], this method managed to extract the fECG and outperform the algorithm of singular value decomposition (SVD). In some cases, however, it did not provide a satisfactory results. If the thoracic mECG T and aECG signals were recorded from different locations, the morphology of mECG T and mECG A was different and the final fECG signal was contaminated with significant maternal residue. During experiments conducted by Assaleh etal. [55], the polynomial ANN managed to sufficiently suppress the maternal component, even in the cases when fetal and maternal beats overlapped. On the other hand, there was a noise present in the extracted fECG signal due to muscular activity, therefore, the use of additional post-processing techniques was recommended for its elimination. It was also interesting to discover that polynomial expansions of higher order than three did not lead to further quality improvement of the extracted signal according to a visual assessment. Ahmadi etal. [106] dealt with the pre-processing and post-processing of signal by means of WT before or after the application of polynomial ANN. Three scenarios were tested: a) the WT method filtered aECG signal before the application of polynomial ANN, b) WT was applied to an extracted fECG signal obtained by the application of polynomial ANN and c) WT was used for pre-processing of aECG and subsequently also for post-processing of the extracted fECG. Although SNR improved in all three scenarios in contrast to the use of basic polynomial ANN, the biggest improvement was achieved in the case of b) variant, i.e. in the application of WT as post-processing. • Convolutional Neural Networks CNNs belong to deep, feed-forward, multi-layer networks composed of an input layer, multiple hidden layers and an output layer. Hidden layers contain a convolutional layer, activation layer, pooling layer, fully-connected layer and normalization layers [107]. In convolutional layer, the operation of convolution is applied and multiple feature maps are obtained, which leads to the reduction of memory bulk used by CNNs. The activation layer maps the output of convolutional layer through the activation function to form the feature mapping relationship. The normalization layer serves for standardizing the input data of each layer during the training. Pooling layers appear periodically between convolutional layers going one after another to Fig. 5 A general schema of fECG extraction by means of AI-based algorithms. The thoracic electrode records the reference mECG T signal and the electrodes on the mother’s abdomen record aECG which is a mixture of mECG A , fECG and noise. The mECG T and aECG signal enters the AI-based algorithm and it adjusts the mECG T signal into the form of mECG A signal contained in aECG. The adjusted mECG T is finally deducted from the aECG and the final fECG is obtained Estimated fECG mECGT aECG1 aECGn mm m+fm fff ff AI-based algorithm 2565Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring reduce the amount of data, the complexity of network, to speed up the calculation and to prevent overfitting. Thus, more information intensive features for final classification finally enter into the fully-connected layer (this is a classical MLP). After the fully-connected layer, there is a dropout layer preventing the overfitting in such a way that during the training process, there are several neural units which are with a certain probability temporarily dropped from the network. At the end, the classification network using the function of softmax is used to separate outputs [108]. The CNN-based approach introduced by Fotiadou etal. [19] was used to remove residual noise in extracted fECG signals in which the maternal component was already suppressed. The technique used the convolutional encoder-decoder network with symmetric skip-layer connections. The encoder as well as decoder contained eight convolutional layers, but the convolutional layers of the decoder were symmetrically transposed. Skip connections were placed between every two convolutional as well as transposed convolutional layers. When testing the algorithm on simulated signals, its efficiency was evaluated according to the SNR improvement (SNR imp ) parameter. The final fECG signals were improved (SNR imp = 9.5dB) and the benefit was the keeping of beat-to-beat morphological variations. Moreover, there was no need of any prior information on the power spectra of the noise. To increase the accuracy of fECG extraction, Almadani etal. [109] proposed a combination of two parallel fully CNNs (U-Nets [110]) with transformer encoding. In addition to efficient fECG extraction, the system was able to operate in real time and, according to the authors, could be implemented in a portable device. The CNN turned out to be powerful in combination with Bayesian filter as showed by Jagannath etal. [98] in 2019. The Bayesian filter managed to provide accurate mECG A estimate in the aECG signal and the deep CNN estimated a non-linear relationship between the mECG A and the thoracic mECG T , which was non-linearly transformed. A nine-layer network was used with three convolutional layers, three max-pooling layers for the compression of signal features and reduction of complexity and three fully-connected layers. The last layer contained one neuron representing the final fECG signal. The linear activation function was used for all layers, excluding the last one, and the softmax function was used in case of the last fully-connected layer. In terms of efficiency, this combined algorithm surpassed the classical adaptive LMS algorithm. The disadvantage of the algorithm is the high computational time during the training process, and therefore it was not suitable for training large datasets. In 2020, the same authors [57] compared their previously designed combination of CNN with the Bayesian filter to two other networks (the deep belief ANN and the conventional ANN using BP algorithm) which were also combined with the Bayesian filter. The input layer of conventional ANN contained 72 neurons, the hidden layer contained 2 layers with 84 neurons in each of them and 1 output neuron. In the input layer of the deep belief ANN, there were 98 neurons, 2 hidden layers were composed of the total number of 84 neurons and 1 neuron was used in the output layer. All three methods extracted a high-quality fECG, but it was the CNN (SNR imp = 39.73dB) that achieved the best results in terms of the SNR improvement. The limitation of all three algorithms was their high time complexity, which would not allow their implementation in real-time operating devices. • Multilayer Perceptron It is a feed-forward multi-layer network with one or more hidden layers. The main feature of the network is that every neuron in a specific layer is connected with all neurons in the preceding layer [52, 54]. In order to select the number of neurons in the hidden layer, two rules are generally used: a) their number should not be higher than the double of neurons in the input layer and b) their number should move between the number of neurons in the input layer and the output layer [54]. Golzan etal. [80] suggested a MLP where the connections between the input and hidden neurons were weighted by an adjustable weight parameter. The authors compared the efficiency of two different training methods: maximum likelihood (it presumes that weights have a fixed unknown value) and Bayesian learning (it considers the uncertainties of weight vector and assigns them probability distribution). The algorithms were tested on real recordings and their efficiency was evaluated according to the accuracy (ACC), sensitivity (SE), and positive predictive value (PPV) parameters. The algorithm based on Bayesian learning turned out to be superior with ACC = 94.86%, SE = 96.49% and PPV = 93.79% which may be attributed to its more effective use of training data. • Long Short Term Memory LSTM networks are a specific type of RNN able to remember information for a long period of time and learn a long-term dependency. The chain structure with recurring modules of ANNs, each containing four layers, is typical for the LSTM. The classic LSTM unit contains an input and an output gate, a forget gate and a cell. The cell remembers values in time intervals and gates decide which information will be removed and which will be retained [111]. The two-stage architecture combining slow and fast LSTM was employed by Zhou etal. [22]. The principle of the method was the implementation of slow LSTM for filtering mECG and the fast LSTM in order to highlight fECG, eliminate the remaining noise and improve the computing efficiency. Compared to the classic LSTM, the improved method reduced the total number of cal- 2572 K.Barnova et al. (normal, abnormal) [147, 149, 150] or three classes (normal, suspect, pathological) [54, 86, 87]. 3.3.1 Artificial Neural Networks inClassification In order to successfully classify a fetal state using ANNs, a suitable type of ANN must be selected as well as its architecture and hyper-parameter setting [87]. Using a classic feedforward multilayer network requires setting up the number of neurons in the input layer, the number of hidden layers including the number of neurons, the number of neurons in the output layer, training algorithms (e.g. gradient descent BP, Levenberg-Marquardt BP, quasi-Newton BP) [87, 151], training concept (incremental-weights are updated in each iteration, or batch-weights are updated only when all inputs are available in the network) [87], number of epochs, learning rate (usually a small positive value ranging between 0 and 1) [152], and an activation function (e.g. linear, sigmoid, Gaussian) [151]. Comert etal. [87] achieved accurate fetal state classification by means of the CTG recordings and feed-forward ANN, a structure that included 21 input variables, 10 nodes in a hidden layer, and 3 nodes in an output layer. A test was conducted on a total of 12 training algorithms, including, for example, gradient descent BP, gradient descent with adaptive learning rate BP, resilient BP, conjugate gradient BP with Fletcher-Reeves restarts, or one-step secant BP. The authors achieved the best results with the resilient BP training algorithm and an average of 5707 epochs. Noguchi etal. [153] used substantially more nodes (30) in the hidden layer. The authors used 24 nodes in the input layer and 3 nodes in the output layer in combination with the BP training algorithm. The study outcomes proved that evaluating a CTG recording longer than 50min was difficult and recommended a shorter measuring period to make the analysis more accurate, e.g. 15min and analysing it every 5min. Georgieva etal. [146] employed only 2 neurons in a hidden layer, 12 neurons in an input layer, and 2 neurons in an output layer. Instead of implementing a single ANN, the authors tested a combination of 10 ANNs so that each network was trained in a different section of the dataset and that the result was determined as an average of all 10 outputs. Quasi-Newton BP algorithm [154] and the hyperbolic tangent transfer function were used in all networks. The basic assumption that multiple networks tested on different parts of the dataset can provide better performance, was confirmed. In 2007, Jezewski etal. [147] used a feed-forward ANN to classify fetal condition from CTG recordings and testing several configurations of the used signal features. The best results were achieved by reducing the number of the used features from 21 to 7 (some features did not carry important information about the fetal condition). Since more than 50% of the recordings were of the female patients, where multiple CTG recordings were made, the recording acquired the closest to the date of labour proved to be the most suitable. Comert etal. designed an interesting extension for selecting and extracting features in [149]. In addition to the usual morphological, spectral, and statistical characteristics, they used new features such as contrast, correlation, energy, and homogeneity. This was ensured by transforming signal spectra containing time and frequency information into 8-bit grey images and creating a grey-level co-occurrence matrix (GLCM). The subsequent classification with ANN led to a more accurate classification of the fetal condition by means of CTG compared to using traditional features only. However, using solely GLCM features without the traditional ones did not yield satisfactory results. • Convolutional Neural Networks CNN was used to classify fetal medical state using CTG recordings by Tang etal. [12]. The network contained five convolution blocks (each convolution block contained three convolution layers), three full connection layers, and one softmax layer. CNN was able to classify the fetal medical state into two groups with substantially higher accuracy (ACC = 94.7%) compared to the SVM method (ACC = 83.46%), random forest (ACC = 84.5%), and RNN (ACC = 90.3%). The self-training CNN with eight layers (input, convolution, activation, normalization, pooling, fullyconnected, dropout, and classification layer with softmax function) were implemented by Zhao etal. [108] to predict fetal acidaemia based on features acquired from CTG by means of continuous WT (CWT). Daubechies wavelets and symlet with an order of two and wavelet scales of four, five and six were used. CWT was used to extract the features due to its ability to capture hidden signal characteristics concurrently in the time and frequency domain. In addition, the classic signal features were susceptible to distortion during extraction. The same authors, Zhao etal. [141] slightly improved the classification using a combination of CNN and recurrence plot, which was able to capture non-linear signal characteristics. However, the disadvantage of CNN is the computational complexity and the need to optimally set a large number of parameters for the network to work effectively. • Probabilistic Neural Networks Probabilistic ANN is an implementation of Parzen windows probability density approximation. It is a feed-forward network consisting of four layers (input, pattern, summation and output) [54]. In 2016, Yılmaz [54] presented probabilistic ANN for fetal medical state classification using the CTG. The number of neurons in an input layer was given by the number of features in a dataset (21 neurons). The number of neurons in a pattern layer was given by the number of used training patterns, while each neuron was connected to all neurons in an input layer (1913 neurons for 6 itera- 2573Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring tions and 1914 for 4 iterations), 3 neurons (number of classes) in a summary layer, 1 neuron in an output layer, which applied Bayes decision rule and carried out classification. The optimum value of the smoothing parameter was 0.13. The performance of the method was compared, among other, with MLP containing 2 hidden layers with 20 neurons in each. The classification accuracy was similar in both methods, probabilistic ANN with ACC = 92.15% slightly surpassed MLP with ACC = 90.35%. The high storage needs can be considered as limitation of the method. • Legendre Neural Networks Legendre ANNs are single-layer networks consisting of functional Legendre expansion block based on Legendre polynomials and an output layer. Hidden layers are eliminated, since the input is transformed into higher dimensional space using Legendre polynomials. These networks excel particularly with their simple implementation and speed [155]. Highly accurate classification of fetal state using CTG recordings and the second-order Legendre ANN was designed by Alsayyari [86]. When using 21 attributes, 4 signals out of 1000 were misclassified, with 10 attributes, only 2 signals out of 1000 were misclassified. In addition, only several iterations (5 to 10) were required for training. Legendre ANN had lower computational requirements compared to the Volterra ANN and converged faster with a lower mean square error. The Legendre ANN performance could be improved by increasing the Legendre polynomial order in the testing phase. 3.3.2 Machine Learning inClassification The ML algorithms also proved effective for classification of fetal medical state. The research in this area focused particularly on testing the supervised learning algorithms [43, 46, 72, 88, 89]. • Support Vector Machine One of the important representatives of ML is the SVM method [156] based on supervised learning. The main goal of the algorithm is to assemble a hyperplane so that the space of features has optimal distribution (data belonging to different classes will lie in opposite semi-spaces). In optimal situation, the minimum value of distance of points from the hyperplane is as high as possible. In other words, the maximal margin is as high as possible on both sides around the hyperplane [89, 142]. The hyperplane can be described by only the points on the edge of the band, while there is usually not many of them; these are called support vectors. The kernel transformation allows transforming the originally inseparable task to a linearly separable one, on which an algorithm for finding the separating hyperplane can be applied [89]. SVM seems to be a very promising technique for classification and prediction of fetal medical state using CTG recordings. In the study of Nagendra etal. [88], the SVM method yielded accuracy similar to random forest (the average ACC > 99% in both cases). However, the SVM algorithm performed slightly better with suspect signals. Comparison studies [11, 13] had similar outcomes and concluded that the SVM method performed better than algorithms such as ANN, k-NN, or decision tree. The SVM method had another particular advantage over ANNs—it did not require many model parameters and always found a global solution during the training. An important factor for acquiring high-quality results from CTG recordings is to select suitable signal features that will serve as the classification algorithm input. Lunghi etal. [148] used a total of nine features for the classification, originating from the time and frequency domains, morphological features, and regularity parameters. They achieved the most accurate classification in a test phase, using only six features. Other features carried less information and could be therefore omitted. Appropriate feature selection and dataset balancing were also highlighted as key prerequisites for accurate CTG classification using SVM by Ricciardi etal. [157]. The optimal feature subset could be found with FA according to Subha etal. [78] or GA according to Ocak etal. [72], which was able to detect the most important features and ignore the irrelevant ones. This led to the maximization of the subsequent classification by means of SVM and, at the same time, to the reduction of the number of used features (from 21 to 13). As Krupa etal. [142] proved, feature extraction from CTG could also be done with the EMD method, which decomposed the input signal to individual IMFs. High-frequency IMFs were eliminated and a standard deviation value was calculated for the remaining ones. Standard deviations were considered as signal features and served as the input of a SVM classifier, which classified them into two groups: normal and at risk. Silwattananusarn etal. [89] proposed improving the stability of CTG signal features in order to improve the performance of SVM with polynomial kernel function. To do this, a combination of two feature search strategy approaches (correlation-based feature selection and information gain) was used. The selected features entered an ensemble of seven SVM classifiers that yielded ACC = 99.85%. A modified version of the classic SVM - least squares SVM (LS-SVM) was designed by Yilmaz etal. [145]. In addition, PSO was used to optimize parameters, leading to an effective classification, but at the cost of increasing the computational complexity of the algorithm. When classifying a fetal state by means of an fHR trace estimated from fMCG, SVM proved to be the best choice compared to MLP and J48 decision tree (also known as C4.5 algorithm), as shown in the experiments 2574 K.Barnova et al. in Snider etal. [44]. Signals were acquired from fetuses with the age of 24–39 gestation weeks, and features used in the classifications were selected from the time (e.g. RR interval mean, RR interval standard deviation) and frequency domain (e.g. peak frequency, kurtosis). All three methods yielded similar accuracy, but SVM with ACC = 66.2% was slightly more accurate than the C4.5 algorithm with ACC = 65.4% and MLP with an overall ACC = 61.4%. • Naive Bayes The naive Bayes probabilistic classification algorithm is the simplest Bayesian network model based on an assumption that there is a strong (naive) independence between the extracted features. Despite its simplicity and unrealistic independence assumption, this algorithm is effective and correct in real-world tasks [158]. The algorithm was tested for classification of fetal state with CTG recordings by Avuclu etal. [46] and achieved ACC = 97.18%. • Decision Trees Among the leading representatives of decision trees used for the interpretation of fetal medical state with CTG is the random forest published by Subasi etal. [150], who achieved ACC = 99.02% in their experiments. Based on the research conducted by Jacob etal. [43], after detecting and eliminating outliers from the CTG recordings, the use of both, the classic random forest and the C4.5 algorithm yielded ACC = 100% (C4.5 is a single tree algorithm based on the concept of information entropy [159]). In some cases, the presence of outliers caused inaccurate diagnosis. Reducing computational cost while maintaining high classification accuracy using random forest was achieved in experiments conducted by Sharma etal. [160]. They combined random forest with enhanced binary bat algorithm (EBBA), which was used for optimized feature set selection and hence for dimensionality reduction. EBBA selected only a set of 11 out of 21 possible features for classification while achieving ACC = 96.21%. A similar results were obtained when EBBA was combined with decision tree (ACC = 94.36%) or with k-NN (ACC = 94.67%). According to the authors, further improvements could be achieved by hybridization of various nature inspired algorithms. 3.3.3 Fuzzy Logic inClassification Fuzzy logic classification is based on determining the degree of truth of an feature into a fuzzy class represented by a membership function. Features are classified by means of a set of fuzzy rules based on linguistic values of its attributes [161, 162]. The relevance and redundancy of the resulting classification should be considered in the final decision [161]. Jezewski etal. [68] implemented fuzzy logic in the classification of fetal medical state with CTG recordings. To simplify the fuzzy classifier rule base, they combined the fuzzy classifier with 𝜖 -insensitive distance. When classifying CTG signals into 2 classes using 12 signal features and evaluating the accuracy of classification using negative predictive value (NPV) and PPV parameters, very high NPV=97.63% was achieved, but with low PPV=40.17%. The drawback of the algorithm was the necessity of 𝜖 parameter tuning, which could be overcome by implementing the ES algorithm, as shown in their previous research [75]. The classification of fetal state using fHR traces acquired from fPCG signals into three groups (normal, abnormal and suspicious) by means of fuzzy logic was presented by Chourasia etal. [66]. An envelope of the signal filtered by the WT method was detected by means of the Hilbert transform (HT) and converted into a series of rectangular pulses. These pulses were used to identify S 1 and S 2 sounds and calculate the fHR. Four features were extracted from each signal (baseline fHR, baseline variability, accelerations, and decelerations), followed by their classification by means of the fuzzy logic. The testing was conducted on real recordings and CTG was measured concurrently with fPCG. Medical experts used a CTG recording to create a reference classifications, which were used to evaluate the accuracy of classification by means of fPCG and fuzzy logic. Application of type-2 fuzzy logic with Mamdani type fuzzy inference system and Gaussian membership functions yielded ACC = 92.24%, which was substantially better than type-1 fuzzy logic, which yielded ACC = 81.03%. The results acquired with type-2 fuzzy logic were comparable with the results of the classification with ANFIS (ACC=92%) presented by the same authors in [91]. The five-layered ANFIS, the first-order Sugeno model, Gaussian membership functions were used, 961 epochs and 2–5 membership functions. Chourasia etal. used the same methodology to classify fetal state from an fHR trace acquired from fPCG also in [90], but for the final classification, MLP trained by an adaptive BP algorithm was used. The input network layer consisted of ten neurons, two tan-sigmoid hidden layers (ten and five neurons) and a linear output layer of three neurons. MLP yielded ACC = 95.7%, surpassing fuzzy logic and ANFIS. Recording and analysis of fPCG signals was difficult in women with high BMI values. • Fuzzy Unordered Rule Induction Algorithm FURIA is a fuzzy rule-based classification algorithm that excels primarily in datasets with many features. Its characteristic attribute is that the rule set is generated for each class as one-vs-rest [65, 163]. Each class is therefore separated from other classes and no single class is prioritized as a default prediction. In addition, there is no default rule and the order of rules is irrelevant [163]. An estimate of membership function plays a key role in the application of fuzzy sets. According to the study of Das etal. 2575Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring [65] conducted in 2014, ANN proved suitable for estimating a membership function. Compared to the FURIA approach presented earlier in 2013 by the same authors [164], using the combination of ANN and FURIA for classification of fetal medical state using CTG led to a reduction of error rate with pathological recordings and to an increase of suspicious recordings detection accuracy. 4 Summary andDiscussion The review showed that the current research in this area focuses on improving conventional CTG as well as on alternative fECG, fPCG, and fMCG techniques for monitoring fetal cardiac activity. Fetal cardiac signals acquired by these techniques carry very important information about the medical state of the fetus. However, these complex and often very long signals are relatively difficult to analyse and correctly interpret without using information technology. In addition, the environmental effects, biological tissues, and movements of the mother and the fetus make the use of clinical information difficult, rendering the use of signal processing methods inevitable. With the developments in science and technology, it was possible to implement and test plenty of AI-based and ML-based algorithm in the recent past, which appear to be more effective than conventional signal processing methods. Unfortunately, it was rather difficult to objectively compare the algorithms mentioned in this review, as the authors used different signals (real or synthetic) originating from different sources (publicly accessible databases or their own measured signals) with different quality (various types and noise levels) and they were not unified even in the applied evaluation parameters (ACC, SE, PPV, F1, SP, PPA, NPV or SNR imp ). The authors did not evaluate the quality of extraction by means of statistic parameters in some cases, but merely visually evaluated the extracted signals. These criteria should be unified in future research and create one extensive dataset (similar to the case of CTG and the existing UCI CTG dataset [144]), which would be the only dataset used for objective comparison of the algorithms. For these reasons, we tried to summarize the performance of the presented algorithms both objectively and subjectively and to highlight the most important findings and outline the directions, in which researchers in the field of EFM related to AI should be heading in the future. 4.1 Noise Suppression Effective noise suppression appears to be a great challenge, particularly in the case of fECG and fPCG. Based on the statistic results of each method summarized in Table2 and based on a subjective comparison of the extracted signals in each study, one could summarize that most of the tested ANNs were effective. The different performances of algorithms could be caused by a different dataset used in the testing or by using less suitable algorithm parameter settings, which have a major impact on the extraction quality. The need to set up large number of parameters and the rather demanding computation are among the main limitations of ANNs. In case the parameters are set up incorrectly, the performance of the methods is substantially affected, leading to reduction of the method’s effectiveness. This effect of suitable parameter settings on the resulting performance of an algorithm for extracting fECG for a simple ADALINE network is demonstrated using a 3D plot and extracted fECG signals in Fig.6. The example shows the effect of the input space (p) and the learning rate ( 𝜂 ) parameters on the ACC parameter value. As shown in Fig.6a, the algorithm working area is marked red and corresponds to an area of p ∈ (50;100) ⋂ 𝜂 ∈ (0.001;0.06). It is an area where the algorithm was stable and reached ACC > 85%. Setting the algorithm parameters outside the working area led to a deteriorated performance of the algorithm. As illustrated in Fig.6b, the algorithm was unable to eliminate the maternal component with the p=20 and 𝜂 =0.064 setting, which led to a very low ACC = 66.20%. The global maximum was reached with p=100 and 𝜂 =0.026 setting and led to (Fig.6c) sufficient suppression of the mECG resulting in ACC = 88.84%. Further, this review showed that nature-inspired optimization algorithms are effective for finding optimal parameter values of extraction algorithms. However, despite improvements in the performance of extraction algorithms, they might be computationally more expensive than conventional learning algorithms (e.g. BP). To improve the algorithm performance and to determine of the optimal setting faster, the ANNs should be combined with modern optimization algorithms (e.g. grey wolf optimizer (GWO) [170] or whale optimization algorithm [171]) or other improved hybrid versions of these algorithms (e.g. improved PSO-GWO algorithm with chaos and a new adaptive inertial weight [172]). The use of an accurate and time effective extraction algorithm would allow its implementation in devices operating in real time. Nevertheless, in some cases, even after optimizing the algorithm parameters, it is almost impossible to eliminate the maternal component. These are cases that use input aECG signals with poor quality (low magnitude of fetal component compared to the maternal one, presence of other interferences). Influence of input aECG signals quality on the resulting efficiency of fECG extraction using the ANFIS algorithm is shown in Fig.7. Figure7a represents aECG signals acquired with high quality and adequate magnitude of fetal component compared to the maternal one, leading 2576 K.Barnova et al. Table 2 Overview of AI-based algorithms and their use for noise suppression Author, source Technique Method Dataset Result Kaleem and Kokate [21] fECG ANN Real dataset (not specified) – Ayat etal. [56] fECG Polynomial ANN Own real, simulated dataset (not specified) – Assaleh and Al-Nashash [55] DaISy – Ahmadi etal. [106] fECG Polynomial ANN-WT Own real, own simulated dataset – Fotiadou and Vullings [19] fECG CNN Own simulated dataset SNR imp = 9.5 dB Almadani etal. [109] fECG U-Nets Challenge2013 F1 = 98.9% ADFECGDB F1 = 99.88% Jagannath etal. [98] fECG CNN-Bayesian filter DaISy, simulated dataset (not specified) SNR imp = 32.98 dB Jagannath etal. [57] fECG CNN-Bayesian filter DaISy, simulated dataset (not specified) SNR imp = 39.73 dB Deep belief ANN-Bayesian filter SNR imp = 39.54 dB ANN-Bayesian filter SNR imp = 39.45 dB Golzan etal. [80] fECG MLP NIFECGDB ACC = 94.86% SE = 96.49% PPV = 93.79% Zhou etal. [22] fECG LSTM DaISy, FECGSYNDB SNR imp = 4.9 dB Ghonchi etal. [112] fECG AE-LSTM NIFECGDB, Challenge 2013 ACC = 92.40% SE = 94.30% PPV = 96.67% F1 = 95.45% Behar etal. [62] fECG ESN-grid search NIFECGDB, own real dataset SE = 91.4% PPV = 88.9% F1 = 90.2% Behar etal. [61] fECG ESN-grid search NIFECGDB, own real dataset SE = 87.6% PPV = 86.5% F1 = 87.9% ESN-random search SE = 87.6% PPV = 85.5% F1 = 85.6% Amin etal. [115] fECG ADALINE Not specified – Reaz and Lee Sze Wei [116] Not specified – Kahankova etal. [51] NIFECGDB, own simulated dataset – Assaleh [58] fECG ANFIS DaISy, own simulated dataset – Ahmadieh and Asl [117] DaISy, own simulated dataset – Emuoyibofarhe etal. [118] Not specified – Saranya. and Priyadharsini [59] fECG PSO-ANFIS Simulated dataset (not specified) – Nasiri [77] DaISy, own simulated dataset – Elmansouri etal. [119] Own simulated dataset – Panigrahy and Sahu [74] fECG EKS-DE-ANFIS Challenge 2013, NIFECGDB ACC = 90.66% SE = 94.21% PPV = 96.05% Swarnalath and Prasad [120] fECG ANFIS-WT Real dataset (not specified) ACC = 100% SE = 100% PPV = 100% Jothi and Prabha [121] Own simulated dataset – Kumar and Prasad [123] Own simulated dataset – Hemajothi and Prabha [122] Simulated dataset (not specified) – Al-Zaben and Al-Smadi [124] fECG SVD-ANFIS DaISy, own simulated dataset – Skutova etal. [60] fPCG ANFIS Own simulated dataset – Kockanat and Kockanat [73] fECG DE-adaptive algorithm DaISy – 2577Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring ADFECGDB—Abdominal and Direct Fetal Electrocardiogram Database [165]: 5 real recordings containing 4 aECGs and 1 signal from scalp electrode DaISy—A Database for Identification of Systems [166]: 1 real recording containing 5 aECGs and 2 mECGs T NIFECGDB—Non-Invasive Fetal Electrocardiogram Database [167]: 55 real recordings containing 4 aECGs and 2 mECGs T Challenge 2013—PhysioNet/Computing in Cardiology Challenge 2013 [168]: 75 real recordings containing 4 aECGs FECGSYNDB—Fetal ECG Synthetic Database [169]: 5 simulated recordings containing 4 aECGs and 1 mECG T Table 2 (continued) Author, source Technique Method Dataset Result Panigrahy etal. [128] fECG PSO-EKS DaISy, NIFECGDB ACC = 89.7% SE = 93.2% PPV = 94.97% Anoop etal. [76] fECG PSO-adaptive algorithm Real dataset (not specified) – Jibia and Jibia [79] fECG MFO-LMS Real, simulated dataset (not specified) – 40 100 60 75 0.1 ACC (%) 80 0.075 p (-) 50 (-) 100 0.05 25 0.025 0 40 45 50 55 60 65 70 75 80 85 ACC (%) (a) Time (s) p=20, η=0.064 012345 (b) 012345 Time (s) p=100, η=0.026 (c) Fig. 6 Influence of parameter setting (p and 𝜂 ) on the performance of ADALINE algorithm during extraction of fECG in a form of 3D plot and extracted fECG signals. Example (a) shows 3D plot, example (b) demonstrates an incorrect parameter setting, leading to insufficient suppression of mECG, and example (c) shows optimal parameter setting leading to sufficient elimination of mECG 01234 Time (s) aECG1 aECG2 ANFIS (a) 01234 Time (s) aECG1 aECG2 ANFIS (b) Fig. 7 Influence of input aECG signals quality on the resulting efficiency of fECG extraction. Example (a) shows high-quality aECG signals and effective extraction of fECG using the ANFIS method. On the other hand, example (b) shows poor-quality aECG signals, the use of which leads to insufficient suppression of the maternal component and to an unsatisfactory quality of the fECG 2578 K.Barnova et al. to a high-quality extraction of fECG signal by the ANFIS method. Conversely, Fig.7b shows the effect of poor-quality aECG signals, where the fetal component has low magnitude compared to the maternal component and where the useful fECG signal is contaminated by other interferences. The extraction is very difficult in this case and leads to insufficient suppression of the mECG and to a decrease in filtration quality. The quality of aECG signals is given primarily by the positioning of sensing electrodes, which is currently not a standardised matter and should be a subject of further research. One of the possible solutions to securing effective extraction even with poorly sensed signals might be the implementation of hybrid algorithms that combine the advantages of several AI-based methods (e.g. hybrid fuzzy CNN [173] or CNN-LSTM [174]). When designing and implementing extraction algorithms, the tested algorithms should not alter the morphology of the extracted fECG signals so that a morphological analysis can be done (ST segment or QT interval analysis), thus helping to make the detection of fetal hypoxia more accurate. 4.2 Feature Detection Feature detection in this review included detection of fQRS complexes, estimation of fHR without having to detect R-peaks, and detection of fHSs. AI-based algorithms proved to be very promising for these tasks, even in signals with lower SNR values, which pose a risk of false positive detection of a peak that is not generated by a fetal heart (e.g. mQRS complex, mHS, or residue of another interference). Based on the results summarised in Table3, it can be stated that the most accurate detection was provided by k-means and k-medoids algorithms, which surpassed most of the other algorithms. In addition to that, these algorithms are far quicker than ANNs and simpler from the perspective of algorithm parameter settings. However, very few authors addressed this area in the past and further research is needed. Therefore, it would be useful to test a broader range of AI-based algorithms in the future, especially nature-inspired optimization algorithms for feature selection. These algorithms (e.g. FA algorithm [78] and GA algorithm [72]) has proved to be effective as feature selectors for fetal state classification. It would also be beneficial to conduct research for the purposes of detecting S 2 sounds in fPCG, which are difficult to distinguish and detect in signals with low SNR ratio [175]. Research in the field of fPCG signal analysis might be also beneficial to doctors in detecting pathological heart murmurs. These may be caused by tissue vibrations or when the laminar blood flow changes to turbulent [176], while the detection thereof may contribute to the identification of heart abnormalities (e.g. aortic valve stenosis or mitral stenosis) [16, 176, 177]. 4.3 Fetal State Classification In order to overcome the human intraand inter-observer variation during the evaluation of fetal state, using an automatic intelligent classification system is inevitable. The research focused on testing the classification algorithms used particularly with CTG recordings. Several authors decided to classify a fetal state using fPCG and fMCG recordings as well. Table4 lists the results achieved by individual algorithms used for classification along with corresponding dataset, number of classification classes and number of signal features used. Even in this case, the comparison of individual algorithms was difficult due to the different datasets used. However, when comparing study results that utilized the same UCI CTG dataset [144], it can be concluded that ANN achieved worse results than ML-based algorithms and thus were less suitable for this task. The SVM method and the random forest proved the most effective. The use of fuzzy logic seems to be promising as well. However, this approach was implemented and tested by only a few authors. Therefore, further research in this area is necessary. The research also demonstrated that the selection of algorithm as well as the selection of suitable signal features play a key part in the correct classification. Some authors conducted the classification only based on extracted fHR features [12, 66, 91, 148], some combined these fHR features with uterine contraction features (number of uterine contractions per second) [54, 87, 145, 150], while some others included additional features such as fetal gestation age and maternal temperature during labour [146]. The combination of uterine contraction features and fHR features could substantially affect the classification accuracy, since evaluating the isolated fHR features only might not provide accurate information about the fetus’ reaction to the labour. Fetal pathology may be therefore indicated incorrectly in relation to the fetus’ reaction to uterine contractions [143]. For these reasons, it would be interesting to include other uterine contraction features in the future research such as their length or frequency. One of the areas that have not been addressed enough so far is the classification of fetal medical state by means of fECG signals. Nevertheless, the ability to acquire fECG signal from abdominally acquired recordings for estimating fHR traces as well as the electrohysterographic signal that provides reliable information about uterine contractions (their frequency as well as intensity) makes this technique a very promising instrument. 5 Remaining Challenges andOpen Research Questions The aim of this section is to discuss the remaining challenges and future directions concerning the monitoring of a fetus, as well as the use of AI. Among the main challenges 2579Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring is the issue of selecting suitable input signals when measuring fECG via the mother’s abdomen using a higher number of sensing electrodes. Another important area, particularly with fECG, fPCG, and fMCG, is the absence of high-quality and extensive dataset with a broad range of data that could be used to test conventional algorithm as well as AI-based algorithms. The last area discussed is the use of parallel processing to reduce the computational cost of AI-based algorithms in connection with the use of Big data. 5.1 Selection ofInput Signals One of the interesting areas that might utilize AI is the selection of suitable input signals when measuring fECG. As mentioned earlier, unlike with the ECG performed on adults, the positions of sensing electrodes and their number is not standardised for fECG. Most authors recommend using larger number of sensing electrodes (e.g. Vullings [178] proposed using 8, while Taylor etal. [179] Table 3 Overview of AI-based algorithms and their use for feature detection ADFECGDB—Abdominal and Direct Fetal Electrocardiogram Database [165]: 5 real recordings containing 4 aECGs and 1 signal from scalp electrode Challenge 2013—PhysioNet/Computing in Cardiology Challenge 2013 [168]: 75 real recordings containing 4 aECGs Author, source Technique Method Task Dataset Result Septiyani etal. [83] fECG ANN fQRS detection ADFECGDB ACC = 72.8% Lee etal. [53] fECG CNN fQRS detection Challenge 2013 SE = 89.06% PPV = 92.77% Zhong etal. [85] SE = 80.54% PPV = 75.33% F1 = 77.85% Lo and Tsai [81] fECG STFT-CNN fQRS detection ADFECGDB ACC = 87.58% Vo etal. [84] fECG 1-D octave CNN fQRS detection Challenge 2013 SE=90.32% PPV=91.82% F1=91.1% Krupa etal. [132] fECG MobileNet fQRS detection Challenge 2013 ACC = 91.32% SE = 89.52% PPV = 94.37% F1 = 90.12% Fotiadou etal. [20] fECG Dilated inception fHR estimation Own real dataset, PPA = 98.45% CNN-LSTM Challenge 2013 Lukosevicius and Marozas [82] fECG ESN-dynamic fQRS detection Challenge 2013 – programming Castillo etal. [49] fECG WT-k-medoids fQRS detection ADFECGDB, Challenge 2013 ACC = 97.19% SE = 98.17% PPV = 98.99% F1 = 98.58% Alvarez etal. [47] fECG WT-k-means fQRS detection ADFECGDB ACC = 94.8% WT-k-medoids ACC = 94.5% WT-fuzzy c-means ACC = 93.7% WT-hierarchical clustering ACC = 87.8% Jimenez-Gonzalez and James [48] fPCG ICA-k-means Clustering of Own real dataset SE = 68% ICA components SP = 99% into fHSs, mHSs, maternal respiration and noise Vican etal. [45] fPCG EMD-random forest Detection of S 1 sounds Own real dataset ACC = 72.8% EMD-logistic regression ACC = 66.87% EMD-SVM ACC = 66.83% EMD-MLP ACC = 62.95% 2580 K.Barnova et al. Table 4 Overview of AI-based techniques and their use for fetal state classification Author, source Technique Method Number of classification groups Number of features Dataset Result Comert and Kocamaz [87] CTG ANN 3 21 UCI CTG dataset ACC = 93.6% SE = 88.42% SP = 90.98% Noguchi etal. [153] CTG ANN 3 24 Own real dataset ACC = 86% Georgieva etal. [146] CTG ANN 2 12 Own real dataset SE = 60.3% SP = 67.5% Jezewski etal. [147] CTG ANN 2 7 Own real dataset SE = 83% PPV = 59% SP = 77% NPV = 92% Comert and Kocamaz [149] CTG GLCM-ANN 2 18 CTU-UHB CTG dataset ACC = 87% SE = 88.7% SP = 85.1% Tang etal. [12] CTG SVM 2 9 Own real dataset ACC = 83.46% random forest ACC = 84.5% RNN ACC = 90.3% CNN ACC = 94.7% Zhao etal. [108] CTG CWT-CNN 2 Not specified CTU-UHB CTG dataset ACC = 98.34% SE = 98.22% SP=94.87% Zhao etal. [141] CTG Recurrence plot-CNN 2 Not specified CTU-UHB CTG dataset ACC = 98.69% SE = 99.29% SP=98.1% Yilmaz [54] CTG MLP 3 21 UCI CTG dataset ACC = 90.35% probabilistic ANN ACC = 92.15% Alsayyari [86] CTG Legendre ANN 3 10 UCI CTG dataset ACC= 99.8% Nagendra etal. [88] CTG SVM 3 16 UCI CTG dataset ACC = 99.89% random forest ACC = 99.73% Comert etal. [11] CTG ANN 2 12 CTU-UHB CTG dataset ACC = 77.71% k-NN ACC = 70.47% decision tree ACC = 79.34% SVM ACC = 88.58% Lunghi etal. [148] CTG SVM 3 6 Own real dataset ACC = 84% Ricciardi etal. [157] CTG SVM 2 Not specified Own real dataset ACC = 91% SE = 90.2% SP = 81.8% Ocak [72] CTG GA-SVM 3 13 UCI CTG dataset ACC = 99.65% Subha and Murugan [78] CTG FA-SVM 3 Not specified UCI CTG dataset ACC = 91.95% Krupa etal. [142] CTG EMD-SVM 2 10 Own real dataset ACC = 87% SE = 95% SP = 70% Silwattananusarn etal. [89] CTG SVM ensembles 3 Not specified UCI CTG dataset ACC = 99.85% Yilmaz and Kilikcier [145] CTG LS-SVM-PSO 3 21 UCI CTG dataset ACC = 91.62% Snider and Xu [44] fMCG SVM 2 10 Own real dataset ACC = 66.2% MLP ACC = 61.4% C4.5 algorithm ACC = 65.4% 2581Artificial Intelligence andMachine Learning inElectronic Fetal Monitoring proposed 12 sensing electrodes) so that most of the mother’s abdomen is covered. Sensing electrodes location, as well as fetal position and pregnancy stage, affects the quality of the acquired signals, particularly from the perspective of magnitude and polarity [4]. The quality of each signal can therefore vary with individual sensing electrodes as well as over the course of pregnancy. Since the quality of input signals greatly affects the extraction efficiency, it would be desirable to suggest an AI-based algorithm for automated selection of the high-quality signals. With this, the extraction could be performed effectively and without unnecessary degradation. This approach proved effective for example in Yang etal. [181] for channel selection and classification of electroencephalogram signals using a combined ANN-GA method. A similar approach in the field of NI-fECG for the selection of high quality input aECG signals was proposed by Baldazzi etal. [182]. First, signal quality indices were determined for each aECG signal. And then, these indices served as signal feature for subsequent classification using an ensemble tree classifier into two groups (informative or non-informative aECG signal). 5.2 Lack ofLarge Datasets The key element for the correct use of AIand ML-based algorithm is to have an extensive dataset available with large amount of diverse data (Big data), ideally with a reference class determined by experts. Such dataset is available only for CTG (UCI CTG dataset [144]) created particularly for classification tasks. However, there is no such dataset for fECG, fPCG, and fMCG, which is one of the reasons for limited research in these areas. There are several databases containing units or tens of real recordings that can be used with fECG and fPCG. Most databases contain physiological recordings, while pathological or abnormal signals are rarely included. In the case of fMCG, there is not a single publicly available database with real recordings, which is probably due to the costly and complicated acquisition of fMCG signals. Moreover, determining the reference class can be problematic in some cases, since even doctors might disagree with each other (low extra-observer agreement). A possible solution to overcome this barrier would be to create an extensive database using simulated signals. Although real signals are considered more suitable, there are Table 4 (continued) Author, source Technique Method Number of classification groups Number of features Dataset Result Avuclu and Abdullah [46] CTG Naive Bayes 3 21 UCI CTG dataset ACC = 97.18% SE = 75.67% PPV = 94.67% Subasi etal. [150] CTG Random forest-bagging 2 21 UCI CTG dataset ACC=99.02% F1=99% Jacob and Ramani [43] CTG C4.5 algorithm 3 21 UCI CTG dataset ACC = 100% Random forest ACC = 100% Sharma etal. [160] CTG Random forest 3 11 UCI CTG dataset ACC = 96.21% Decision tree ACC = 94.36% k-NN ACC = 94.67% Jezewski etal. [68] CTG Fuzzy logic𝜖 - insensitive distance 2 12 CTU-UHB CTG dataset SE=74.55% PPV=40.17% SP=90.1% NPV=97.63% Chourasia etal. [66] fPCG WT-HT-fuzzy logic 3 4 Own real dataset ACC = 92.24% Chourasia etal. [91] fPCG WT-HT-ANFIS 3 4 Own real dataset ACC = 92% Chourasia and Tiwari [90] fPCG WT-HT-MLP 3 10 Own real dataset ACC = 95.7% Das etal. [65] CTG ANN-FURIA 3 4 UCI CTG dataset ACC = 92.14% UCI CTG dataset—University of California Irvine CTG dataset [144]: contains features extracted from 2126 real CTG recordings CTU-UHB CTG dataset—Czech Technical University in Prague and the University Hospital in Brno CTG dataset [180]: contains 552 real CTG recordings 2588 K.Barnova et al. 167. Goldberger AL, Amaral LAN, Glass L etal (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. https:// doi. org/ 10. 1161/ 01. CIR. 101. 23. e215 168. Clifford GD, Silva I, Behar J etal (2014) Non-invasive fetal ECG analysis. Physiol Meas 35(8):1521–1536. https:// doi. org/ 10. 1088/ 09673334/ 35/8/ 1521 169. Andreotti F, Behar J, Zaunseder S etal (2016) An open-source framework for stress-testing non-invasive foetal ECG extraction algorithms. Physiol Meas 37(5):627–648. https:// doi. org/ 10. 1088/ 09673334/ 37/5/ 627 170. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61. https:// doi. org/ 10. 1016/j. adven gsoft. 2013. 12. 007 171. Mirjalili S, Lewis A (2016) The whale optimization algorithm. Adv Eng Softw 95:51–67. https:// doi. org/ 10. 1016/j. adven gsoft. 2016. 01. 008 172. Cheng X, Li J, Zheng C etal (2021) An improved PSO-GWO algorithm with chaos and adaptive inertial weight for robot path planning. Front Neurorobot 15:770361. https:// doi. org/ 10. 3389/ fnbot. 2021. 770361 173. Liu Y, Wang L, Zhao L, etal (eds) (2020) Advances in natural computation, fuzzy systems and knowledge discovery. Volume 1. No. 1074 in Advances in intelligent systems and computing. Springer, Cham 174. Cai Z, Zhu Y (2021) A hybrid CNN-LSTM network for hand gesture recognition with surface EMG signals. In: Jiang X, Fujita H (eds) Thirteenth international conference on digital image processing (ICDIP 2021). SPIE, Singapore, p74. https:// doi. org/ 10. 1117/ 12. 26010 74 175. Koutsiana E, Hadjileontiadis LJ, Chouvarda I etal (2017) Fetal heart sounds detection using wavelet transform and fractal dimension. Front Bioeng Biotechnol 5:49. https:// doi. org/ 10. 3389/ fbioe. 2017. 00049 176. Balogh AT (2012) Analysis of the heart sounds and murmurs of fetuses and preterm infants. PhD thesis, Pazmany Peter Catholic University, Budapest 177. Kovács F, Kersner N, Kádár K etal (2009) Computer method for perinatal screening of cardiac murmur using fetal phonocardiography. Comput Biol Med 39(12):1130–1136. https:// doi. org/ 10. 1016/j. compb iomed. 2009. 10. 001 178. Vullings R (2010) Non-invasive fetal electrocardiogram: analysis and interpretation. Citeseer 179. Taylor MJ, Smith MJ, Thomas M etal (2003) Non-invasive fetal electrocardiography in singleton and multiple pregnancies. BJOG 110(7):668–678. https:// doi. org/ 10. 1046/j. 14710528. 2003. 02005.x 180. Chudacek V, Spilka J, Bursa M etal (2014) Open access intrapartum CTG database. BMC Pregnancy Childbirth 14(1):16. https:// doi. org/ 10. 1186/ 147123931416 181. Yang J, Singh H, Hines EL etal (2012) Channel selection and classification of electroencephalogram signals: an artificial neural network and genetic algorithm-based approach. Artif Intell Med 55(2):117–126. https:// doi. org/ 10. 1016/j. artmed. 2012. 02. 001 182. Baldazzi G, Sulas E, Vullings R etal (2023) Automatic signal quality assessment of raw trans-abdominal biopotential recordings for non-invasive fetal electrocardiography. Front Bioeng Biotechnol 11:1059119. https:// doi. org/ 10. 3389/ fbioe. 2023. 10591 19 183. Hazra D, Byun YC (2020) SynSigGAN: generative adversarial networks for synthetic biomedical signal generation. Biology 9(12):441. https:// doi. org/ 10. 3390/ biolo gy912 0441 184. Liu J, Liang X, Ruan W etal (2021) High-performance medical data processing technology based on distributed parallel machine learning algorithm. J Supercomput. https:// doi. org/ 10. 1007/ s1122702104060-4 Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.