A method for the automatic reconstruction of fetal cardiac signals from magnetocardiographic recordings

Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes

Objective

Development of novel informatics methods focused on improving pregnancy outcomes remains an active area of research. The purpose of this study is to systematically review the ways that artificial intelligence (AI) and machine learning (ML), including deep learning (DL), methodologies can inform patient care during pregnancy and improve outcomes.

Materials and methods

We searched English articles on EMBASE, PubMed and SCOPUS. Search terms included ML, AI, pregnancy and informatics. We included research articles and book chapters, excluding conference papers, editorials and notes.

Results

We identified 127 distinct studies from our queries that were relevant to our topic and included in the review. We found that supervised learning methods were more popular (n = 69) than unsupervised methods (n = 9). Popular methods included support vector machines (n = 30), artificial neural networks (n = 22), regression analysis (n = 17) and random forests (n = 16). Methods such as DL are beginning to gain traction (n = 13). Common areas within the pregnancy domain where AI and ML methods were used the most include prenatal care (e.g. fetal anomalies, placental functioning) (n = 73); perinatal care, birth and delivery (n = 20); and preterm birth (n = 13). Efforts to translate AI into clinical care include clinical decision support systems (n = 24) and mobile health applications (n = 9).

Conclusions

Overall, we found that ML and AI methods are being employed to optimize pregnancy outcomes, including modern DL methods (n = 13). Future research should focus on less-studied pregnancy domain areas, including postnatal and postpartum care (n = 2). Also, more work on clinical adoption of AI methods and the ethical implications of such adoption is needed.

Developing fetal motor-cardiovascular coordination analyzed from multi-channel magnetocardiography

Fetal movements (FM) related heart rate accelerations (AC) are an important maturation criterion. Since Doppler-based time resolution is not sufficient for accompanying heart rate variability analysis, the work is aimed at a comprehensive FM-AC analysis using magnetocardiographic recordings from fetuses during sleep.We identify FM and AC by independent component analysis and automatic recognition algorithms. We investigate associations between FM and AC of different magnitude by means of event coincidence and time series cross-correlation over the maturation period of 21-40 weeks of gestation (WGA).FM related AC appear with increasing AC magnitude and WGA. Vice versa, AC related FM appear independent of WGA, but more frequently with increasing AC amplitude. The FM-AC correlation exists already at 21 WGA and further increases with WGA while the variability of its time delay decreases. Hence, FM and AC are clearly associated over the whole investigated maturation period. The increase of FM related AC runs parallel to the increasing AC magnitude.The MCG methodology was confirmed and results from previous Doppler-based analyses reproduced. Hence, MCG recordings allow the collective analysis of heart rate variability based maturation indices and FM related AC. This synergism may improve the diagnosis of fetal developmental disorders.

Localization of spontaneous magnetoencephalographic activity of neonates and fetuses using independent component and Hilbert phase analysis

The fetal magnetoencephalogram (fMEG) is measured in the presence of large interference from maternal and fetal magnetocardiograms (mMCG and fMCG). These cardiac interferences can be attenuated by orthogonal projection (OP) technique of the corresponding spatial vectors. However, the OP technique redistributes the fMEG signal among the channels and also leaves some cardiac residuals (partially attenuated mMCG and fMCG) due to loss of stationarity in the signal. In this paper, we propose a novel way to extract and localize the neonatal and fetal spontaneous brain activity by using independent component analysis (ICA) technique. In this approach, we perform ICA on a small subset of sensors for 1-min duration. The independent components obtained are further investigated for the presence of discontinuous patterns as identified by the Hilbert phase analysis and are used as decision criteria for localizing the spontaneous brain activity. In order to locate the region of highest spontaneous brain activity content, this analysis is performed on the sensor subsets, which are traversed across the entire sensor space. The region of the spontaneous brain activity as identified by the proposed approach correlated well with the neonatal and fetal head location. In addition, the burst duration and the inter-burst interval computed for the identified discontinuous brain patterns are in agreement with the reported values.

Independent component analysis of normal and abnormal rhythm in twin pregnancies

We investigated the utility of ICA for evaluation of fetal rhythm in five uncomplicated twin pregnancies and in five twin pregnancies complicated by fetal arrhythmia. Using objective and subjective criteria, we sought to determine how the signal-to-noise ratio, signal fidelity and interference rejection are affected when synthesizing the fetal signal using all the signal-containing ICA components (rank-p ICA) versus using the single dominant component (rank-1 ICA). The signal of each fetus was most commonly distributed over 1 or 2 ICA components, as previously observed in studies of singleton pregnancies; however, in 8 of 26 (31%) cases the signal of each fetus was distributed over 3, 4 or even 5 ICA components. Rank-1 ICA provided the highest SNR and interference rejection, but at the cost of reduced signal fidelity. Our results corroborate that in twin pregnancies, including twin pregnancies complicated by fetal arrhythmia, rank-1 ICA is very effective in isolating the QRS complexes of each fetus; however, it has some limitations when used for fetal rhythm evaluation due to signal distortion. Occasionally, rank-1 ICA completely separates the P-wave and the T-wave from the QRS complex, thus requiring the mixing of several ICA components to achieve acceptable signal fidelity.

The role of independent component analysis in the signal processing of ECG recordings

Independent component analysis (ICA) is an emerging technique for multidimensional signal processing. In recent years, these techniques have been proposed for solving a large number of biomedical applications. This work reviews current knowledge on ICA in electrocardiographic (ECG) analysis. The benefits that ICA can bring to clinical practice are illustrated with four relevant clinical applications: foetal ECG extraction from maternal ECG recordings, analysis of atrial fibrillation, ECG denoising and removal of pacemaker artefacts.

Application of decorrelation-independent component analysis to biomagnetic multi-channel measurements

Biomagnetic multi-channel recordings are typically a superposition of signals from several biological sources of interest and from biological and technical noise sources. Besides averaging, source localization, and spectral analysis to name only a few methods, independent component analysis is an established tool to resolve the superposition present in raw biomagnetic data on a purely statistical basis. Here the time-delayed decorrelation-independent component analysis algorithm is applied to exemplary magnetocardiographic and magnetoencephalographic data and the successful signal separation is demonstrated.

Entropy-based automated classification of independent components separated from fMCG

Fetal magnetocardiography (fMCG) is a noninvasive technique suitable for the prenatal diagnosis of the fetal heart function. Reliable fetal cardiac signals can be reconstructed from multi-channel fMCG recordings by means of independent component analysis (ICA). However, the identification of the separated components is usually accomplished by visual inspection. This paper discusses a novel automated system based on entropy estimators, namely approximate entropy (ApEn) and sample entropy (SampEn), for the classification of independent components (ICs). The system was validated on 40 fMCG datasets of normal fetuses with the gestational age ranging from 22 to 37 weeks. Both ApEn and SampEn were able to measure the stability and predictability of the physiological signals separated with ICA, and the entropy values of the three categories were significantly different at p <0.01. The system performances were compared with those of a method based on the analysis of the time and frequency content of the components. The outcomes of this study showed a superior performance of the entropy-based system, in particular for early gestation, with an overall ICs detection rate of 98.75% and 97.92% for ApEn and SampEn respectively, as against a value of 94.50% obtained with the time-frequency-based system.