Use of Deep Learning to Detect the Maternal Heart Rate and False Signals on Fetal Heart Rate Recordings.

We have developed deep learning models for automatic identification of the maternal heart rate (MHR) and, more generally, false signals (FSs) on fetal heart rate (FHR) recordings. The models can be used to preprocess FHR data prior to automated analysis or as a clinical alert system to assist the practitioner. Three models were developed and used to detect (i) FSs on the MHR channel (the FSMHR model), (ii) the MHR and FSs on the Doppler FHR sensor (the FSDop model), and (iii) FSs on the scalp ECG channel (the FSScalp model). The FSDop model was the most useful because FSs are far more frequent on the Doppler FHR channel. All three models were based on a multilayer, symmetric, GRU, and were trained on data recorded during the first and second stages of delivery. The FSMHR and FSDop models were also trained on antepartum recordings. The training dataset contained 1030 expert-annotated periods (mean duration: 36 min) from 635 recordings. In an initial evaluation of routine clinical practice, 30 fully annotated recordings for each sensor type (mean duration: 5 h for MHR and Doppler sensors, and 3 h for the scalp ECG sensor) were analyzed. The sensitivity, positive predictive value (PPV) and accuracy were respectively 62.20%, 87.1% and 99.90% for the FSMHR model, 93.1%, 95.6% and 99.68% for the FSDop model, and 44.6%, 87.2% and 99.93% for the FSScalp model. We built a second test dataset with a more solid ground truth by selecting 45 periods (lasting 20 min, on average) on which the Doppler FHR and scalp ECG signals were recorded simultaneously. Using scalp ECG data, the experts estimated the true FHR value more reliably and thus annotated the Doppler FHR channel more precisely. The models achieved a sensitivity of 53.3%, a PPV of 62.4%, and an accuracy of 97.29%. In comparison, two experts (blinded to the scalp ECG data) respectively achieved a sensitivity of 15.7%, a PPV of 74.3%, and an accuracy of 96.91% and a sensitivity of 60.7%, a PPV of 83.5% and an accuracy of 98.24%. Hence, the models performed at expert level (better than one expert and worse than the other), although a well-trained expert with good knowledge of FSs could probably do better in some cases. The models and datasets have been included in the Fetal Heart Rate Morphological Analysis open-source MATLAB toolbox and can be used freely for research purposes.

Identifying Drugs Inducing Prematurity by Mining Claims Data with High-Dimensional Confounder Score Strategies.

BACKGROUND: Pregnant women are largely exposed to medications. However, knowledge is lacking about their effects on pregnancy and the fetus. OBJECTIVE: This study sought to evaluate the potential of high-dimensional propensity scores and high-dimensional disease risk scores for automated signal detection in pregnant women from medico-administrative databases in the context of drug-induced prematurity. METHODS: We used healthcare claims and hospitalization discharges of a 1/97th representative sample of the French population. We tested the association between prematurity and drug exposure during the trimester before delivery, for all drugs prescribed to at least five pregnancies. We compared different strategies (1) for building the two scores, including two machine-learning methods and (2) to account for these scores in the final logistic regression models: adjustment, weighting, and matching. We also proposed a new signal detection criterion derived from these scores: the p value relative decrease. Evaluation was performed by assessing the relevance of the signals using a literature review and clinical expertise. RESULTS: Screening 400 drugs from a cohort of 57,407 pregnancies, we observed that choosing between the two machine-learning methods had little impact on the generated signals. Score adjustment performed better than weighting and matching. Using the p value relative decrease efficiently filtered out spurious signals while maintaining a number of relevant signals similar to score adjustment. Most of the relevant signals belonged to the psychotropic class with benzodiazepines, antidepressants, and antipsychotics. CONCLUSIONS: Mining complex healthcare databases with statistical methods from the high-dimensional inference field may improve signal detection in pregnant women.

Fetal heart rate baseline computation with a weighted median filter.

BACKGROUND: Automated fetal heart rate (FHR) analysis removes inter- and intra-expert variability, and is a promising solution for reducing the occurrence of fetal acidosis and the implementation of unnecessary medical procedures. The first steps in automated FHR analysis are determination of the baseline, and detection of accelerations and decelerations (A/D). We describe a new method in which a weighted median filter baseline (WMFB) is computed and A/Ds are then detected. METHOD: The filter weightings are based on the prior probability that the sampled FHR is in the baseline state or in an A/D state. This probability is computed by estimating the signal's stability at low frequencies and by progressively trimming the signal. Using a competition dataset of 90 previously annotated FHR recordings, we evaluated the WMFB method and 11 recently published literature methods against the ground truth of an expert consensus. The level of agreement between the WMFB method and the expert consensus was estimated by calculating several indices (primarily the morphological analysis discordance index, MADI). The agreement indices were then compared with the values for eleven other methods. We also compared the level of method-expert agreement with the level of interrater agreement. RESULTS: For the WMFB method, the MADI indicated a disagreement of 4.02% vs. the consensus; this value is significantly lower (p<10-13) than that calculated for the best of the 11 literature methods (7.27%, for Lu and Wei's empirical mode decomposition method). The level of inter-expert agreement (according to the MADI) and the level of WMFB-expert agreement did not differ significantly (p=0.22). CONCLUSION: The WMFB method reproduced the expert consensus analysis better than 11 other methods. No differences in performance between the WMFB method and individual experts were observed. The method Matlab source code is available under General Public Licence at http://utsb.univ-catholille.fr/fhr-wmfb.

Prescription drug use during pregnancy in France: a study from the national health insurance permanent sample.

PURPOSE: To provide an up-to-date account of drug prescription during pregnancy in France from 2011 to 2014 using the permanent sample of the French national computerized healthcare database and with a focus on recommended supplementations, fetotoxic drugs and teratogenic drugs. METHODS: All pregnancies identified by the International Classification of Diseases, 10th Revision codes list in the hospitalization database, lasting more than 9 weeks of amenorrhea and whose delivery occurred between 01/01/2011 and 12/31/2014, were included. Drugs delivered between the trimester before and until the end of the pregnancy were included. Drug exposure prevalence was calculated for each year and according to pregnancy trimesters. RESULTS: The study included 28,491 pregnancies with a median number of 9 [5-13] (median [IQ range]) drugs delivered. The most prescribed drug class was antianemia (in 72.5% of exposed). The prescription rate of recommended vitamins (B9 and D) increased over the study period (+10%). Influenza vaccination also increased but remained at a low rate (1%). Exposure to fetotoxic drugs decreased as pregnancy advanced. Exposure to the main teratogenic antiepileptics was stable over the study period. Low-income pregnant women had a higher average drug consumption except for recommended vitamins. CONCLUSION: Pregnant French women are among the largest consumers of prescription medications worldwide. Overall, the dispensation trends observed in this study are in line with the recommendations of the French National College of Gynecologists and Obstetricians. Nevertheless, while being low, exposure to fetotoxic drugs, teratogenic drugs or those under safety alerts still occurred. Supplementations and vaccines in low-income pregnant women should also be increased.

Baseline fetal heart rate analysis: eleven automatic methods versus expert consensus.

Visual analysis of fetal heart rate (FHR) during labor is subject to inter- and intra-observer variability that is particularly troublesome for anomalous recordings. Automatic FHR analysis has been proposed as a promising way to reduce this variability. The major difficulty with automatic analysis is to determine the baseline from which accelerations and decelerations will be detected. Eleven methods for automatic FHR analysis were reprogrammed using description from the literature and applied to 66 FHR recordings collected during the first stage of delivery. The FHR baselines produced by the automatic methods were compared with the baseline defined by agreement among a panel of three experts. The better performance of the automatic methods described by Mongelli, Lu, Wrobel and Pardey was noted despite their different approaches on signal processing. Nevertheless, for several recordings, none of the automatic studied methods produced a baseline similar to that defined by the experts.