Franc Jager

The current trends in the development of methods for non-invasive prediction of premature birth based on the electromyogram of the uterus, i.e., electrohysterogram (EHG), suggest an ever-increasing use of large number of features, complex models, and deep learning approaches. These “black-box” approaches rarely provide insights into the underlying physiological mechanisms and are not easily explainable, which may prevent their use in clinical practice. Alternatively, simple methods using meaningful features, preferably using a single feature (biomarker), are highly desirable for assessing the danger of premature birth. To identify suitable biomarker candidates, we performed feature selection using the stabilized sequential-forward feature-selection method employing learning and validation sets, and using multiple standard classifiers and multiple sets of the most widely used features derived from EHG signals. The most promising single feature to classify between premature EHG records and EHG records of all other term delivery modes evaluated on the test sets appears to be Peak Amplitude of the normalized power spectrum (PA) of the EHG signal in the low frequency band (0.125-0.575 Hz) which closely matches the known Fast Wave Low (FWL) frequency band. For classification of EHG records of the publicly available TPEHG DB, TPEHGT DS, and ICEHG DS databases, using the Partition-Synthesis evaluation technique, the proposed single feature, PA, achieved Classification Accuracy (CA) of 76.5% (AUC of 0.81). In combination with the second most promising feature, Median Frequency (MF) of the power spectrum in the frequency band above 1.0 Hz, which relates to the maternal resting heart rate, CA increased to 78.0% (AUC of 0.86). The developed method in this study for the prediction of premature birth outperforms single-feature and many multi-feature methods based on the EHG, and existing non-invasive chemical and molecular biomarkers. The developed method is fully automatic, simple, and the two proposed features are explainable.

The existing non-invasive automated preterm birth prediction methods rely on the use of uterine electrohysterogram (EHG) records coming from spontaneous preterm and term deliveries, and are indifferent to term induced and cesarean section deliveries. In order to enhance current publicly available pool of term EHG records, we developed a new EHG dataset, Induced Cesarean EHG DataSet (ICEHG DS), containing 126 30-minute EHG records, recorded early (23rd week), and/or later (31st week) during pregnancy, of those pregnancies that were expected to end in spontaneous term delivery, but ended in induced or cesarean section delivery. The records were collected at the University Medical Center Ljubljana, Ljubljana, Slovenia. The dataset includes 38 and 43, early and later, induced; 11 and 8, early and later, cesarean; and 13 and 13, early and later, induced and cesarean EHG records. This dataset enables better understanding of the underlying physiological mechanisms involved during pregnancies ending in induced and cesarean deliveries, and provides a robust and more realistic assessment of the performance of automated preterm birth prediction methods.

Predicting preterm birth is uncertain, and numerous scientists are searching for non-invasive methods to improve its predictability. Current researches are based on the analysis of ElectroHysteroGram (EHG) records, which contain information about the electrophysiological properties of the uterine muscle and uterine contractions. Since pregnancy is a long process, we decided to also characterize, for the first time, non-contraction intervals (dummy intervals) of the uterine records, i.e., EHG signals accompanied by a simultaneously recorded external tocogram measuring mechanical uterine activity (TOCO signal). For this purpose, we developed a new set of uterine records, TPEHGT DS, containing preterm and term uterine records of pregnant women, and uterine records of non-pregnant women. We quantitatively characterized contraction intervals (contractions) and dummy intervals of the uterine records of the TPEHGT DS in terms of the normalized power spectra of the EHG and TOCO signals, and developed a new method for predicting preterm birth. The results on the characterization revealed that the peak amplitudes of the normalized power spectra of the EHG and TOCO signals of the contraction and dummy intervals in the frequency band 1.0-2.2 Hz, describing the electrical and mechanical activity of the uterus due to the maternal heart (maternal heart rate), are high only during term pregnancies, when the delivery is still far away; and they are low when the delivery is close. However, these peak amplitudes are also low during preterm pregnancies, when the delivery is still supposed to be far away (thus suggesting the danger of preterm birth); and they are also low or barely present for non-pregnant women. We propose the values of the peak amplitudes of the normalized power spectra due to the influence of the maternal heart, in an electro-mechanical sense, in the frequency band 1.0-2.2 Hz as a new biophysical marker for the preliminary, or early, assessment of the danger of preterm birth. The classification of preterm and term, contraction and dummy intervals of the TPEHGT DS, for the task of the automatic prediction of preterm birth, using sample entropy, the median frequency of the power spectra, and the peak amplitude of the normalized power spectra, revealed that the dummy intervals provide quite comparable and slightly higher classification performances than these features obtained from the contraction intervals. This result suggests a novel and simple clinical technique, not necessarily to seek contraction intervals but using the dummy intervals, for the early assessment of the danger of preterm birth. Using the publicly available TPEHG DB database to predict preterm birth in terms of classifying between preterm and term EHG records, the proposed method outperformed all currently existing methods. The achieved classification accuracy was 100% for early records, recorded around the 23rd week of pregnancy; and 96.33%, the area under the curve of 99.44%, for all records of the database. Since the proposed method is capable of using the dummy intervals with high classification accuracy, it is also suitable for clinical use very early during pregnancy, around the 23rd week of pregnancy, when contractions may or may not be present.

Predicting preterm birth is uncertain, and numerous scientists are searching for non-invasive methods to improve its predictability. Current researches are based on the analysis of ElectroHysteroGram (EHG) records, which contain information about the electrophysiological properties of the uterine muscle and uterine contractions. Since pregnancy is a long process, we decided to also characterize, for the first time, non-contraction intervals (dummy intervals) of the uterine records, i.e., EHG signals accompanied by a simultaneously recorded external tocogram measuring mechanical uterine activity (TOCO signal). For this purpose, we developed a new set of uterine records, TPEHGT DS, containing preterm and term uterine records of pregnant women, and uterine records of non-pregnant women. We quantitatively characterized contraction intervals (contractions) and dummy intervals of the uterine records of the TPEHGT DS in terms of the normalized power spectra of the EHG and TOCO signals, and developed a new method for predicting preterm birth. The results on the characterization revealed that the peak amplitudes of the normalized power spectra of the EHG and TOCO signals of the contraction and dummy intervals in the frequency band 1.0-2.2 Hz, describing the electrical and mechanical activity of the uterus due to the maternal heart (maternal heart rate), are high only during term pregnancies, when the delivery is still far away; and they are low when the delivery is close. However, these peak amplitudes are also low during preterm pregnancies, when the delivery is still supposed to be far away (thus suggesting the danger of preterm birth); and they are also low or barely present for non-pregnant women. We propose the values of the peak amplitudes of the normalized power spectra due to the influence of the maternal heart, in an electro-mechanical sense, in the frequency band 1.0-2.2 Hz as a new biophysical marker for the preliminary, or early, assessment of the danger of preterm birth. The classification of preterm and term, contraction and dummy intervals of the TPEHGT DS, for the task of the automatic prediction of preterm birth, using sample entropy, the median frequency of the power spectra, and the peak amplitude of the normalized power spectra, revealed that the dummy intervals provide quite comparable and slightly higher classification performances than these features obtained from the contraction intervals. This result suggests a novel and simple clinical technique, not necessarily to seek contraction intervals but using the dummy intervals, for the early assessment of the danger of preterm birth. Using the publicly available TPEHG DB database to predict preterm birth in terms of classifying between preterm and term EHG records, the proposed method outperformed all currently existing methods. The achieved classification accuracy was 100% for early records, recorded around the 23rd week of pregnancy; and 96.33%, the area under the curve of 99.44%, for all records of the database. Since the proposed method is capable of using the dummy intervals with high classification accuracy, it is also suitable for clinical use very early during pregnancy, around the 23rd week of pregnancy, when contractions may or may not be present.

Differentiation between ischaemic and non-ischaemic transient ST segment events of long term ambulatory electrocardiograms is a persisting weakness in present ischaemia detection systems. Traditional ST segment level measuring is not a sufficiently precise technique due to the single point of measurement and severe noise which is often present. We developed a robust noise resistant orthogonal-transformation based delineation method, which allows tracing the shape of transient ST segment morphology changes from the entire ST segment in terms of diagnostic and morphologic feature-vector time series, and also allows further analysis. For these purposes, we developed a new Legendre Polynomials based Transformation (LPT) of ST segment. Its basis functions have similar shapes to typical transient changes of ST segment morphology categories during myocardial ischaemia (level, slope and scooping), thus providing direct insight into the types of time domain morphology changes through the LPT feature-vector space. We also generated new Karhunen and Lo ève Transformation (KLT) ST segment basis functions using a robust covariance matrix constructed from the ST segment pattern vectors derived from the Long Term ST Database (LTST DB). As for the delineation of significant transient ischaemic and non-ischaemic ST segment episodes, we present a study on the representation of transient ST segment morphology categories, and an evaluation study on the classification power of the KLT- and LPT-based feature vectors to classify between ischaemic and non-ischaemic ST segment episodes of the LTST DB. Classification accuracy using the KLT and LPT feature vectors was 90% and 82%, respectively, when using the k-Nearest Neighbors (k = 3) classifier and 10-fold cross-validation. New sets of feature-vector time series for both transformations were derived for the records of the LTST DB which is freely available on the PhysioNet website and were contributed to the LTST DB. The KLT and LPT present new possibilities for human-expert diagnostics, and for automated ischaemia detection.

Introduction: In a prospective study in a tertiary university hospital we wanted to determine whether uterine electromyography (EMG) can differentiate between the active and latent phase of labor.Material and methods: Thirty women presenting at ≥37^0/7 weeks of gestation with regular uterine contractions, intact membranes, and a Bishop score t‐test was used for statistical analysis (p ≤ 0.05 significant). Diagnostic accuracy of EMG was determined by receiver operator characteristics (ROC) analysis. The integral of the amplitudes of the power density spectrum (PDS) corresponding to the PDS energy within the “bursts” of uterine EMG activity was compared between the active and latent labor groups.Results: Seventeen (57%) women were found to be in the active phase of labor and 13 (43%) were in the latent phase. The EMG PDS integral was significantly higher (p = 0.02) in the active (mean 3.40 ± 0.82 μV) compared with the latent (mean 1.17 ± 0.33 μV) phase of labor. The PDS integral had an area under the ROC curve (AUC) of 0.80 to distinguish between active and latent phases of labor, compared with number of contractions on tocodynamometry (AUC = 0.79), and Bishop score (AUC = 0.78). The combination (sum) of PDS integral, tocodynamometry, and Bishop score predicted active phase of labor with an AUC of 0.90.Conclusions: Adding uterine EMG measurements to the methods currently used in the clinics could improve the accuracy of diagnosing active labor.

In this work, we present the development, architecture and evaluation of a new and robust heart beat detector in multimodal records. The detector uses electrocardiogram (ECG) signals, and/or pulsatile ( P ) signals, such as: blood pressure, artery blood pressure and pulmonary artery pressure, if present. The base approach behind the architecture of the detector is collecting signal energy (differentiating and low-pass filtering, squaring, integrating). To calculate the detection and noise functions, simple and fast slope- and peak-sensitive band-pass digital filters were designed. By using morphological smoothing, the detection functions were further improved and noise intervals were estimated. The detector looks for possible pacemaker heart rate patterns and repairs the ECG signals and detection functions. Heart beats are detected in each of the ECG and P signals in two steps: a repetitive learning phase and a follow-up detecting phase. The detected heart beat positions from the ECG signals are merged into a single stream of detected ECG heart beat positions. The merged ECG heart beat positions and detected heart beat positions from the P signals are verified for their regularity regarding the expected heart rate. The detected heart beat positions of a P signal with the best match to the merged ECG heart beat positions are selected for mapping into the noise and no-signal intervals of the record. The overall evaluation scores in terms of average sensitivity and positive predictive values obtained on databases that are freely available on the Physionet website were as follows: the MIT–BIH Arrhythmia database (99.91%), the MGH/MF Waveform database (95.14%), the augmented training set of the follow-up phase of the PhysioNet/Computing in Cardiology Challenge 2014 (97.67%), and the Challenge test set (93.64%).

Elevated transient ischemic ST segment episodes in the ambulatory electrocardiographic (AECG) records appear generally in patients with transmural ischemia (e. g. Prinzmetal's angina) while depressed ischemic episodes appear in patients with subendocardial ischemia (e. g. unstable or stable angina). Huge amount of AECG data necessitates automatic methods for analysis. We present an algorithm which determines type of transient ischemic episodes in the leads of records (elevations/depressions) and classifies AECG records according to type of ischemic heart disease (Prinzmetal's angina; coronary artery diseases excluding patients with Prinzmetal's angina; other heart diseases). The algorithm was developed using 24-hour AECG records of the Long Term ST Database (LTST DB). The algorithm robustly generates ST segment level function in each AECG lead of the records, and tracks time varying non-ischemic ST segment changes such as slow drifts and axis shifts to construct the ST segment reference function. The ST segment reference function is then subtracted from the ST segment level function to obtain the ST segment deviation function. Using the third statistical moment of the histogram of the ST segment deviation function, the algorithm determines deflections of leads according to type of ischemic episodes present (elevations, depressions), and then classifies records according to type of ischemic heart disease. Using 74 records of the LTST DB (containing elevated or depressed ischemic episodes, mixed ischemic episodes, or no episodes), the algorithm correctly determined deflections of the majority of the leads of the records and correctly classified majority of the records with Prinzmetal's angina into the Prinzmetal's angina category (7 out of 8); majority of the records with other coronary artery diseases into the coronary artery diseases excluding patients with Prinzmetal's angina category (47 out of 55); and correctly classified one out of 11 records with other heart diseases into the other heart diseases category. The developed algorithm is suitable for processing long AECG data, efficient, and correctly classified the majority of records of the LTST DB according to type of transient ischemic heart disease.