Extraction of Premature Newborns' Spontaneous Cries in the Real Context of Neonatal Intensive Care Units.

Cry analysis is an important tool to evaluate the development of preterm infants. However, the context of Neonatal Intensive Care Units is challenging, since a wide variety of sounds can occur (e.g., alarms and adult voices). In this paper, a method to extract cries is proposed. It is based on an initial segmentation between silence and sound events, followed by feature extraction on the resulting audio segments and a cry and non-cry classification. A database of 198 cry events coming from 21 newborns and 439 non-cry events was created. Then, a set of features-including Mel-Frequency Cepstral Coefficients-issued from principal component analysis, was computed to describe each audio segment. For the first time in cry analysis, noise was handled using harmonic plus noise analysis. Several machine learning models have been compared. The K-Nearest Neighbours approach showed the best results with a precision of 92.9%. To test the approach in a monitoring application, 412 h of recordings were automatically processed. The cries automatically selected were replayed and a precision of 92.2% was obtained. The impact of errors on the fundamental frequency characterisation was also studied. Results show that despite a difficult context, automatic cry extraction for non-invasive monitoring of vocal development of preterm infants is achievable.

Functional age estimation through neonatal motion characterization using continuous video recordings.

The follow-up of the development of the premature baby is a major component of its clinical care since it has been shown that it can reveal a pathology. However, no method allowing an automated and continuous monitoring of this development has been proposed. Within the framework of the Digi-NewB European project, our team wishes to offer new clinical indices qualifying the maturation of newborns. In this study, we propose a new method to characterize motor activity from video recordings. For this purpose, we have chosen to characterize the motion temporal organization by drawing inspiration from sleep organization. Thus, we propose a fully automatic process allowing to extract motion features and to combine them to estimate a functional age. By investigating two datasets, one of 28.5 hours (manually annotated) from 33 newborns and one of 4,920 hours from 46 newborns, we show that the proposed approach is relevant for monitoring in clinical routine and that the extracted features reflect the maturation of preterm newborns. Indeed, a compact and interpretable model using gestational age and three motion features (mean duration of intervals with motion, total percentage of time spent in motion and number of intervals without motion) was designed to predict post-menstrual age of newborns and showed an admissible mean absolute error of 1.3 weeks. While the temporal organization of motion was not studied clinically due to a lack of technological means, these results open the door to new developments, new investigations and new knowledge on the evolution of motion in newborns.

Preterm Newborn Presence Detection in Incubator and Open Bed Using Deep Transfer Learning.

Video-based motion analysis recently appeared to be a promising approach in neonatal intensive care units for monitoring the state of preterm newborns since it is contact-less and noninvasive. However it is important to remove periods when the newborn is absent or an adult is present from the analysis. In this paper, we propose a method for automatic detection of preterm newborn presence in incubator and open bed. We learn a specific model for each bed type as the camera placement differs a lot and the encountered situations are different between both. We break the problem down into two binary classifications based on deep transfer learning that are fused afterwards: newborn presence detection on the one hand and adult presence detection on the other hand. Moreover, we adopt a strategy of decision intervals fusion in order to take advantage of temporal consistency. We test three deep neural network that were pre-trained on ImageNet: VGG16, MobileNetV2 and InceptionV3. Two classifiers are compared: support vector machine and a small neural network. Our experiments are conducted on a database of 120 newborns. The whole method is evaluated on a subset of 25 newborns including 66 days of video recordings. In incubator, we reach a balanced accuracy of 86%. In open bed, the performance is lower because of a much wider variety of situations whereas less data are available.

Deep transfer learning for video-based detection of newborn presence in incubator.

Preterm newborns are prone to late-onset sepsis, leading to a high risk of mortality. Video-based analysis of motion is a promising non-invasive approach because the behavior of the newborn is related to his physiological state. But it is needed to analyze only images where the newborn is solely present in incubator. In this context, we propose a method for video-based detection of newborn presence. We use deep transfer learning: bottleneck features are extracted from a pre-trained deep neural network and then a classifier is trained with these features on our database. Moreover, we propose a strategy that allows to take advantage of temporal consistency. On a database of 11 newborns with 56 days of video recordings, the results show a balanced accuracy of 80%.

Quiet Sleep Organization of Very Preterm Infants Is Correlated With Postnatal Maturation.

Background: Sleep is an important determinant of brain development in preterm infants. Its temporal organization varies with gestational age (GA) and post-menstrual age (PMA) but little is known about how sleep develops in very preterm infants. The objective was to study the correlation between the temporal organization of quiet sleep (QS) and maturation in premature infants without severe complications during their neonatal hospitalization. Methods: Percentage of time spent in QS and average duration of time intervals (ADI) spent in QS were analyzed from a cohort of newborns with no severe complications included in the Digi-NewB prospective, multicentric, observational study in 2017-19. Three groups were analyzed according to GA: Group 1 (27-30 weeks), Group 2 (33-37 weeks), Group 3 (>39 weeks). Two 8-h video recordings were acquired in groups 1 and 2: after birth (T1) and before discharge from hospital (T2). The annotation of the QS phases was performed by analyzing video recordings together with heart rate and respiratory traces thanks to a dedicated software tool of visualization and annotation of multimodal long-time recordings, with a double expert reading. Results are expressed as median (interquartile range, IQR). Correlations were analyzed using a linear mixed model. Results: Five newborns were studied in each group (160 h of recording). Median time spent in QS increased from 13.0% [IQR: 13-20] to 28.8% [IQR: 27-30] and from 17.0% [IQR: 15-21] to 29.6% [IQR: 29.5-31.5] in Group 1 and 2, respectively. Median ADI increased from 54 [IQR: 53-54] to 288 s [IQR: 279-428] and from 90 [IQR: 84-96] to 258 s [IQR: 168-312] in Group 1 and 2. Both groups reach values similar to that of group 3, respectively 28.2% [IQR: 24.5-31.3] and 270 s [IQR: 210-402]. The correlation between PMA and time spent in QS or ADI were, respectively 0.73 (p < 10-4) and 0.46 (p = 0.06). Multilinear analysis using temporal organization of QS gave an accurate estimate of PMA (r 2 = 0.87, p < 0.001). Conclusion: The temporal organization of QS is correlated with PMA in newborns without severe complication. An automated standardized continuous behavioral quantification of QS could be interesting to monitor during the hospitalization stay in neonatal units.

Activity Recognition Using Complex Network Analysis.

In this paper, we perform complex network analysis on a connectivity dataset retrieved from a monitoring system in order to classify simple daily activities. The monitoring system is composed of a set of wearable sensing modules positioned on the subject's body and the connectivity data consists of the correlation between each pair of modules. A number of network measures are then computed followed by the application of statistical significance and feature selection methods. These methods were implemented for the purpose of reducing the total number of modules in the monitoring system required to provide accurate activity classification. The obtained results show that an overall accuracy of 84.6% for activity classification is achieved, using a random forest classifier, and when considering a monitoring system composed of only two modules positioned at the neck and thigh of the subject's body.

Detection of Levodopa Induced Dyskinesia in Parkinson's Disease patients based on activity classification.

In this paper, we present an activity classification-based algorithm for the automatic detection of Levodopa Induced Dyskinesia in Parkinson's Disease (PD) patients. Two PD patients experiencing motor fluctuations related to chronic Levodopa therapy performed a protocol of simple daily life activities on at least two different occasions. A Random Forest classifier was able to classify the performed activities by the patients with an overall accuracy of 86%. Based on the detected activity, a K Nearest Neighbor classifier detected the presence of dyskinesia with accuracy ranging from 75% to 88%.

Possible predictors of cardiorespiratory events after immunization in preterm neonates.

BACKGROUND: The influence of the first immunization on cardiorespiratory (CR) stability in very preterm infants is still a controversial subject. OBJECTIVES: To describe the changes induced by immunization on heart and respiratory rate variability (HRV-RRV) and to test a potential association between preimmunization profiles and postimmunization CR events. METHODS: Continuous 72-hour CR recordings and 2.5-hour polysomnographic recordings were performed on very preterm infants immunized after 7 weeks. The results are expressed as medians (interquartile ranges). RESULTS: Immunization was performed on 31 very preterm infants [28 weeks' gestation (26.9-29), birth weight: 965 g (795-1,105)], and was associated with an increased incidence (p < 0.01) of events lasting more than 10 s: bradycardia <80 bpm [2.2 (1.1-7) vs. 1.8 (1-4)/12 h], desaturation [17.6 (9.4-36.4) vs. 13.9 (7.7-33.8)/12 h] and associated bradycardia-desaturation [IB+D, 4.1 (1.4-7.3) vs. 2.4 (1-4.6)/12 h], with mild changes in HRV and no change in RRV. The changes in IB+D frequency were correlated with preimmunization IB+D frequency (r = 0.44, p < 0.05), HRV spectral parameter low frequency/high frequency ratio (LF/HF, r = 0.55, p < 0.01) and approximate entropy of HRV (r = -0.39, p < 0.05). CONCLUSION: The increase in CR events after the first immunization in very preterm infants was associated with: (1) sympathetic predominance in heart rate control (high LF/HF ratio), (2) abnormal oversimplification of HRV (low entropy) and (3) persistent respiratory rhythm control immaturity (high IB+D before vaccine).

Surface electrocardiogram reconstruction from intracardiac electrograms using a dynamic time delay artificial neural network.

This study proposes a method to facilitate the remote follow up of patients suffering from cardiac pathologies and treated with an implantable device, by synthesizing a 12-lead surface ECG from the intracardiac electrograms (EGM) recorded by the device. Two methods (direct and indirect), based on dynamic time-delay artificial neural networks (TDNNs) are proposed and compared with classical linear approaches. The direct method aims to estimate 12 different transfer functions between the EGM and each surface ECG signal. The indirect method is based on a preliminary orthogonalization phase of the available EGM and ECG signals, and the application of the TDNN between these orthogonalized signals, using only three transfer functions. These methods are evaluated on a dataset issued from 15 patients. Correlation coefficients calculated between the synthesized and the real ECG show that the proposed TDNN methods represent an efficient way to synthesize 12-lead ECG, from two or four EGM and perform better than the linear ones. We also evaluate the results as a function of the EGM configuration. Results are also supported by the comparison of extracted features and a qualitative analysis performed by a cardiologist.

Exploring time series retrieved from cardiac implantable devices for optimizing patient follow-up.

Current cardiac implantable devices (IDs) are equipped with a set of sensors that can provide useful information to improve patient follow-up and prevent health deterioration in the postoperative period. In this paper, data obtained from an ID with two such sensors (a transthoracic impedance sensor and an accelerometer) are analyzed in order to evaluate their potential application for the follow-up of patients treated with a cardiac resynchronization therapy (CRT). A methodology combining spatiotemporal fuzzy coding and multiple correspondence analysis (MCA) is applied in order to: 1) reduce the dimensionality of the data and provide new synthetic indexes based on the "factorial axes" obtained from MCA; 2) interpret these factorial axes in physiological terms; and 3) analyze the evolution of the patient's status by projecting the acquired data into the plane formed by the first two factorial axes named "factorial plane." In order to classify the different evolution patterns, a new similarity measure is proposed and validated on the simulated datasets, and then, used to cluster observed data from 41 CRT patients. The obtained clusters are compared with the annotations on each patient's medical record. Two areas on the factorial plane are identified, one being correlated with a health degradation of patients and the other with a stable clinical state.

Blind source separation for ambulatory sleep recording.

This paper deals with the conception of a new system for sleep staging in ambulatory conditions. Sleep recording is performed by means of five electrodes: two temporal, two frontal and a reference. This configuration enables to avoid the chin area to enhance the quality of the muscular signal and the hair region for patient convenience. The electroencephalopgram (EEG), eletromyogram (EMG), and electrooculogram (EOG) signals are separated using the Independent Component Analysis approach. The system is compared to a standard sleep analysis system using polysomnographic recordings of 14 patients. The overall concordance of 67.2% is achieved between the two systems. Based on the validation results and the computational efficiency we recommend the clinical use of the proposed system in a commercial sleep analysis platform.