Search

Objective. Monitoring of apnea of prematurity, performed in neonatal intensive care units by detecting central apneas (CAs) in the respiratory traces, is characterized by a high number of false alarms. A two-step approach consisting of a threshold-based apneic event detection algorithm followed by a machine learning model was recently presented in literature aiming to improve CA detection. However, since this is characterized by high complexity and low precision, we developed a new direct approach that only consists of a detection model based on machine learning directly working with multichannel signals. Approach. The dataset used in this study consisted of 48 h of ECG, chest impedance and peripheral oxygen saturation extracted from 10 premature infants. CAs were labeled by two clinical experts. 47 features were extracted from time series using 30 s moving windows with an overlap of 5 s and evaluated in sets of 4 consecutive moving windows, in a similar way to what was indicated for the two-step approach. An undersampling method was used to reduce imbalance in the training set while aiming at increasing precision. A detection model using logistic regression with elastic net penalty and leave-one-patient-out cross-validation was then tested on the full dataset. Main results. This detection model returned a mean area under the receiver operating characteristic curve value equal to 0.86 and, after the selection of a FPR equal to 0.1 and the use of smoothing, an increased precision (0.50 versus 0.42) at the expense of a decrease in recall (0.70 versus 0.78) compared to the two-step approach around suspected apneic events. Significance. The new direct approach guaranteed correct detections for more than 81% of CAs with length L≥ 20 s, which are considered among the most threatening apneic events for premature infants. These results require additional verifications using more extensive datasets but could lead to promising applications in clinical practice.

Objective. Less invasive surfactant administration (LISA) has been introduced to preterm infants with respiratory distress syndrome on continuous positive airway pressure (CPAP) support in order to avoid intubation and mechanical ventilation. However, after this LISA procedure, a significant part of infants fails CPAP treatment (CPAP-F) and requires intubation in the first 72 h of life, which is associated with worse complication free survival chances. The aim of this study was to predict CPAP-F after LISA, based on machine learning (ML) analysis of high resolution vital parameter monitoring data surrounding the LISA procedure. Approach. Patients with a gestational age (GA) <32 weeks receiving LISA were included. Vital parameter data was obtained from a data warehouse. Physiological features (HR, RR, peripheral oxygen saturation (SpO 2) and body temperature) were calculated in eight 0.5 h windows throughout a period 1.5 h before to 2.5 h after LISA. First, physiological data was analyzed to investigate differences between the CPAP-F and CPAP-Success (CPAP-S) groups. Next, the performance of two types of ML models (logistic regression: LR, support vector machine: SVM) for the prediction of CPAP-F were evaluated. Main results. Of 51 included patients, 18 (35%) had CPAP-F. Univariate analysis showed lower SpO2, temperature and heart rate variability (HRV) before and after the LISA procedure. The best performing ML model showed an area under the curve of 0.90 and 0.93 for LR and SVM respectively in the 0.5 h window directly after LISA, with GA, HRV, respiration rate and SpO 2 as most important features. Excluding GA decreased performance in both models. Significance. In this pilot study we were able to predict CPAP-F with a ML model of patient monitor signals, with best performance in the first 0.5 h after LISA. Using ML to predict CPAP-F based on vital signals gains insight in (possibly modifiable) factors that are associated with LISA failu

The aim of this study is to develop an explainable late-onset sepsis (LOS) prediction algorithm based on continuously measured multi-channel physiological signals that can be applied to a bedside patient monitor for preterm infants in a neonatal intensive care unit (NICU). The study highlights the complementary predictive value of motion information for LOS prediction when combined with cardiorespiratory information. The algorithm uses features that contain information on heart rate variability (HRV), respiration, and motion, based on continuously measured physiological waveforms including electrocardiogram (ECG) and chest impedance (CI). In this study, 127 preterm infants were included, of whom 59 were blood-culture-proven LOS patients and 68 were control patients. Features in 24 hours before the onset of sepsis (for the LOS group), and an age-matched onset time point (for the control group) were extracted and fed into machine learning classifiers together with gestational age (GA) and birth weight. We compared the prediction performance of several well-known classifiers using features extracted from different signal channels (HRV, respiration, and motion) individually as well as their combinations. The prediction performance was evaluated using the area under the receiver-operating-characteristics curve (AUC). The best performance for LOS prediction was achieved by an XGB classifier combining features from all signal channels, with an AUC of 0.88, a positive predictive value of 0.80, and a negative predictive value of 0.83 during the 6 hours preceding LOS onset. This feasibility study demonstrates the complementary predictive value of motion information in addition to cardiorespiratory information for LOS prediction. Furthermore, visualization of how each feature measured in the individual patient impacts the algorithm decision can strengthen its interpretability. In clinical practice, it is important that clinical interventions are motivated and this visualiza

Apnea of prematurity (AOP) is a critical condition for preterm infants which can lead to several adverse outcomes. Despite its relevance, mechanisms underlying AOP are still unclear. In this work we aimed at improving the understanding of AOP and its physiologic responses by analyzing and comparing characteristics of real infant data and model-based simulations of AOP. We implemented an existing algorithm to extract apnea events originating from the central nervous system from a population of 26 premature infants (1248 h of data in total) and investigated oxygen saturation (SpO2) and heart rate (HR) of the infants around these events. We then extended a previously developed cardio-vascular model to include the lung mechanics and gas exchange. After simulating the steady state of a preterm infant, which successfully replicated results described in previous literature studies, the extended model was used to simulate apneas with different lengths caused by a stop in respiratory muscles. Apneas identified by the algorithm and simulated by the model showed several similarities, including a far deeper decrease in SpO2, with the minimum reached later in time, in case of longer apneas. Results also showed some differences, either due to how measures are performed in clinical practice in our neonatal intensive care unit (e.g. delayed detection of decline in SpO2 after apnea onset due to signal averaging) or to the limited number of very long apneas (≥80 s) identified in our dataset.

Premature infants are at risk of developing serious complications after birth. Communicative interventions performed in neonatal intensive care units (NICUs), such as music therapy interventions, can reduce the stress experienced by these infants and promote the development of their autonomic nervous system. In this study we investigated the effects of music therapy interventions, consisting of singing, humming, talking or rhythmic reading, on premature infants by investigating the effects on their heart rate variability (HRV). A total of 27 communicative intervention from 18 patients were included in this study. The NN-intervals were extracted from the ECG and the mean ± SEM values for the 6 different features (HR, SDNN, RMSSD, pNN50, pDec and SDDec) was investigated. Median feature values for the pre- and communicative intervention were compared using the Wilcoxon signed-rank test. An increase in values for the SDNN, RMSSD and pNN50 was found in the 20 minutes preceding the communicative intervention, when caregiving activities were performed, and was followed by an immediate decrease at the start of the intervention. Features’ variability during the intervention appeared to be smaller than in the pre-communicative intervention, indicating improved autonomic regulation. This difference was, however, not statistically significant possibly due to different types of activities applied during the communicative intervention per patient.

Vital signs are used in Neonatal Intensive Care Units (NICUs) to monitor the state of multiple patients at once. Alarms are triggered if a vital sign is below/above a predefined threshold. Numerous alarms sound each hour which could translate into an overload for the medical team, known as alarm fatigue. Yet many of these alarms do not require immediate clinical action of the caregivers. In this paper we automatically detect moments that need an immediate response (i.e. interaction with the patient) of the medical team in NICUs by using caregiver response to the patient, which is based on the interpretation of vital signs and of nonverbal cues (e.g. movements) delivered by patients. The ultimate goal of such approach is to reduce the overload of alarms while maintaining the patient safety. We use features extracted from the electrocardiogram (ECG) and pulse oxymetry (SpO2) sensors of the patient, as most unplanned interactions between patient and caregivers are due to deteriorations. Since in our unit an alarm can only be paused or silenced manually at the bedside, we used this information as a prior for caregiver response. We also propose different labeling schemes for classification, each representative of a possible interaction scenario within the nature of our problem. We accomplished a general detection of caregiver response with a mean AUC of 0.82. We also show that when trained only with stable and truly deteriorating (critical state) samples, the classifiers can better learn the difference between alarms that need no immediate response and those that do. In addition, we present an analysis of the posterior probabilities over time for different labeling schemes, and use it to speculate about the reasons behind some failure cases.