Zheng Peng

Objective: Neonatal late-onset sepsis (LOS) is a life-threatening condition in preterm infants in neonatal intensive care units (NICUs), with early detection being crucial for improving outcomes. Despite advancements in data-driven prediction models, their generalizability remains uncertain due to a lack of independent validation, particularly on national and international scales. This study evaluates the performance of two LOS prediction models on multiple validation datasets to assess their reliability for clinical implementation. Methods: Two models were validated: (1) a multi-channel feature-based extreme gradient boosting model (MC-XGB) and (2) a deep neural network using raw RR intervals (RR-DNN). Validation was conducted on three NICU datasets: an internal dataset (68 LOS, 100 controls) from the model-development hospital in the Netherlands, a national external dataset (20 LOS, 20 controls) from another Dutch hospital, and an international external dataset (17 LOS, 17 controls) from a U.S. hospital. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) across multiple prediction time windows, with an hourly risk analysis. Results: Both models achieved a peak AUC of 0.82 in the internal dataset, their predictive performance demonstrates variable declines in external datasets. The respective AUCs for RR-DNN and MC-XGB were 0.80 and 0.72 in the national dataset, and 0.69 and 0.60 in the international dataset. This may result from variations in clinical practices, patient demographics, and monitoring technologies. Conclusion: Model performance declined in external validations, highlighting the challenges of implementing predictive models across diverse clinical settings. Significance: This study emphasizes the need for standardized guidelines and improved data sharing to enhance model development and facilitate reliable integration into NICU workflow for improved LOS management.

Objective: Neonatal late-onset sepsis (LOS) is a life-threatening condition in preterm infants in neonatal intensive care units (NICUs), with early detection being crucial for improving outcomes. Despite advancements in data-driven prediction models, their generalizability remains uncertain due to a lack of independent validation, particularly on national and international scales. This study evaluates the performance of two LOS prediction models on multiple validation datasets to assess their reliability for clinical implementation. Methods: Two models were validated: (1) a multi-channel feature-based extreme gradient boosting model (MC-XGB) and (2) a deep neural network using raw RR intervals (RR-DNN). Validation was conducted on three NICU datasets: an internal dataset (68 LOS, 100 controls) from the model-development hospital in the Netherlands, a national external dataset (20 LOS, 20 controls) from another Dutch hospital, and an international external dataset (17 LOS, 17 controls) from a U.S. hospital. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) across multiple prediction time windows, with an hourly risk analysis. Results: RR-DNN achieved the highest AUC (0.82) for LOS prediction within 6 hours in the internal dataset. However, both models exhibited reduced performance in external datasets, likely due to variations in clinical practices, patient demographics, and monitoring technologies. Conclusion: Model performance declined in external validations, highlighting the challenges of implementing predictive models across diverse clinical settings. Significance: This study emphasizes the need for standardized guidelines and improved data sharing to enhance model development and facilitate reliable integration into NICU workflow for improved LOS management.

Monitoring position and movements of preterm infants is important to ensure their well-being and optimal development. This study evaluates the feasibility of a pressure-sensitive fiber-optic mattress (FM), made entirely of plastic, for two-dimensional analysis of preterm infant movements and positioning. Before clinical use, we developed a simple, replicable, and cost-effective test protocol to simulate infant movements and positions, enabling early identification of technical limitations. Using data from 20 preterm infants, we assessed the FM’s potential to monitor posture and limb motion. FM-derived pressure patterns were compared with camera-based manual annotations to distinguish between different positions and out-of-bed moments, as well as limb-specific movements. Bench-test results demonstrated the FM’s sensitivity to motion and pressure changes, supporting its use in preclinical validation. Clinical data confirmed the FM’s reliability in identifying infant positions and movement patterns, showing an accuracy comparable to camera annotations. However, limitations such as calibration, sensitivity to ambient light, and edge-related artifacts were noted, indicating areas for improvement. In conclusion, the test protocol proved effective for early-stage evaluation of smart mattress technologies. The FM showed promising clinical feasibility for non-obtrusive monitoring of preterm infants, though further optimization is needed for robust performance in neonatal care.

Aim: This study aimed to classify quiet sleep, active sleep and wake states in preterm infants by analysing cardiorespiratory signals obtained from routine patient monitors.Methods: We studied eight preterm infants, with an average postmenstrual age of 32.3 ± 2.4 weeks, in a neonatal intensive care unit in the Netherlands. Electrocardiography and chest impedance respiratory signals were recorded. After filtering and R‐peak detection, cardiorespiratory features and motion and cardiorespiratory interaction features were extracted, based on previous research. An extremely randomised trees algorithm was used for classification and performance was evaluated using leave‐one‐patient‐out cross‐validation and Cohen's kappa coefficient.Results: A sleep expert annotated 4731 30‐second epochs (39.4 h) and active sleep, quiet sleep and wake accounted for 73.3%, 12.6% and 14.1% respectively. Using all features, and the extremely randomised trees algorithm, the binary discrimination between active and quiet sleep was better than between other states. Incorporating motion and cardiorespiratory interaction features improved the classification of all sleep states (kappa 0.38 ± 0.09) than analyses without these features (kappa 0.31 ± 0.11).Conclusion: Cardiorespiratory interactions contributed to detecting quiet sleep and motion features contributed to detecting wake states. This combination improved the automated classifications of sleep states.

Movement patterns in preterm infants can offer crucial insights into their physiological state including maturational development and sleep. These patterns can also serve as early indicators of potential deteriorations, such as cerebral palsy, sepsis, and epilepsy. In this study, we investigated a novel two-dimensional optical fiber mat system for the automated monitoring of infant movement, thereby enhancing the efficiency and safety of neonatal care in both neonatal intensive care unit (NICU) and neonatal medium care unit (NMCU). Twenty preterm infants admitted to both NICU and NMCU were enrolled in the study. They underwent monitoring for a duration of 2 to 5 hours using both an optical fiber mat and a camera which provided valuable movement annotations. The signals from the fiber mat were quantified, selected, and then integrated into a consolidated movement signal. This signal was subsequently transformed into binary states, distinguishing between ‘movement’ and ‘still’ based on the distribution of the movement signal. The proposed fiber mat system achieved a mean (standard deviation) area under the receiver operating curve (AUC) of 0.91 (0.05), and an F-score of 0.73 (0.09) when compared to manually annotated video recordings. This study demonstrates the feasibility of continuous movement monitoring for preterm infants within hospital settings. It illustrates the promising potential to evolve into a predictive tool for monitoring patient deterioration through the fusion of physiological information in both hospital environments and within the comfort of homes.

The classification of sleep state in preterm infants, particularly in distinguishing between active sleep (AS) and quiet sleep (QS), has been investigated using cardiorespiratory information such as electrocardiography (ECG) and respiratory signals. However, accurately differentiating between AS and wake remains challenging; therefore, there is a pressing need to include additional information to further enhance the classification performance. To address the challenge, this study explores the effectiveness of incorporating video-based actigraphy analysis alongside cardiorespiratory signals for classifying the sleep states of preterm infants. The study enrolled eight preterm infants, and a total of 91 features were extracted from ECG, respiratory signals, and video-based actigraphy. By employing an extremely randomized trees (ET) algorithm and leave-one-subject-out cross-validation, a kappa score of 0.33 was achieved for the classification of AS, QS, and wake using cardiorespiratory features only. The kappa score significantly improved to 0.39 when incorporating eight video-based actigraphy features. Furthermore, the classification performance of AS and wake also improved, showing a kappa score increase of 0.21. These suggest that combining video-based actigraphy with cardiorespiratory signals can potentially enhance the performance of sleep-state classification in preterm infants. In addition, we highlighted the distinct strengths and limitations of video-based actigraphy and cardiorespiratory data in classifying specific sleep states.

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 visualization method can help to support the clinical decision.