This study in preterm infants was designed to characterize the prognostic potential of several features of heart rate variability (HRV), respiration, and (infant) motion for the predictive monitoring of late-onset sepsis (LOS). In a neonatal intensive care setting, the cardiorespiratory waveforms of infants with blood-culture positive LOS were analyzed to characterize the prognostic potential of 22 features for discriminating control- from sepsis-state, using the Naive Bayes algorithm. Historical data of the subjects acquired from a period sufficiently before the clinical suspicion of LOS was used as control-state whereas data from the 24 hours preceding the clinical suspicion of LOS were used as sepsis-state (test-data). The overall prognostic potential of all features was quantified at three-hourly intervals for the period corresponding to test data by calculating the area under the receiver operating characteristics curve. For the 49 infants studied, features of HRV, respiration, and movement showed characteristic changes in the hours leading up to the clinical suspicion of sepsis, namely an increased propensity towards pathological heart rate decelerations, increased respiratory instability and a decrease in spontaneous infant activity, i.e., lethargy. While features characterizing HRV and respiration can be used to probe the state of the autonomic nervous system, those characterizing movement probe the state of the motor system - dysregulation of both reflects an increased likelihood of sepsis. By using readily interpretable features derived from cardiorespiratory monitoring, opportunities for preemptively identifying and treating LOS can be developed.

Continuously monitoring body movement in preterm infants can have important clinical applications since changes in movement-patterns can be a significant marker for clinical deteriorations including the onset of sepsis, seizures, and apneas. This paper proposes a system and method to monitor body movement of preterm infants in a clinical environment using ballistography. The ballistographic signal (BSG) is acquired using a thin and a film-like sensor that is placed underneath an infant. Manual annotations based on video-recordings served as a reference standard for identifying movement. We investigated the performance of multiple features, constructed from the BSG waveform, to discriminate movement from no movement based on data acquired from 10 preterm infants. Since routine cardiorespiratory monitoring is prone to movement artifacts, we also compared the application of these features on the simultaneously acquired cardiorespiratory waveforms, i.e., the electrocardiogram, the chest impedance, and the photoplethysmogram. The BSG-based-features consistently outperformed those based on the routinely acquired cardiorespiratory waveforms. The best performing BSG-based feature-the signal instability index-had a mean (standard deviation) effect size of 0.90 (0.06), as measured by the area under the receiver operating curve. The proposed system for monitoring body movement is robust to noise, non-obtrusive, and has high performance in clinical settings.

Alarm fatigue is a well-recognized patient safety concern in intensive care settings. Decreased nurse responsiveness and slow response times to alarms are the potentially dangerous consequences of alarm fatigue. The aim of this study was to determine the factors that modulate nurse responsiveness to critical patient monitor and ventilator alarms in the context of a private room neonatal intensive care setting. The study design comprised of both a questionnaire and video monitoring of nurse-responsiveness to critical alarms. The Likert scale questionnaire, comprising of 50 questions across thematic clusters (critical alarms, yellow alarms, perception, design, nursing action, and context) was administered to 56 nurses (90% response rate). Nearly 6000 critical alarms were recorded from 10 infants in approximately 2400 hours of video monitoring. Logistic regression was used to identify patient and alarm-level factors that modulate nurse-responsiveness to critical alarms, with a response being defined as a nurse entering the patient’s room within the 90s of the alarm being generated. Based on the questionnaire, the majority of nurses found critical alarms to be clinically relevant even though the alarms did not always mandate clinical action. Based on video observations, for a median of 34% (IQR, 20–52) of critical alarms, the nurse was already present in the room. For the remaining alarms, the response rate within 90s was 26%. The median response time was 55s (IQR, 37-70s). Desaturation alarms were the most prevalent and accounted for more than 50% of all alarms. The odds of responding to bradycardia alarms, compared to desaturation alarms, were 1.47 (95% CI = 1.21–1.78; <0.001) while that of responding to a ventilator alarm was lower at 0.35 (95% CI = 0.27–0.46; p <0.001). For every 20s increase in the duration of an alarm, the odds of responding to the alarm (within 90s) increased to 1.15 (95% CI = 1.1–1.2; p <0.001). The random effect per infant improved the fit of the model to the data with the response times being slower for infants suffering from chronic illnesses while being faster for infants who were clinically unstable. Even though nurses respond to only a fraction of all critical alarms, they consider the vast majority of critical and yellow alarms as useful and relevant. When notified of a critical alarm, they seek waveform information and employ heuristics in determining whether or not to respond to the alarm. Amongst other factors, the category and duration of critical alarms along with the clinical status of the patient determine nurse-responsiveness to alarms.

Patient monitoring generates a large number of alarms, the vast majority of which are false. Excessive non-actionable medical alarms lead to alarm fatigue, a well-recognized patient safety issue. While multiple approaches to reduce alarm fatigue have been explored, patterns in alarming and inter-alarm relationships, as they manifest in the clinical workspace, are largely a black-box and hamper research efforts towards reducing alarms. The aim of this study is to detect opportunities to safely reduce alarm pressure, by developing techniques to identify, capture and visualize patterns in alarms. Nearly 500 000 critical medical alarms were acquired from a neonatal intensive care unit over a 20 month period. Heuristic techniques were developed to extract the inter-alarm relationships. These included identifying the presence of alarm clusters, patterns of transition from one alarm category to another, temporal associations amongst alarms and determination of prevalent sequences in which alarms manifest. Desaturation, bradycardia and apnea constituted 86% of all alarms and demonstrated distinctive periodic increases in the number of alarms that were synchronized with nursing care and enteral feeding. By inhibiting further alarms of a category for a short duration of time (30 s/60 s), non-actionable physiological alarms could be reduced by 20%. The patterns of transition from one alarm category to another and the time duration between such transitions revealed the presence of close temporal associations and multiparametric derangement. Examination of the prevalent alarm sequences reveals that while many sequences comprised of multiple alarms, nearly 65% of the sequences were isolated instances of alarms and are potentially irreducible. Patterns in alarming, as they manifest in the clinical workspace were identified and visualized. This information can be exploited to investigate strategies for reducing alarms.

In preterm infants, a better understanding and quantification of cardiorespiratory coupling may help improve caregiving by enabling the tracking of maturational changes and subclinical signatures of disease. Therefore, in a study of 20 preterm infants admitted to a neonatal intensive care unit, we analyzed the cardiac and respiratory regulatory mechanisms as well as the coupling between them. In particular, we selectively analyzed coupling from changes in heart rate to respiratory oscillations as well as coupling from respiratory oscillations to the heart rate. Furthermore, we stratified this coupling based on decelerations and accelerations of the heart rate and by inspiration and expiration during respiration while contrasting periods of kangaroo care, an intervention known to enhance autonomic regulation, with periods in the incubator. We identified that preterm infants exhibit cardiorespiratory coupling that is nonsymmetric with regard to the direction of coupling. We demonstrate coupling from decelerations and accelerations of the heart rate to exhalation and inhalation, respectively, both on a beat-to-beat basis as well as with sustained decelerations and accelerations. On the other hand, on average, we also observed coupling from both inspiration and expiration to marginal decelerations in the heart rate. These phenomena, especially coupling from the changes in the heart rate to respiratory oscillations, were sensitive to whether the infant was receiving kangaroo care. NEW & NOTEWORTHY Preterm infants exhibit cardiorespiratory coupling that is nonsymmetric with regard to the direction of coupling; coupling from fluctuations in the heart rate to respiratory oscillations and vice versa are asymmetric. On average, coupling is observable from decelerations or accelerations in the heart rate to inhalation or exhalation, respectively, whereas, on average, both peaks and troughs of respiration exhibit coupling to marginal decelerations in the heart rate.