Indwelling arterial lines, the clinical gold standard for continuous blood pressure (BP) monitoring in the pediatric intensive care unit (PICU), have significant drawbacks due to their invasive nature, ischemic risk, and impediment to natural body movement. A noninvasive, wireless, and accurate alternative would greatly improve the quality of patient care. Recently introduced classes of wireless, skin‐interfaced devices offer capabilities in continuous, precise monitoring of physiologic waveforms and vital signs in pediatric and neonatal patients, but have not yet been employed for continuous tracking of systolic and diastolic BP—critical for guiding clinical decision‐making in the PICU. The results presented here focus on materials and mechanics that optimize the system‐level properties of these devices to enhance their reliable use in this context, achieving full compatibility with the range of body sizes, skin types, and sterilization schemes typically encountered in the PICU. Systematic analysis of the data from these devices on 23 pediatric patients, yields derived, noninvasive BP values that can be quantitatively validated against direct recordings from arterial lines. The results from this diverse cohort, including those under pharmacological protocols, suggest that wireless, skin‐interfaced devices can, in certain circumstances of practical utility, accurately and continuously monitor BP in the PICU patient population.
- Award ID(s):
- 1635443
- NSF-PAR ID:
- 10301650
- Date Published:
- Journal Name:
- Proceedings of the National Academy of Sciences
- Volume:
- 117
- Issue:
- 50
- ISSN:
- 0027-8424
- Page Range / eLocation ID:
- 31674 to 31684
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
more » « less
Abstract Continuous monitoring of vital signs is an essential aspect of operations in neonatal and pediatric intensive care units (NICUs and PICUs), of particular importance to extremely premature and/or critically ill patients. Current approaches require multiple sensors taped to the skin and connected via hard‐wired interfaces to external data acquisition electronics. The adhesives can cause iatrogenic injuries to fragile, underdeveloped skin, and the wires can complicate even the most routine tasks in patient care. Here, materials strategies and design concepts are introduced that significantly improve these platforms through the use of optimized materials, open (i.e., “holey”) layouts and precurved designs. These schemes 1) reduce the stresses at the skin interface, 2) facilitate release of interfacial moisture from transepidermal water loss, 3) allow visual inspection of the skin for rashes or other forms of irritation, 4) enable triggered reduction of adhesion to reduce the probability for injuries that can result from device removal. A combination of systematic benchtop testing and computational modeling identifies the essential mechanisms and key considerations. Demonstrations on adult volunteers and on a neonate in an operating NICUs illustrate a broad range of capabilities in continuous, clinical‐grade monitoring of conventional vital signs, and unconventional indicators of health status.
-
more » « less
Abstract Objectives Manual clinical scoring systems are the current standard used for acute asthma clinical care pathways. No automated system exists that assesses disease severity, time course, and treatment impact in pediatric acute severe asthma exacerbations. Working hypothesis: machine learning applied to continuous vital sign data could provide a novel pediatric‐automated asthma respiratory score (pARS) by using the manual pediatric asthma score (PAS) as the clinical care standard.
Methods Continuous vital sign monitoring data (heart rate, respiratory rate, and pulse oximetry) were merged with the health record data including a provider‐determined PAS in children between 2 and 18 years of age admitted to the pediatric intensive care unit (PICU) for status asthmaticus. A cascaded artificial neural network (ANN) was applied to create an automated respiratory score and validated by two approaches. The ANN was compared with the Normal and Poisson regression models.
Results Out of an initial group of 186 patients, 128 patients met inclusion criteria. Merging physiologic data with clinical data yielded >37 000 data points for model training. The pARS score had good predictive accuracy, with 80% of the pARS values within ±2 points of the provider‐determined PAS, especially over the mid‐range of PASs (6‐9). The Poisson and Normal distribution regressions yielded a smaller overall median absolute error.
Conclusions The pARS reproduced the manually recorded PAS. Once validated and studied prospectively as a tool for research and for physician decision support, this methodology can be implemented in the PICU to objectively guide treatment decisions.
-
null (Ed.)Abstract Capabilities for continuous monitoring of pressures and temperatures at critical skin interfaces can help to guide care strategies that minimize the potential for pressure injuries in hospitalized patients or in individuals confined to the bed. This paper introduces a soft, skin-mountable class of sensor system for this purpose. The design includes a pressure-responsive element based on membrane deflection and a battery-free, wireless mode of operation capable of multi-site measurements at strategic locations across the body. Such devices yield continuous, simultaneous readings of pressure and temperature in a sequential readout scheme from a pair of primary antennas mounted under the bedding and connected to a wireless reader and a multiplexer located at the bedside. Experimental evaluation of the sensor and the complete system includes benchtop measurements and numerical simulations of the key features. Clinical trials involving two hemiplegic patients and a tetraplegic patient demonstrate the feasibility, functionality and long-term stability of this technology in operating hospital settings.more » « less
-
null (Ed.)Objective: The objective of the study is to build models for early prediction of risk for developing multiple organ dysfunction (MOD) in pediatric intensive care unit (PICU) patients. Design: The design of the study is a retrospective observational cohort study. Setting: The setting of the study is at a single academic PICU at the Johns Hopkins Hospital, Baltimore, MD. Patients: The patients included in the study were <18 years of age admitted to the PICU between July 2014 and October 2015. Measurements and main results: Organ dysfunction labels were generated every minute from preceding 24-h time windows using the International Pediatric Sepsis Consensus Conference (IPSCC) and Proulx et al. MOD criteria. Early MOD prediction models were built using four machine learning methods: random forest, XGBoost, GLMBoost, and Lasso-GLM. An optimal threshold learned from training data was used to detect high-risk alert events (HRAs). The early prediction models from all methods achieved an area under the receiver operating characteristics curve ≥0.91 for both IPSCC and Proulx criteria. The best performance in terms of maximum F1-score was achieved with random forest (sensitivity: 0.72, positive predictive value: 0.70, F1-score: 0.71) and XGBoost (sensitivity: 0.8, positive predictive value: 0.81, F1-score: 0.81) for IPSCC and Proulx criteria, respectively. The median early warning time was 22.7 h for random forest and 37 h for XGBoost models for IPSCC and Proulx criteria, respectively. Applying spectral clustering on risk-score trajectories over 24 h following early warning provided a high-risk group with ≥0.93 positive predictive value. Conclusions: Early predictions from risk-based patient monitoring could provide more than 22 h of lead time for MOD onset, with ≥0.93 positive predictive value for a high-risk group identified pre-MOD.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1073/pnas.2019786117
