Sensors (Basel, Switzerland) · 2026
A Wearable Morphic Sensor for Unobtrusive Heart Rate and Respiratory Rate Monitoring in ICU Patients: A Pilot Validation Study.
СтатьяВалидационное исследованиеНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Jayarathna Titus, Polley Caitlin, Breen Paul P, Gargiulo Gaetano D, Aneman Anders
Аннотация
PURPOSE: This pilot study evaluated the real-world accuracy of a novel wearable morphic sensor system for unobtrusive, continuous heart rate (HR) and respiratory rate (RR) monitoring in critically ill patients within an intensive care unit (ICU).
METHODS: A hybrid piezoresistive/piezoelectric disk-shaped sensor was placed on patients' backs to capture cardiorespiratory activity via forcecardiographic principles. Data were acquired from 15 ICU patients using a custom wireless recorder. The piezoelectric channel was processed using discrete wavelet transform and an adaptive peak detection algorithm. Derived HR and RR were compared against reference measurements from clinical patient monitors and a ventilator.
RESULTS: Bland-Altman analysis showed a mean bias of -0.39 ± 1.99 beats per minute for HR and 0.06 ± 0.90 breaths per minute for RR. Linear regression revealed strong correlation with clinical monitors (HR R-squared = 0.982; RR R-squared = 0.966). The device's RR performance matched the agreement between two independent clinical reference devices.
CONCLUSION: The proposed system met the pre-specified bias and standard deviation criteria for HR and RR monitoring in bed-bound ICU patients. Its skin-adhesive-free design enables unobtrusive, continuous vital sign surveillance without direct skin contact. These findings support ICU monitoring. Step-down ward and ambulatory applications remain to be validated in future studies.
METHODS: A hybrid piezoresistive/piezoelectric disk-shaped sensor was placed on patients' backs to capture cardiorespiratory activity via forcecardiographic principles. Data were acquired from 15 ICU patients using a custom wireless recorder. The piezoelectric channel was processed using discrete wavelet transform and an adaptive peak detection algorithm. Derived HR and RR were compared against reference measurements from clinical patient monitors and a ventilator.
RESULTS: Bland-Altman analysis showed a mean bias of -0.39 ± 1.99 beats per minute for HR and 0.06 ± 0.90 breaths per minute for RR. Linear regression revealed strong correlation with clinical monitors (HR R-squared = 0.982; RR R-squared = 0.966). The device's RR performance matched the agreement between two independent clinical reference devices.
CONCLUSION: The proposed system met the pre-specified bias and standard deviation criteria for HR and RR monitoring in bed-bound ICU patients. Its skin-adhesive-free design enables unobtrusive, continuous vital sign surveillance without direct skin contact. These findings support ICU monitoring. Step-down ward and ambulatory applications remain to be validated in future studies.