3 Citations (Scopus)

Abstract

Non-contact sensors are gaining popularity in clinical settings to monitor the vital parameters of patients. In this study, we used a non-contact sensor device to monitor vital parameters like the heart rate, respiration rate, and heart rate variability of hemodialysis (HD) patients for a period of 23 weeks during their HD sessions. During these 23 weeks, a total number of 3237 HD sessions were observed. Out of 109 patients enrolled in the study, 78 patients reported clinical events such as muscle spasms, inpatient stays, emergency visits or even death during the study period. We analyzed the sensor data of these two groups of patients, namely an event and no-event group. We found a statistically significant difference in the heart rates, respiration rates, and some heart rate variability parameters among the two groups of patients when their means were compared using an independent sample t-test. We further developed a supervised machine-learning-based prediction model to predict event or no-event based on the sensor data and demographic information. A mean area under curve (ROC AUC) of 90.16% with 96.21% mean precision, and 88.47% mean recall was achieved. Our findings point towards the novel use of non-contact sensors in clinical settings to monitor the vital parameters of patients and the further development of early warning solutions using artificial intelligence (AI) for the prediction of clinical events. These models could assist healthcare professionals in taking decisions and designing better care plans for patients by early detecting changes to vital parameters.

Original languageEnglish
Article number2833
JournalSensors (Switzerland)
Volume18
Issue number9
DOIs
Publication statusPublished - Sep 1 2018

Fingerprint

artificial intelligence
Artificial Intelligence
Artificial intelligence
Renal Dialysis
heart rate
sensors
Sensors
predictions
Heart Rate
Respiratory Rate
respiration
Area Under Curve
spasms
Muscle
Learning systems
Spasm
machine learning
warning
emergencies
muscles

Keywords

  • Artificial intelligence
  • Heart rate
  • Heart rate variability
  • Hemodialysis
  • Non-contact sensor
  • Predictive analytics
  • Respiration rate
  • Supervised machine learning

ASJC Scopus subject areas

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Artificial-intelligence-based prediction of clinical events among hemodialysis patients using non-contact sensor data. / Thakur, Saurabh Singh; Abdul, Shabbir Syed; Shannon Chiu, Hsiao Yean; Roy, Ram Babu; Huang, Po Yu; Malwade, Shwetambara; Nursetyo, Aldilas Achmad; Jack Li, Yu Chuan.

In: Sensors (Switzerland), Vol. 18, No. 9, 2833, 01.09.2018.

Research output: Contribution to journalArticle

@article{0d5d19ad925744e4b27b402ed89bf909,
title = "Artificial-intelligence-based prediction of clinical events among hemodialysis patients using non-contact sensor data",
abstract = "Non-contact sensors are gaining popularity in clinical settings to monitor the vital parameters of patients. In this study, we used a non-contact sensor device to monitor vital parameters like the heart rate, respiration rate, and heart rate variability of hemodialysis (HD) patients for a period of 23 weeks during their HD sessions. During these 23 weeks, a total number of 3237 HD sessions were observed. Out of 109 patients enrolled in the study, 78 patients reported clinical events such as muscle spasms, inpatient stays, emergency visits or even death during the study period. We analyzed the sensor data of these two groups of patients, namely an event and no-event group. We found a statistically significant difference in the heart rates, respiration rates, and some heart rate variability parameters among the two groups of patients when their means were compared using an independent sample t-test. We further developed a supervised machine-learning-based prediction model to predict event or no-event based on the sensor data and demographic information. A mean area under curve (ROC AUC) of 90.16{\%} with 96.21{\%} mean precision, and 88.47{\%} mean recall was achieved. Our findings point towards the novel use of non-contact sensors in clinical settings to monitor the vital parameters of patients and the further development of early warning solutions using artificial intelligence (AI) for the prediction of clinical events. These models could assist healthcare professionals in taking decisions and designing better care plans for patients by early detecting changes to vital parameters.",
keywords = "Artificial intelligence, Heart rate, Heart rate variability, Hemodialysis, Non-contact sensor, Predictive analytics, Respiration rate, Supervised machine learning",
author = "Thakur, {Saurabh Singh} and Abdul, {Shabbir Syed} and {Shannon Chiu}, {Hsiao Yean} and Roy, {Ram Babu} and Huang, {Po Yu} and Shwetambara Malwade and Nursetyo, {Aldilas Achmad} and {Jack Li}, {Yu Chuan}",
year = "2018",
month = "9",
day = "1",
doi = "10.3390/s18092833",
language = "English",
volume = "18",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "9",

}

TY - JOUR

T1 - Artificial-intelligence-based prediction of clinical events among hemodialysis patients using non-contact sensor data

AU - Thakur, Saurabh Singh

AU - Abdul, Shabbir Syed

AU - Shannon Chiu, Hsiao Yean

AU - Roy, Ram Babu

AU - Huang, Po Yu

AU - Malwade, Shwetambara

AU - Nursetyo, Aldilas Achmad

AU - Jack Li, Yu Chuan

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Non-contact sensors are gaining popularity in clinical settings to monitor the vital parameters of patients. In this study, we used a non-contact sensor device to monitor vital parameters like the heart rate, respiration rate, and heart rate variability of hemodialysis (HD) patients for a period of 23 weeks during their HD sessions. During these 23 weeks, a total number of 3237 HD sessions were observed. Out of 109 patients enrolled in the study, 78 patients reported clinical events such as muscle spasms, inpatient stays, emergency visits or even death during the study period. We analyzed the sensor data of these two groups of patients, namely an event and no-event group. We found a statistically significant difference in the heart rates, respiration rates, and some heart rate variability parameters among the two groups of patients when their means were compared using an independent sample t-test. We further developed a supervised machine-learning-based prediction model to predict event or no-event based on the sensor data and demographic information. A mean area under curve (ROC AUC) of 90.16% with 96.21% mean precision, and 88.47% mean recall was achieved. Our findings point towards the novel use of non-contact sensors in clinical settings to monitor the vital parameters of patients and the further development of early warning solutions using artificial intelligence (AI) for the prediction of clinical events. These models could assist healthcare professionals in taking decisions and designing better care plans for patients by early detecting changes to vital parameters.

AB - Non-contact sensors are gaining popularity in clinical settings to monitor the vital parameters of patients. In this study, we used a non-contact sensor device to monitor vital parameters like the heart rate, respiration rate, and heart rate variability of hemodialysis (HD) patients for a period of 23 weeks during their HD sessions. During these 23 weeks, a total number of 3237 HD sessions were observed. Out of 109 patients enrolled in the study, 78 patients reported clinical events such as muscle spasms, inpatient stays, emergency visits or even death during the study period. We analyzed the sensor data of these two groups of patients, namely an event and no-event group. We found a statistically significant difference in the heart rates, respiration rates, and some heart rate variability parameters among the two groups of patients when their means were compared using an independent sample t-test. We further developed a supervised machine-learning-based prediction model to predict event or no-event based on the sensor data and demographic information. A mean area under curve (ROC AUC) of 90.16% with 96.21% mean precision, and 88.47% mean recall was achieved. Our findings point towards the novel use of non-contact sensors in clinical settings to monitor the vital parameters of patients and the further development of early warning solutions using artificial intelligence (AI) for the prediction of clinical events. These models could assist healthcare professionals in taking decisions and designing better care plans for patients by early detecting changes to vital parameters.

KW - Artificial intelligence

KW - Heart rate

KW - Heart rate variability

KW - Hemodialysis

KW - Non-contact sensor

KW - Predictive analytics

KW - Respiration rate

KW - Supervised machine learning

UR - http://www.scopus.com/inward/record.url?scp=85052572165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052572165&partnerID=8YFLogxK

U2 - 10.3390/s18092833

DO - 10.3390/s18092833

M3 - Article

C2 - 30150592

AN - SCOPUS:85052572165

VL - 18

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 9

M1 - 2833

ER -