Patient Ambulations Predict Hospital Readmission
Authors:
- 1 November 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
- Vol. 2021, 7506-7510
Abstract
Improved functional ability and physical activity are strongly associated with a broad range of positive health outcomes including reduced risk of hospital readmission. This study presents an algorithm for detecting ambulations from time-resolved step counts gathered from remote monitoring of patients receiving hospital care in their homes. It examines the statistical power of these ambulations in predicting hospital readmission. A diverse demographic cohort of 233 patients of age 70.5±16.8 years are evaluated in a retrospective analysis. Eleven statistical features are derived from raw time series data, and their F-statistics are assessed in discriminating between patients who were and were not readmitted within 30 days of discharge. Using these features, logistic regression models are trained to predict readmission. The results show that the fraction of days with at least one ambulation was the strongest feature, with an F-statistic of 17.2. The models demonstrate AUROC performances of 0.741, 0.766 and 0.769 using stratified 5-fold train-test splits in all included patients (n=233), congestive heart failure (CHF, n=105) and non-CHF (n=128) patient subgroups, respectively. This study suggests that patient ambulation metrics derived from wearable sensors can offer powerful predictors of adverse clinical outcomes such as hospital readmission, even in the absence of other features such as physiological vital signs.Index Terms—readmission, ambulation, step count, heart failure, physical activity, regression, actigraphy, accelerometer.Keywords
This publication has 12 references indexed in Scilit:
- Hospital-Level Care at Home for Acutely Ill AdultsAnnals of Internal Medicine, 2020
- Validity of accelerometry in step detection and gait speed measurement in orthogeriatric patientsPLOS ONE, 2019
- Step-Count Accuracy of 3 Motion Sensors for Older and Frail Medical InpatientsArchives of Physical Medicine and Rehabilitation, 2017
- An Activity Index for Raw Accelerometry Data and Its Comparison with Other Activity MetricsPLOS ONE, 2016
- International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital ReadmissionsJAMA Internal Medicine, 2016
- Promoting mobility and reducing length of stay in hospitalized general medicine patients: A quality‐improvement projectJournal of Hospital Medicine, 2016
- The Prevention of Hospital Readmissions in Heart FailureProgress in Cardiovascular Diseases, 2016
- Using the LACE index to predict hospital readmissions in congestive heart failure patientsBMC Cardiovascular Disorders, 2014
- Exercise-based rehabilitation for heart failureCochrane Database of Systematic Reviews, 2014
- Activity classification and dead reckoning for pedestrian navigation with wearable sensorsMeasurement Science and Technology, 2008