Detecting early signs of patient deterioration at home using wearable sensors: a personalized anomaly detection approach

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Heterogeneous patients: Isolation Forest AUROC 0.69, Local Outlier Factor AUROC 0.67; Postoperative patients: Isolation Forest AUROC 0.41, Local Outlier Factor AUROC 0.44

• Primary Outcome: Detection of patient deterioration 24 hours before mortality or unplanned readmission

• Nnt Or Sensitivity: Sensitivity and specificity not reported; REWS comparator achieved AUROC 0.63-0.76

• Confidence Interval: Not reported

Clinical Application

Limited by poor performance in postoperative patients and requirement for continuous sensor data and model updating Relevant to Australian telehealth initiatives and remote patient monitoring programs, but would require TGA approval for clinical decision-making applications Home-monitored patients with wearable sensors, particularly heterogeneous medical patients rather than postoperative patients

Abstract

In the rapidly emerging field of transferring healthcare from hospitals to patients' homes, it is essential that signs of remote deterioration at home should be detected early to timely upscale care when needed. As patient deterioration is a rare event, datasets have insufficient event data for supervised machine learning. Personalized anomaly detection (AD) may be a good alternative. Therefore, this study aimed to obtain insight into the use of personalized AD models in detecting early signs of patient deterioration at home using wearable sensor data. To address this, Isolation Forest and Local Outlier Factor models were applied to detect signs of deterioration in terms of mortality or unplanned readmission in the 24 preceding hours in two datasets: one of heterogeneous patients, the other of postoperative patients. A pipeline was developed for continuously updating personalized AD models over time and applying them to detection windows twice per day. Results were compared with the Remote Early Warning Score. Isolation Forest (AUROC: 0.69) and Local Outlier Factor (AUROC: 0.67) models were able to find some early signs of deterioration in heterogeneous patients (n = 113). However, in postoperative patients (n = 193), Isolation Forest (AUROC: 0.41) and Local Outlier Factor (AUROC 0.44) performed badly. The Remote Early Warning Score was able to find some early signs of deterioration for both groups (AUROC: 0.63-0.76). Based on these findings, three requirements were formulated that should be fulfilled for a potentially successful application of personalized AD. First, the training set should be normal and representative of non-deteriorating patients. Second, signs of deterioration should exhibit abnormal characteristics. Third, non-deteriorating patients should not exhibit abnormal characteristics.

References

1. 1.Garssen, S. H., Oude Wesselink, S. F., Babac, S., Nabben, D. L. J., De Bie Dekker, A. J. R., Nienhuijs, S., Bouwman, A. R., Verhaegh, W. F. J., Doggen, C. J. M., Veldkamp, B. P., & Amir Haeri, M. (2026). Detecting early signs of patient deterioration at home using wearable sensors: a personalized anomaly detection approach. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae55a9