JMIR Publications

ABSTRACT

Background:

In 2022, over 18,000 patients aged ≥70 years were hospitalized in the Netherlands for a hip fracture, with 50% requiring geriatric rehabilitation after surgery. Increasing geriatric rehabilitation patient numbers, staff shortages, and rising pressure on healthcare budgets makes adequate care challenging. To make geriatric rehabilitation more future-proof, a stronger focus on home-based rehabilitation is needed. Early identification of patients likely to be discharged soon enables timely discharge planning and coordination of support at home. Early geriatric rehabilitation discharge planning may help organize home-based rehabilitation more effectively by arranging home care services in advance. This can facilitate smoother transitions towards home and prevent discharge delays, which is important to ensure optimal bed occupancy.

Objective:

This study aims to develop machine learning (ML) models to predict a geriatric rehabilitation stay of ≤ 4 weeks in a skilled nursing home for older patients after hip fracture surgery, using continuously monitored physical activity data from the first week of geriatric rehabilitation and patient characteristics.

Methods:

This prospective cohort study (January 2019-August 2024) included 100 patients. Patient characteristics and physical activity data from the MOX1 accelerometer during the first rehabilitation week were collected. Principal component analysis was used to reduce the physical activity features. Eight ML models were developed using Bayesian hyperparameter optimization and refined if necessary. The performance of the ML models was evaluated and the most important features for predicting the length of geriatric rehabilitation stay were identified.

Results:

The support vector machines (SVM) showed the best performances, with nineteen and eighteen out of twenty correct predictions (accuracy = 0.95 and 0.90, F1-score = 0.95238 and 0.90909, AUC = 0.97 and 0.95). The most important features for predicting the length of geriatric rehabilitation stay across all ML models included the continuously monitored physical activity data; Age; Katz-ADL6 at hospital discharge; surgery type; FAC at hospital discharge; gender; MoCa; Availability of non-professional help; premorbid living situation; ASA score; time in the ER; and CCI.

Conclusions:

This study developed several ML models which proved to be highly accurate in predicting a geriatric rehabilitation stay of ≤ 4 weeks in a skilled nursing home for older patients after hip fracture surgery.