Background: Approximately 50% of older patients hospitalized for hip fractures are admitted to a geriatric rehabilitation department at a skilled nursing home. Given the wide variation in rehabilitation stay lengths, predicting the length of stay upon hospital discharge would help manage patients’ recovery expectations and create appropriate therapy schedules. Existing literature on length of stay predictors included both acute hospital and in-hospital rehabilitation phases or involved small sample sizes. The present study aims to identify predictors for the length of geriatric rehabilitation stay in skilled nursing homes for older patients after hip fracture surgery upon hospital discharge. Methods: This retrospective cohort study was conducted from 1 October 2017 to 1 July 2023, including 561 patients. Potential predictors of the length of geriatric rehabilitation stay were first tested univariately, with variables showing p < 0.15 entered into a multivariate forward linear regression model. Results: This model identified the following independent predictors of a longer length of geriatric rehabilitation stay: Functional Ambulation Categories (FACs) 0 (B = 29.9, 95% CI 24.1–35.7), 1 (B = 18.0, 95% CI 11.8–24.2), 2 (B = 12.0, 95% CI 7.1–17.0), or 3 (B = 3.6, 95% CI −1.2–9.4) at hospital discharge vs. FAC 4, living independently with home care services (B = 5.9, 95% CI 2.5–9.3) or in a residential home prior to the hip fracture (B = 0.2, 95% CI −7.4–7.8) vs. living independently without home care services, non- or partial weight-bearing mobilization vs. full weight-bearing mobilization (B = 15.4, 95% CI 8.5–22.2), internal fixation vs. hemiarthroplasty (B = 4.7, 95% CI 1.4–7.9), in-hospital delirium (B = 7.0, 95% CI 2.2–11.7), and in-hospital heart failure (B = 7.9, 95% CI 0.5–15.3). The explained variance was 32.0%. Conclusions: This study identified FAC at hospital discharge, premorbid living situation, postoperative weight-bearing protocol, surgery type, in-hospital delirium, and in-hospital heart failure as independent predictors of the length of geriatric rehabilitation stay. Future investigations are needed to identify additional predictors, such as cognitive functioning, to better predict the length of geriatric rehabilitation stay upon hospital discharge.

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 health care budgets make 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 toward 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 or less 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 (Maastricht Instruments BV) were collected during the first rehabilitation week. Principal component analysis was used to reduce the physical activity features. ML models were developed using Bayesian hyperparameter optimization and refined if necessary. The performance of the single best-performing configuration per remaining ML model type was evaluated, and the most important features for predicting the length of geriatric rehabilitation stay were identified. Results: Of the 3 ML models evaluated (support vector machine [SVM], ensemble of decision trees, and neural network), the SVM achieved the highest performance, with 19 out of 20 correct predictions (accuracy=0.95, 95% CI 0.85-1.00; precision=0.91, 95% CI 0.71-1.00; recall=1.00, 95% CI 1.00-1.00; F1-score=0.95238, 95% CI 0.83-1.00; area under the curve [AUC]=0.97, 95% CI 0.83-1.00). The most important features for predicting the length of geriatric rehabilitation stay across the best-performing ML models included the continuously monitored physical activity data, time in the emergency room, functional ambulation category (FAC) at hospital discharge, age, Katz Index of Independence in Activities of Daily Living–6 (Katz-ADL6) at hospital discharge, Montreal Cognitive Assessment (MoCA), availability of nonprofessional help, surgery type, Charlson Comorbidity Index (CCI), gender, and hemoglobin level at hospital admission. Conclusions: This study developed several ML models to predict a geriatric rehabilitation stay of ≤4 weeks in a skilled nursing home for older patients after hip fracture surgery. Among these models, the SVM proved to be highly accurate in its predictions with an accuracy of 0.95 (95% CI 0.85-1.00), precision of 0.91 (95% CI 0.71-1.00), recall of 1.00 (95% CI 1.00-1.00), F1-score of 0.95 (95% CI 0.83-1.00), and AUC of 0.97 (95% CI 0.88-1.00).

Objectives: To identify early predictors of discharge destination in patients aged ≥70 years following hip fracture surgery, using the Dutch Hip Fracture Audit (DHFA) Indicator Taskforce database with the aim of developing and validating a prediction model. Methods: Patients living in a (residential) home prior to the hip fracture were categorized into three discharge groups: home (n = 1322), geriatric rehabilitation (n = 2181), and nursing home (n = 337). The dataset was randomly split into a training set (75%) and a test set (25%). Potential predictors of discharge destination were collected immediately after hip fracture surgery and first tested univariately in the training set. Variables showing p < 0.15 were entered into a multinomial regression model. The model was validated on the test set. Results: The training set consisted of 2878 patients (median age: 83 years (IQR 77–89 years), 2012 females (70%)). The final multinomial regression model included age, gender, PFMS, premorbid Katz-ADL, ASA score, polypharmacy, history of dementia, delirium during previous hospital admissions, fall in the past six months, surgical treatment, anaesthesia type, and co-treatment by a geriatrician. The strength and direction of the associations between these variables and discharge destination varied across the three pairwise comparisons. The validated model predicted discharge to geriatric rehabilitation, home, and a nursing home with sensitivities of 86.7%, 37.9%, and 9.6%, respectively. Precision ranged from 33.3% (nursing home) to 60.9% (home) and 66.7% (geriatric rehabilitation). Conclusions: Discharge destination could be predicted with relatively high sensitivity and moderate precision for geriatric rehabilitation, whereas sensitivity and precision for predicting discharge home and to a nursing home remained limited. This highlights the need to refine the model before clinical implementation can be considered.