Prediction Model for Discharge Destination in Older Patients After Hip Fracture Surgery Using Early Predictors.

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.