Hip fracture rehabilitation for people living in nursing homes: Randomised trial

Does anatomical type of proximal hip fracture affect rehabilitation outcomes among older adults?

BACKGROUND AND PURPOSE

Numerous studies have detailed the potential benefits of inpatient geriatric rehabilitation for older adults with hip fractures. However, data regarding effect of fracture type (femoral neck, intertrochanteric, or subtrochanteric) on rehabilitation outcomes are limited. This study assessed whether the anatomical type of proximal hip fracture affects rehabilitation outcomes among disabled older adults.

METHODS

A population-based study was conducted comparing all patients with a recent hip fracture who were admitted to a geriatric rehabilitation facility in Israel. Data were collected retrospectively from an electronic database during a 5-year period (2014-2019). The Functional Independence Measure (FIM) was used to assess physical and cognitive function at admission and discharge.

RESULTS

The analyses included 624 older adults with hip fractures. We found significant differences in motor FIM score at admission, as patients with femoral neck fracture performed better than patients with intertrochanteric and subtrochanteric fracture did. The disparity in motor FIM score remained consistent through discharge, with all groups achieving a median gain of 14 points. Within one month of rehabilitation, about a third of all patients achieved a higher functional level.

CONCLUSIONS

Patients with femoral neck fracture have better motor ability than do those with intertrochanteric and subtrochanteric fractures, which were retained throughout the course of rehabilitation; yet, the level of improvement remained similar. Clinicians should be aware of such differences in functional ability when discussing goals of care with older adults with hip fractures and consider them when implementing individual rehabilitation programs .

Application of Machine Learning Methods in Nursing Home Research

Background: A machine learning (ML) system is able to construct algorithms to continue improving predictions and generate automated knowledge through data-driven predictors or decisions. Objective: The purpose of this study was to compare six ML methods (random forest (RF), logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM) of predicting falls in nursing homes (NHs). Methods: We applied three representative six-ML algorithms to the preprocessed dataset to develop a prediction model (N = 60). We used an accuracy measure to evaluate prediction models. Results: RF was the most accurate model (0.883), followed by the logistic regression model, SVM linear, and polynomial SVM (0.867). Conclusions: RF was a powerful algorithm to discern predictors of falls in NHs. For effective fall management, researchers should consider organizational characteristics as well as personal factors. Recommendations for Future Research: To confirm the superiority of ML in NH research, future studies are required to discern additional potential factors using newly introduced ML methods.