Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In Archives of physical medicine and rehabilitation ; h5-index 61.0

OBJECTIVE : To use machine learning-based methods in designing a predictive model of rehabilitation outcomes for post-acute hip-fractured patients.

DESIGN : A retrospective analysis using linear models, AdaBoost, CatBoost, ExtraTrees, K-Nearest Neighbors, RandomForest, Support vector machine, XGBoost, and voting of all models to develop and validate a predictive model.

SETTING : A university-affiliated 300-bed major post-acute geriatric rehabilitation center.

PARTICIPANTS : Consecutive hip-fractured patients (n=1625) admitted to an acute rehabilitation department.

MAIN OUTCOME MEASURES : The Functional Independence Measure (FIM) instrument, motor-FIM (mFIM), and the relative functional gain on mFIM (mFIM effectiveness) as a continuous and binary variable. Ten predictive models were created: base models (linear/logistic regression), and eight machine learning models (AdaBoost, CatBoost, ExtraTrees, K-Nearest Neighbors, RandomForest, Support vector machine, XGBoost, and a voting ensemble). R-squared was used to evaluate their performance in predicting a continuous outcome variable, and the area under the receiver operating characteristic curve was used to evaluate the binary outcome. A paired two-tailed t-test compared the results of the different models.

RESULTS : Machine learning-based models yielded better results than the linear/logistic regression models in predicting rehabilitation outcomes. The three most important predictors of the mFIM effectiveness score were: the MMSE, pre-fracture mFIM scores, and age; of the discharge mFIM score: the admission mFIM, MMSE and pre-fracture mFIM scores. The most contributing factors for favorable outcomes (mFIM effectiveness> median) with higher prediction confidence level were: high MMSE (25.7±2.8), high pre-facture mFIM (81.5±7.8) and high admission mFIM (48.6±8) scores. We present a simple prediction instrument for estimating the expected performance of post-acute hip-fractured patients.

CONCLUSION : Use of machine learning models to predict rehabilitation outcomes of post-acute hip-fractured patients is superior to the linear/logistic regression models. The higher the MMSE, pre-fracture mFIM and admission mFIM scores are, the higher the confidence levels of the predicted parameters.

Shtar Guy, Rokach Lior, Shapira Bracha, Nissan Ran, Hershkovitz Avital

2020-Sep-16

Hip fracture, Machine learning, Outcome, Rehabilitation