PMID- 32949551
OWN - NLM
STAT- MEDLINE
DCOM- 20210315
LR  - 20210315
IS  - 1532-821X (Electronic)
IS  - 0003-9993 (Linking)
VI  - 102
IP  - 3
DP  - 2021 Mar
TI  - Using Machine Learning to Predict Rehabilitation Outcomes in Postacute Hip 
      Fracture Patients.
PG  - 386-394
LID - S0003-9993(20)30924-2 [pii]
LID - 10.1016/j.apmr.2020.08.011 [doi]
AB  - OBJECTIVE: To use machine learning-based methods in designing a predictive model 
      of rehabilitation outcomes for postacute hip fracture 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 postacute geriatric rehabilitation center. 
      PARTICIPANTS: Consecutive hip fracture patients (N=1625) admitted to an postacute 
      rehabilitation department. MAIN OUTCOME MEASURES: The 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 8 machine learning models (AdaBoost, CatBoost, 
      ExtraTrees, K-Nearest Neighbors, RandomForest, Support vector machine, XGBoost, 
      and a voting ensemble). R(2) 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 2-tailed t 
      test compared the results of the different models. RESULTS: Machine 
      learning-based models yielded better results than the linear and logistic 
      regression models in predicting rehabilitation outcomes. The 3 most important 
      predictors of the mFIM effectiveness score were the Mini Mental State Examination 
      (MMSE), prefracture mFIM scores, and age. The 3 most important predictors of the 
      discharge mFIM score were the admission mFIM, MMSE, and prefracture 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 
      prefacture 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 postacute 
      hip fracture patients. CONCLUSIONS: The use of machine learning models to predict 
      rehabilitation outcomes of postacute hip fracture patients is superior to linear 
      and logistic regression models. The higher the MMSE, prefracture mFIM, and 
      admission mFIM scores are, the higher the confidence levels of the predicted 
      parameters.
CI  - Copyright (c) 2020 American Congress of Rehabilitation Medicine. Published by 
      Elsevier Inc. All rights reserved.
FAU - Shtar, Guy
AU  - Shtar G
AD  - Department of Software and Information Systems Engineering, Ben-Gurion University 
      of the Negev, Beer-Sheva, Israel.
FAU - Rokach, Lior
AU  - Rokach L
AD  - Department of Software and Information Systems Engineering, Ben-Gurion University 
      of the Negev, Beer-Sheva, Israel.
FAU - Shapira, Bracha
AU  - Shapira B
AD  - Department of Software and Information Systems Engineering, Ben-Gurion University 
      of the Negev, Beer-Sheva, Israel.
FAU - Nissan, Ran
AU  - Nissan R
AD  - 'Beit Rivka' Geriatric Rehabilitation Center, Petach Tikva, Israel.
FAU - Hershkovitz, Avital
AU  - Hershkovitz A
AD  - 'Beit Rivka' Geriatric Rehabilitation Center, Petach Tikva, Israel; Sackler 
      School of Medicine, Tel Aviv University, Tel Aviv, Israel. Electronic address: 
      avitalhe@clalit.org.il.
LA  - eng
PT  - Journal Article
DEP - 20200916
PL  - United States
TA  - Arch Phys Med Rehabil
JT  - Archives of physical medicine and rehabilitation
JID - 2985158R
SB  - IM
MH  - Aged
MH  - Aged, 80 and over
MH  - Disability Evaluation
MH  - Female
MH  - Geriatric Assessment
MH  - Hip Fractures/*rehabilitation
MH  - Humans
MH  - *Machine Learning
MH  - Male
MH  - *Occupational Therapy
MH  - *Physical Therapy Modalities
MH  - Rehabilitation Centers
MH  - Retrospective Studies
MH  - Subacute Care
MH  - Surveys and Questionnaires
MH  - Treatment Outcome
OTO - NOTNLM
OT  - Hip fracture
OT  - Machine learning
OT  - Rehabilitation
OT  - Subacute care
EDAT- 2020/09/20 06:00
MHDA- 2021/03/16 06:00
CRDT- 2020/09/19 20:08
PHST- 2020/05/12 00:00 [received]
PHST- 2020/07/12 00:00 [revised]
PHST- 2020/08/12 00:00 [accepted]
PHST- 2020/09/20 06:00 [pubmed]
PHST- 2021/03/16 06:00 [medline]
PHST- 2020/09/19 20:08 [entrez]
AID - S0003-9993(20)30924-2 [pii]
AID - 10.1016/j.apmr.2020.08.011 [doi]
PST - ppublish
SO  - Arch Phys Med Rehabil. 2021 Mar;102(3):386-394. doi: 10.1016/j.apmr.2020.08.011. 
      Epub 2020 Sep 16.