Application of Machine Learning Methods in Nursing Home Research.

Soo-Kyoung Lee,Ji Yeon Lee,Jinhyun Ahn,Juh Hyun Shin

doi:10.3390/ijerph17176234

Abstract

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.

Highlights

A machine learning (ML) system is able to construct algorithms to continue improving predictions and generate automated knowledge through data-driven predictors or decisions
The proportion of residents with psychiatric medications was supported by accuracy of memetic algorithms; a meta-analysis reported that SVM was more accurate than an logistic regression, random forest (RF), polynomial SVM, radial SVM, and sigmoid SVM
This study applied six ML methods to predict factors related to falls of nursing homes (NHs) residents

Summary

Introduction

A machine learning (ML) system is able to construct algorithms to continue improving predictions and generate automated knowledge through data-driven predictors or decisions. Accurate prediction of the factors associated with falls in NHs is important because nurses, health care professionals, researchers in practice, administrative staff, researchers, and politicians address fall issues. These stakeholders develop targeted fall-prevention management, and assess residents based on factors associated with a fall [5]. Traditional regression analysis has limitations in addressing the variability in data, nonlinear interactions of variables, and diverse distributions of datasets, which usually require basic assumptions [15] To offset these limitations, researchers recently introduced a new approach: machine learning (ML).

Objectives

Results

Discussion

Conclusion