College of Nursing, Keimyung University, 1095 Dalgubeol-daero, Dalseo-gu, Daegu 42601, Korea.
College of Nursing, Ewha Womans University, Science & Ewha Research Institute of Nursing Science, Seoul 120750, Korea.
Int J Environ Res Public Health. 2021 Mar 13;18(6):2954. doi: 10.3390/ijerph18062954.
Machine learning (ML) can keep improving predictions and generating automated knowledge via data-driven predictors or decisions.
The purpose of this study was to compare different ML methods including random forest, logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM in terms of their accuracy, sensitivity, specificity, negative predictor values, and positive predictive values by validating real datasets to predict factors for pressure ulcers (PUs).
We applied representative ML algorithms (random forest, logistic regression, linear SVM, polynomial SVM, radial SVM, and sigmoid SVM) to develop a prediction model (N = 60).
The random forest model showed the greatest accuracy (0.814), followed by logistic regression (0.782), polynomial SVM (0.779), radial SVM (0.770), linear SVM (0.767), and sigmoid SVM (0.674).
The random forest model showed the greatest accuracy for predicting PUs in nursing homes (NHs). Diverse factors that predict PUs in NHs including NH characteristics and residents' characteristics were identified according to diverse ML methods. These factors should be considered to decrease PUs in NH residents.
机器学习 (ML) 可以通过数据驱动的预测器或决策不断改进预测并生成自动化知识。
本研究旨在通过验证真实数据集来预测压疮 (PU) 的因素，比较随机森林、逻辑回归、线性支持向量机 (SVM)、多项式 SVM、径向 SVM 和 Sigmoid SVM 等不同 ML 方法在准确性、灵敏度、特异性、阴性预测值和阳性预测值方面的表现。
我们应用了代表性的 ML 算法（随机森林、逻辑回归、线性 SVM、多项式 SVM、径向 SVM 和 Sigmoid SVM）来开发一个预测模型（N = 60）。
随机森林模型的准确率最高（0.814），其次是逻辑回归（0.782）、多项式 SVM（0.779）、径向 SVM（0.770）、线性 SVM（0.767）和 Sigmoid SVM（0.674）。
随机森林模型在预测养老院中的 PU 方面表现出最高的准确率。根据不同的 ML 方法，确定了预测养老院中 PU 的多种因素，包括养老院的特征和居民的特征。这些因素应被考虑用于降低养老院居民的 PU 发生率。
