Department of Health Information Management, Shahrekord University of Medical Sciences, Shahrekord, Iran.
Student Research Committee, School of Health Management and Information Sciences Branch, Iran University of Medical Sciences, Tehran, Iran.
Biomed Eng Online. 2023 Aug 29;22(1):85. doi: 10.1186/s12938-023-01140-9.
The worldwide society is currently facing an epidemiological shift due to the significant improvement in life expectancy and increase in the elderly population. This shift requires the public and scientific community to highlight successful aging (SA), as an indicator representing the quality of elderly people's health. SA is a subjective, complex, and multidimensional concept; thus, its meaning or measuring is a difficult task. This study seeks to identify the most affecting factors on SA and fed them as input variables for constructing predictive models using machine learning (ML) algorithms.
Data from 1465 adults aged ≥ 60 years who were referred to health centers in Abadan city (Iran) between 2021 and 2022 were collected by interview. First, binary logistic regression (BLR) was used to identify the main factors influencing SA. Second, eight ML algorithms, including adaptive boosting (AdaBoost), bootstrap aggregating (Bagging), eXtreme Gradient Boosting (XG-Boost), random forest (RF), J-48, multilayered perceptron (MLP), Naïve Bayes (NB), and support vector machine (SVM), were trained to predict SA. Finally, their performance was evaluated using metrics derived from the confusion matrix to determine the best model.
The experimental results showed that 44 factors had a meaningful relationship with SA as the output class. In total, the RF algorithm with sensitivity = 0.95 ± 0.01, specificity = 0.94 ± 0.01, accuracy = 0.94 ± 0.005, and F-score = 0.94 ± 0.003 yielded the best performance for predicting SA.
Compared to other selected ML methods, the effectiveness of the RF as a bagging algorithm in predicting SA was significantly better. Our developed prediction models can provide, gerontologists, geriatric nursing, healthcare administrators, and policymakers with a reliable and responsive tool to improve elderly outcomes.
由于预期寿命的显著提高和老年人口的增加，全球社会目前正面临着一种流行病学转变。这种转变要求公众和科学界强调成功老龄化（SA），作为代表老年人健康质量的指标。SA 是一个主观的、复杂的和多维的概念；因此，它的含义或衡量是一项艰巨的任务。本研究旨在确定影响 SA 的最主要因素，并将其作为输入变量，利用机器学习（ML）算法构建预测模型。
通过访谈收集了 2021 年至 2022 年间伊朗阿巴丹市卫生中心就诊的 1465 名年龄≥60 岁的成年人的数据。首先，采用二元逻辑回归（BLR）来识别影响 SA 的主要因素。其次，采用 8 种 ML 算法，包括自适应提升（AdaBoost）、自举聚合（Bagging）、极端梯度提升（XG-Boost）、随机森林（RF）、J-48、多层感知机（MLP）、朴素贝叶斯（NB）和支持向量机（SVM），对 SA 进行预测。最后，使用混淆矩阵得出的指标来评估它们的性能，以确定最佳模型。
实验结果表明，44 个因素与作为输出类的 SA 有意义的关系。总的来说，RF 算法的灵敏度为 0.95±0.01、特异性为 0.94±0.01、准确性为 0.94±0.005 和 F 分数为 0.94±0.003，在预测 SA 方面表现最佳。
与其他选定的 ML 方法相比，RF 作为一种装袋算法在预测 SA 方面的有效性明显更好。我们开发的预测模型可以为老年学家、老年护理、医疗保健管理人员和政策制定者提供一种可靠和响应迅速的工具，以改善老年人的结局。
