Predicting frailty in older patients with chronic pain using explainable machine learning: A cross-sectional study.

Xiaoang Zhang, Yuping Liao, Daying Zhang, Weichen Liu, Zhijian Wang, Yaxin Jin, Shushu Chen, Jianmei Wei

School of Nursing, Jiangxi Medical College, Nanchang University, Nanchang, China; Department of Pain Medicine, the 1(st) affiliated hospital, Jiangxi Medical College, Nanchang University, Nanchang, China. Electronic address: [email protected]. · pubmed

Paper

Abstract

Frailty is common among older adults with chronic pain, and early identification is crucial in preventing adverse outcomes like falls, disability, and dementia. However, effective tools for identifying frailty in this population remain limited. This study aimed to explore frailty risk factors in older adults with chronic pain and to develop 9 machine learning models for frailty identification. The Shapley Additive Explanations (SHAP) method was used to explain the models. The Random Forest (RF) model performed best with 0.822 accuracy, 0.797 precision, and an AUC of 0.881. The variables in the RF model included: age, BMI, education level, pain duration, number of pain sites, pain level, depression, and Activity of Daily Living (ADL). Pain level, depression, and ADL were the 3 most important variables in the RF model. This model helps healthcare providers to identify frailty early, enabling timely interventions to improve patient outcomes and promote healthy aging.

The following analysis is generated by AI and may contain errors. It is separate from the authors’ abstract and is not peer review.

Research summary

The paper addresses frailty in older adults with chronic pain, which is a significant issue in aging populations. However, it primarily focuses on identifying risk factors and developing machine learning models for early detection rather than addressing the root causes of aging or promoting lifespan extension. While the findings may contribute to better management of frailty, the impact on the broader field of longevity research is limited, making it a solid but not groundbreaking contribution.

Author of this paper? Send a correction.