Interpretable Analysis of Influencing Factors and the Current State of Social Frailty in Patients with Chronic Heart Failure

Abstract

Background The comprehensive management of heart failure in conjunction with frailty necessitates a multidimensional approach to frailty assessment. However, the social frailty, despite being an incremental predictor of negative health outcomes in heart failure patients, has not been adequately addressed. Objective To understand the current status of social frailty in patients with chronic heart failure and analyze its influencing factors. Methods From September 2022 to July 2023, convenience sampling was used to select patients with chronic heart failure from the First Affiliated Hospital with Nanjing Medical University as the research objects, the general information questionnaire, the HALFT Scale, the Loneliness Scale, the Brief 2-Way Social Support Scale, Personal Mastery Scale, and the Patient Health Questionnaire were used to investigate. Univariate analysis and support vector machine-feature recursive elimination were used to filter the feature, SVM classification model was constructed, and SHAP value was introduced to analyze the influencing factors. Results A total of 228 patients were screened in this study, of which 8 patients refused to fill in. A total of 220 questionnaires were distributed and 213 valid questionnaires were returned, with an effective recovery rate of 96.81%. The proportion of pre-social frailty and social frailty in patients with chronic heart failure was 46.0% (98/213) and 17.8% (38/213), respectively. Statistically significant differences were observed among chronic heart failure patients with different degrees of social frailty in terms of education level, place of residence, working status, economic burden of disease, personal monthly income, course of disease, exercise habits, medical satisfaction, traffic, the UCLA Loneliness Scale score, the Brief 2-Way Social Support Scale score, the PMS score, and the PHQ-9 score. When the SVM-RFE model play the best performance, the optimal feature subset was used to construct the SVM classification prediction model and perform SHAP interpretability analysis. The accuracy of the model was 0.73 in the training set and 0.63 in the test set, respectively. At this time, the ranking of feature importance from high to low was no exercise habit (+), personal mastery (-), heavy economic burden of disease (+), 2-way social support (-), depression (+), loneliness (+), unemployment (+) . Conclusion Patients with chronic heart failure experiencing severe social frailty. Healthcare providers should prioritize identifying and addressing the resource deficits of patients and the underlying factors contributing to social frailty. Targeted interventions should be implemented to mitigate social frailty in patients with heart failure by enhancing external support systems, fostering positive beliefs, addressing negative emotional experiences, developing comprehensive management plans, coordinating medical resources, and implementing strategies to delay or reverse social frailty progression. These interventions aim to enhance the prognosis and quality of life for patients with heart failure.

Keywords

• chronic heart failure|social frailty|root cause analysis|support vector machine|shap