Development of predictive model for post-stroke depression at discharge based on decision tree algorithm: A multi-center hospital-based cohort study

IF 3.5 2区医学 Q2 PSYCHIATRY

Journal of Psychosomatic Research Pub Date : 2024-09-24 DOI:10.1016/j.jpsychores.2024.111942

{"title":"Development of predictive model for post-stroke depression at discharge based on decision tree algorithm: A multi-center hospital-based cohort study","authors":"","doi":"10.1016/j.jpsychores.2024.111942","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>Post-stroke depression (PSD) is one of the most common and severe neuropsychological sequelae after stroke. Using a prediction model composed of multiple predictors may be more beneficial than verifying the predictive performance of any single predictor. The primary objective of this study was to construct practical prediction tools for PSD at discharge utilizing a decision tree (DT) algorithm.</div></div><div><h3>Methods</h3><div>A multi-center prospective cohort study was conducted from May 2018 to October 2019 and stroke patients within seven days of onset were consecutively recruited. The independent predictors of PSD at discharge were identified through multivariate logistic regression with backward elimination. Classification and regression tree (CART) algorithm was employed as the DT model's splitting method.</div></div><div><h3>Results</h3><div>A total of 876 stroke patients who were discharged from the neurology departments of three large general Class A tertiary hospitals in Wuhan were eligible for analysis. Firstly, we divided these 876 patients into PSD and non-PSD groups, history of coronary heart disease (OR = 1.835; 95 % CI, 1.106–3.046; <em>P</em> = 0.019), length of hospital stay (OR = 1.040; 95 % CI, 1.013–1.069; <em>P</em> = 0.001), NIHSS score (OR = 1.124; 95 % CI, 1.052–1.201; <em>P</em> = 0.001), and Mini mental state examination (MMSE) score (OR = 0.935; 95 % CI, 0.893–0.978; <em>P</em> = 0.004) were significant predictors. The subgroup analysis results have shown that hemorrhagic stroke, history of hypertension and higher modified Rankin Scale score (mRS) score were associated with PSD at discharge in the young adult stroke patients.</div></div><div><h3>Conclusions</h3><div>Several predictors of PSD at discharge were identified and convenient DT models were constructed to facilitate clinical decision-making.</div></div>","PeriodicalId":50074,"journal":{"name":"Journal of Psychosomatic Research","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Psychosomatic Research","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022399924003544","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

Post-stroke depression (PSD) is one of the most common and severe neuropsychological sequelae after stroke. Using a prediction model composed of multiple predictors may be more beneficial than verifying the predictive performance of any single predictor. The primary objective of this study was to construct practical prediction tools for PSD at discharge utilizing a decision tree (DT) algorithm.

Methods

A multi-center prospective cohort study was conducted from May 2018 to October 2019 and stroke patients within seven days of onset were consecutively recruited. The independent predictors of PSD at discharge were identified through multivariate logistic regression with backward elimination. Classification and regression tree (CART) algorithm was employed as the DT model's splitting method.

Results

A total of 876 stroke patients who were discharged from the neurology departments of three large general Class A tertiary hospitals in Wuhan were eligible for analysis. Firstly, we divided these 876 patients into PSD and non-PSD groups, history of coronary heart disease (OR = 1.835; 95 % CI, 1.106–3.046; P = 0.019), length of hospital stay (OR = 1.040; 95 % CI, 1.013–1.069; P = 0.001), NIHSS score (OR = 1.124; 95 % CI, 1.052–1.201; P = 0.001), and Mini mental state examination (MMSE) score (OR = 0.935; 95 % CI, 0.893–0.978; P = 0.004) were significant predictors. The subgroup analysis results have shown that hemorrhagic stroke, history of hypertension and higher modified Rankin Scale score (mRS) score were associated with PSD at discharge in the young adult stroke patients.

Conclusions

Several predictors of PSD at discharge were identified and convenient DT models were constructed to facilitate clinical decision-making.

查看原文本刊更多论文

基于决策树算法的卒中后出院抑郁预测模型的开发：基于医院的多中心队列研究

目的中风后抑郁（PSD）是中风后最常见、最严重的神经心理后遗症之一。使用由多个预测因子组成的预测模型可能比验证任何单一预测因子的预测性能更有益处。本研究的主要目的是利用决策树（DT）算法构建出院时 PSD 的实用预测工具。方法于 2018 年 5 月至 2019 年 10 月开展了一项多中心前瞻性队列研究，连续招募了发病七天内的卒中患者。通过多变量逻辑回归和反向排除法确定了出院时 PSD 的独立预测因素。结果武汉市三家大型甲级综合三甲医院神经内科出院的 876 例脑卒中患者符合分析条件。首先，我们将这 876 例患者分为 PSD 组和非 PSD 组，冠心病史（OR = 1.835; 95 % CI, 1.106-3.046; P = 0.019）、住院时间（OR = 1.040; 95 % CI, 1.013-1.069；P = 0.001）、NIHSS 评分（OR = 1.124；95 % CI，1.052-1.201；P = 0.001）和迷你精神状态检查（MMSE）评分（OR = 0.935；95 % CI，0.893-0.978；P = 0.004）是重要的预测因素。亚组分析结果显示，出血性卒中、高血压病史和较高的改良 Rankin 量表评分（mRS）与青壮年卒中患者出院时的 PSD 相关。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Psychosomatic Research 医学-精神病学

CiteScore

7.40

自引率

6.40%

发文量

314

审稿时长

6.2 weeks

期刊介绍： The Journal of Psychosomatic Research is a multidisciplinary research journal covering all aspects of the relationships between psychology and medicine. The scope is broad and ranges from basic human biological and psychological research to evaluations of treatment and services. Papers will normally be concerned with illness or patients rather than studies of healthy populations. Studies concerning special populations, such as the elderly and children and adolescents, are welcome. In addition to peer-reviewed original papers, the journal publishes editorials, reviews, and other papers related to the journal''s aims.