{"title":"预测自发性脑出血患者长期预后的可解释模型:一项回顾性队列研究。","authors":"Kai-Cheng Yang, Yu-Jia Jin, Li-Li Tang, Feng Gao, Lusha Tong","doi":"10.1136/svn-2024-003864","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and aim: </strong>Recently, long-term outcomes in patients with spontaneous intracerebral haemorrhage (sICH) have gained increasing attention besides acute-phase characteristics. Predictive models for long-term outcomes are valuable for risk stratification and treatment strategies. This study aimed to develop and validate an explainable model for predicting long-term recurrence and all-cause death in patients with ICH, using clinical and imaging markers of cerebral small vascular diseases from MRI.</p><p><strong>Method: </strong>We retrospectively analysed data from a prospectively collected large-scale cohort of patients with acute ICH admitted to the Neurology Department of The Second Affiliated Hospital of Zhejiang University between November 2016 and April 2023. After comprehensive variable selection using least absolute shrinkage and selection operator and stepwise Cox regression, we constructed Cox proportional hazards models to predict recurrence and all-cause death. Model performance was evaluated using the concordance index, integrated Brier score and time-dependent area under the curve. Global and local interpretability were assessed using variable importance calculated as SurvSHAP(t) and SurvLIME methods for the entire training set and individual patients, respectively.</p><p><strong>Results: </strong>A total of 842 eligible patients were included. Over a median follow-up of 36 months (IQR: 12-51), 86 patients (9.1%) died, and 62 patients (6.6%) experienced recurrence of ICH. The concordance indexes for the all-cause death and recurrence models were 0.841 (95% CI 0.767 to 0.913) and 0.759 (95% CI 0.651 to 0.867), respectively, with integrated Brier scores of 0.079 and 0.063. The interpretability maps highlighted age, aetiology of ICH and low haemoglobin as key predictors of long-term death, while cortical superficial siderosis and previous haemorrhage were crucial for predicting recurrence.</p><p><strong>Conclusions: </strong>This model demonstrates high predictive accuracy and emphasises the crucial factors in predicting long-term outcomes of patients with sICH.</p>","PeriodicalId":48733,"journal":{"name":"Journal of Investigative Medicine","volume":" ","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Explainable models for predicting long-term outcomes in patients with spontaneous intracerebral haemorrhage: a retrospective cohort study.\",\"authors\":\"Kai-Cheng Yang, Yu-Jia Jin, Li-Li Tang, Feng Gao, Lusha Tong\",\"doi\":\"10.1136/svn-2024-003864\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background and aim: </strong>Recently, long-term outcomes in patients with spontaneous intracerebral haemorrhage (sICH) have gained increasing attention besides acute-phase characteristics. Predictive models for long-term outcomes are valuable for risk stratification and treatment strategies. This study aimed to develop and validate an explainable model for predicting long-term recurrence and all-cause death in patients with ICH, using clinical and imaging markers of cerebral small vascular diseases from MRI.</p><p><strong>Method: </strong>We retrospectively analysed data from a prospectively collected large-scale cohort of patients with acute ICH admitted to the Neurology Department of The Second Affiliated Hospital of Zhejiang University between November 2016 and April 2023. After comprehensive variable selection using least absolute shrinkage and selection operator and stepwise Cox regression, we constructed Cox proportional hazards models to predict recurrence and all-cause death. Model performance was evaluated using the concordance index, integrated Brier score and time-dependent area under the curve. Global and local interpretability were assessed using variable importance calculated as SurvSHAP(t) and SurvLIME methods for the entire training set and individual patients, respectively.</p><p><strong>Results: </strong>A total of 842 eligible patients were included. Over a median follow-up of 36 months (IQR: 12-51), 86 patients (9.1%) died, and 62 patients (6.6%) experienced recurrence of ICH. The concordance indexes for the all-cause death and recurrence models were 0.841 (95% CI 0.767 to 0.913) and 0.759 (95% CI 0.651 to 0.867), respectively, with integrated Brier scores of 0.079 and 0.063. The interpretability maps highlighted age, aetiology of ICH and low haemoglobin as key predictors of long-term death, while cortical superficial siderosis and previous haemorrhage were crucial for predicting recurrence.</p><p><strong>Conclusions: </strong>This model demonstrates high predictive accuracy and emphasises the crucial factors in predicting long-term outcomes of patients with sICH.</p>\",\"PeriodicalId\":48733,\"journal\":{\"name\":\"Journal of Investigative Medicine\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2025-02-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Investigative Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1136/svn-2024-003864\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Investigative Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/svn-2024-003864","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
背景与目的:近年来,自发性脑出血(siich)患者的长期预后除了急性期特征外,也越来越受到关注。长期预后的预测模型对于风险分层和治疗策略是有价值的。本研究旨在建立和验证一个可解释的模型,用于预测脑出血患者的长期复发和全因死亡,使用MRI的脑小血管疾病的临床和影像学标志物。方法:回顾性分析2016年11月至2023年4月浙江大学第二附属医院神经内科收治的急性脑出血患者的前瞻性大规模队列数据。在使用最小绝对收缩和选择算子以及逐步Cox回归进行综合变量选择后,我们构建了Cox比例风险模型来预测复发和全因死亡。采用一致性指数、综合Brier评分和随时间变化的曲线下面积来评价模型的性能。对整个训练集和个体患者,分别使用以SurvSHAP(t)和SurvLIME方法计算的变量重要性评估全局和局部可解释性。结果:共纳入842例符合条件的患者。中位随访36个月(IQR: 12-51), 86例(9.1%)患者死亡,62例(6.6%)患者出现脑出血复发。全因死亡和复发模型的一致性指数分别为0.841 (95% CI 0.767 ~ 0.913)和0.759 (95% CI 0.651 ~ 0.867), Brier综合评分分别为0.079和0.063。可解释性图强调年龄、脑出血的病因和低血红蛋白是长期死亡的关键预测因素,而皮质浅表性铁沉着和既往出血是预测复发的关键因素。结论:该模型具有较高的预测准确性,并强调了预测sICH患者长期预后的关键因素。
Explainable models for predicting long-term outcomes in patients with spontaneous intracerebral haemorrhage: a retrospective cohort study.
Background and aim: Recently, long-term outcomes in patients with spontaneous intracerebral haemorrhage (sICH) have gained increasing attention besides acute-phase characteristics. Predictive models for long-term outcomes are valuable for risk stratification and treatment strategies. This study aimed to develop and validate an explainable model for predicting long-term recurrence and all-cause death in patients with ICH, using clinical and imaging markers of cerebral small vascular diseases from MRI.
Method: We retrospectively analysed data from a prospectively collected large-scale cohort of patients with acute ICH admitted to the Neurology Department of The Second Affiliated Hospital of Zhejiang University between November 2016 and April 2023. After comprehensive variable selection using least absolute shrinkage and selection operator and stepwise Cox regression, we constructed Cox proportional hazards models to predict recurrence and all-cause death. Model performance was evaluated using the concordance index, integrated Brier score and time-dependent area under the curve. Global and local interpretability were assessed using variable importance calculated as SurvSHAP(t) and SurvLIME methods for the entire training set and individual patients, respectively.
Results: A total of 842 eligible patients were included. Over a median follow-up of 36 months (IQR: 12-51), 86 patients (9.1%) died, and 62 patients (6.6%) experienced recurrence of ICH. The concordance indexes for the all-cause death and recurrence models were 0.841 (95% CI 0.767 to 0.913) and 0.759 (95% CI 0.651 to 0.867), respectively, with integrated Brier scores of 0.079 and 0.063. The interpretability maps highlighted age, aetiology of ICH and low haemoglobin as key predictors of long-term death, while cortical superficial siderosis and previous haemorrhage were crucial for predicting recurrence.
Conclusions: This model demonstrates high predictive accuracy and emphasises the crucial factors in predicting long-term outcomes of patients with sICH.
期刊介绍:
Journal of Investigative Medicine (JIM) is the official publication of the American Federation for Medical Research. The journal is peer-reviewed and publishes high-quality original articles and reviews in the areas of basic, clinical, and translational medical research.
JIM publishes on all topics and specialty areas that are critical to the conduct of the entire spectrum of biomedical research: from the translation of clinical observations at the bedside, to basic and animal research to clinical research and the implementation of innovative medical care.