免疫抑制脓毒症患者28天死亡率的回顾性队列研究:基于MIMIC-IV v2.2的可解释性预测模型

IF 2.9 3区 医学 Q2 CRITICAL CARE MEDICINE
SHOCK Pub Date : 2025-09-12 DOI:10.1097/SHK.0000000000002721
Zhiru Zhong, Huiwei He, Zhiying Lin
{"title":"免疫抑制脓毒症患者28天死亡率的回顾性队列研究:基于MIMIC-IV v2.2的可解释性预测模型","authors":"Zhiru Zhong, Huiwei He, Zhiying Lin","doi":"10.1097/SHK.0000000000002721","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Sepsis in immunosuppressed patients is associated with significantly higher mortality rates, yet predictive models tailored to this high-risk population remain limited. This study aims to develop an interpretable machine learning model to predict 28-day mortality in immunosuppressed sepsis patients, with a focus on model transparency and clinical applicability.</p><p><strong>Methods: </strong>A retrospective cohort study was conducted using clinical, laboratory, and demographic data from immunosuppressed sepsis patients. Feature selection was performed using LASSO regression, followed by the development of predictive models, including XGBoost. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUROC). To enhance clinical interpretability, Shapley Additive Explanations (SHAP) were employed to provide insights into the contribution of individual features to mortality predictions.</p><p><strong>Results: </strong>The final model identified key predictors of 28-day mortality, including lactate levels, red cell distribution width, platelet count, and Sequential Organ Failure Assessment (SOFA) score. XGBoost demonstrated superior predictive accuracy with an AUROC of 0.93 (95% CI: 0.90-0.96), outperforming other models. SHAP analysis revealed that elevated lactate levels and reduced platelet counts were strong risk factors for mortality, while lower lactate and higher platelet counts were protective. The model's interpretability provided clear insights into the role of each predictor, facilitating individualized risk stratification.</p><p><strong>Conclusion: </strong>The XGBoost model, combined with SHAP analysis, offers an accurate and interpretable tool for predicting 28-day mortality in immunosuppressed sepsis patients. This approach enhances clinical decision-making by providing transparent insights into the factors driving mortality risk, thus supporting personalized and timely interventions aimed at improving patient outcomes.</p>","PeriodicalId":21667,"journal":{"name":"SHOCK","volume":" ","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Retrospective Cohort Study on 28-Day Mortality in Immunosuppressed Sepsis: An Interpretability-Based Predictive Model Using MIMIC-IV v2.2.\",\"authors\":\"Zhiru Zhong, Huiwei He, Zhiying Lin\",\"doi\":\"10.1097/SHK.0000000000002721\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Sepsis in immunosuppressed patients is associated with significantly higher mortality rates, yet predictive models tailored to this high-risk population remain limited. This study aims to develop an interpretable machine learning model to predict 28-day mortality in immunosuppressed sepsis patients, with a focus on model transparency and clinical applicability.</p><p><strong>Methods: </strong>A retrospective cohort study was conducted using clinical, laboratory, and demographic data from immunosuppressed sepsis patients. Feature selection was performed using LASSO regression, followed by the development of predictive models, including XGBoost. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUROC). To enhance clinical interpretability, Shapley Additive Explanations (SHAP) were employed to provide insights into the contribution of individual features to mortality predictions.</p><p><strong>Results: </strong>The final model identified key predictors of 28-day mortality, including lactate levels, red cell distribution width, platelet count, and Sequential Organ Failure Assessment (SOFA) score. XGBoost demonstrated superior predictive accuracy with an AUROC of 0.93 (95% CI: 0.90-0.96), outperforming other models. SHAP analysis revealed that elevated lactate levels and reduced platelet counts were strong risk factors for mortality, while lower lactate and higher platelet counts were protective. The model's interpretability provided clear insights into the role of each predictor, facilitating individualized risk stratification.</p><p><strong>Conclusion: </strong>The XGBoost model, combined with SHAP analysis, offers an accurate and interpretable tool for predicting 28-day mortality in immunosuppressed sepsis patients. This approach enhances clinical decision-making by providing transparent insights into the factors driving mortality risk, thus supporting personalized and timely interventions aimed at improving patient outcomes.</p>\",\"PeriodicalId\":21667,\"journal\":{\"name\":\"SHOCK\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2025-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SHOCK\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1097/SHK.0000000000002721\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CRITICAL CARE MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SHOCK","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/SHK.0000000000002721","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CRITICAL CARE MEDICINE","Score":null,"Total":0}
引用次数: 0

摘要

背景:免疫抑制患者的脓毒症与明显较高的死亡率相关,但针对这一高危人群的预测模型仍然有限。本研究旨在开发一种可解释的机器学习模型,以预测免疫抑制脓毒症患者的28天死亡率,重点是模型透明度和临床适用性。方法:对免疫抑制脓毒症患者的临床、实验室和人口学资料进行回顾性队列研究。使用LASSO回归进行特征选择,然后开发预测模型,包括XGBoost。模型的性能用受试者工作特征曲线下面积(AUROC)来评价。为了提高临床可解释性,采用Shapley加性解释(SHAP)来深入了解个体特征对死亡率预测的贡献。结果:最终模型确定了28天死亡率的关键预测因素,包括乳酸水平、红细胞分布宽度、血小板计数和序贯器官衰竭评估(SOFA)评分。XGBoost表现出卓越的预测准确性,AUROC为0.93 (95% CI: 0.90-0.96),优于其他模型。SHAP分析显示,乳酸水平升高和血小板计数减少是死亡率的强烈危险因素,而乳酸水平降低和血小板计数增加则具有保护作用。该模型的可解释性为每个预测因子的作用提供了清晰的见解,促进了个性化的风险分层。结论:XGBoost模型与SHAP分析相结合,为预测免疫抑制脓毒症患者28天死亡率提供了一个准确且可解释的工具。这种方法通过对导致死亡风险的因素提供透明的见解来增强临床决策,从而支持旨在改善患者预后的个性化和及时干预。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Retrospective Cohort Study on 28-Day Mortality in Immunosuppressed Sepsis: An Interpretability-Based Predictive Model Using MIMIC-IV v2.2.

Background: Sepsis in immunosuppressed patients is associated with significantly higher mortality rates, yet predictive models tailored to this high-risk population remain limited. This study aims to develop an interpretable machine learning model to predict 28-day mortality in immunosuppressed sepsis patients, with a focus on model transparency and clinical applicability.

Methods: A retrospective cohort study was conducted using clinical, laboratory, and demographic data from immunosuppressed sepsis patients. Feature selection was performed using LASSO regression, followed by the development of predictive models, including XGBoost. The model's performance was evaluated using the area under the receiver operating characteristic curve (AUROC). To enhance clinical interpretability, Shapley Additive Explanations (SHAP) were employed to provide insights into the contribution of individual features to mortality predictions.

Results: The final model identified key predictors of 28-day mortality, including lactate levels, red cell distribution width, platelet count, and Sequential Organ Failure Assessment (SOFA) score. XGBoost demonstrated superior predictive accuracy with an AUROC of 0.93 (95% CI: 0.90-0.96), outperforming other models. SHAP analysis revealed that elevated lactate levels and reduced platelet counts were strong risk factors for mortality, while lower lactate and higher platelet counts were protective. The model's interpretability provided clear insights into the role of each predictor, facilitating individualized risk stratification.

Conclusion: The XGBoost model, combined with SHAP analysis, offers an accurate and interpretable tool for predicting 28-day mortality in immunosuppressed sepsis patients. This approach enhances clinical decision-making by providing transparent insights into the factors driving mortality risk, thus supporting personalized and timely interventions aimed at improving patient outcomes.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
SHOCK
SHOCK 医学-外科
CiteScore
6.20
自引率
3.20%
发文量
199
审稿时长
1 months
期刊介绍: SHOCK®: Injury, Inflammation, and Sepsis: Laboratory and Clinical Approaches includes studies of novel therapeutic approaches, such as immunomodulation, gene therapy, nutrition, and others. The mission of the Journal is to foster and promote multidisciplinary studies, both experimental and clinical in nature, that critically examine the etiology, mechanisms and novel therapeutics of shock-related pathophysiological conditions. Its purpose is to excel as a vehicle for timely publication in the areas of basic and clinical studies of shock, trauma, sepsis, inflammation, ischemia, and related pathobiological states, with particular emphasis on the biologic mechanisms that determine the response to such injury. Making such information available will ultimately facilitate improved care of the traumatized or septic individual.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信