Scholarlink

Background <p>In-hospital cardiac arrest (IHCA) from non-cardiac causes is a life-threatening condition characterized by high mortality and complex etiology. Despite advances in critical care monitoring, effective early warning systems remain lacking due to challenges in balancing sensitivity and specificity within imbalanced clinical data and the interpretability of machine learning models remains poorly defined.</p> Methods <p>We developed and evaluated six machine learning algorithms using data from 43,618 ICU patients in the MIMIC-IV database. Model performance was assessed through multiple metrics, and SHapley Additive exPlanations (SHAP) analysis was employed for model interpretability. Decision curve analysis was performed to evaluate clinical utility.</p> Results <p>Distinct performance trade-offs were identified across models. XGBoost achieved optimal discriminative ability (AUC = 0.730, 95% CI: 0.695–0.763), while CatBoost favored sensitivity (0.907) to meet clinical guidelines. SHAP analysis identified anion gap (AG), white blood cell count (WBC), red cell distribution width (RDW), Glasgow Coma Scale (GCS), platelet, partial thromboplastin time (PTT), and red blood cell count (RBC) as key predictors, with elevated inflammatory markers and reduced neurological parameters consistently associated with increased risk.</p> Conclusions <p>Gradient boosting algorithms demonstrate crucial utility in predicting non-cardiac IHCA. The identified interpretable biomarkers align with established pathophysiological mechanisms and may reflect downstream manifestations of genome instability pathways, representing potential targets for early clinical intervention.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development and evaluation of interpretable machine learning models for predicting in-ICU cardiac arrest from non-cardiac causes using clinical biomarkers

  • 期刊论文

  • 发表日期：

    2026年6月15日

查看全文
  • Shanshan Zheng,
  • Weijie Gong,
  • Wenxiang Zhang,
  • Shengsen Yao,
  • Jiajun Sun,
  • Xianghong Peng,
  • Xixiang Ding,
  • Xiaojing Wu,
  • Zhen Liang,
  • Lei Su

摘要

Background

In-hospital cardiac arrest (IHCA) from non-cardiac causes is a life-threatening condition characterized by high mortality and complex etiology. Despite advances in critical care monitoring, effective early warning systems remain lacking due to challenges in balancing sensitivity and specificity within imbalanced clinical data and the interpretability of machine learning models remains poorly defined.

Methods

We developed and evaluated six machine learning algorithms using data from 43,618 ICU patients in the MIMIC-IV database. Model performance was assessed through multiple metrics, and SHapley Additive exPlanations (SHAP) analysis was employed for model interpretability. Decision curve analysis was performed to evaluate clinical utility.

Results

Distinct performance trade-offs were identified across models. XGBoost achieved optimal discriminative ability (AUC = 0.730, 95% CI: 0.695–0.763), while CatBoost favored sensitivity (0.907) to meet clinical guidelines. SHAP analysis identified anion gap (AG), white blood cell count (WBC), red cell distribution width (RDW), Glasgow Coma Scale (GCS), platelet, partial thromboplastin time (PTT), and red blood cell count (RBC) as key predictors, with elevated inflammatory markers and reduced neurological parameters consistently associated with increased risk.

Conclusions

Gradient boosting algorithms demonstrate crucial utility in predicting non-cardiac IHCA. The identified interpretable biomarkers align with established pathophysiological mechanisms and may reflect downstream manifestations of genome instability pathways, representing potential targets for early clinical intervention.