Scholarlink

Background <p>Early prediction of clinical deterioration in patients admitted to general wards from the emergency department (ED) is crucial for timely interventions and improved outcomes. Traditional scoring systems often fail to account for dynamic physiological changes occurring during ED stays. Machine learning (ML) offers a promising alternative by integrating comprehensive patient data for enhanced predictive capabilities.</p> Objective <p>This study aimed to develop and validate an ML-based early warning system to predict adverse events, including cardiac arrest, mechanical ventilation, or intensive care unit (ICU) transfer, within 48&#xa0;h of hospitalization.</p> Methods <p>This retrospective multicenter study included data from 169,807 patients across two medical centers to train ML models for predicting adverse events occurring within 48&#xa0;h of hospitalization. The prediction time origin (T0) was the moment of hospital admission. All ED data obtained before T0 were included as model input, and adverse events were defined as those occurring within 48&#xa0;h after T0. Three machine learning models were trained and evaluated: logistic regression (LR), random forest (RF), and extreme gradient boosting (XGB). The ML models were evaluated in external test cohorts with 54,515 patients from a regional teaching hospital. Model performance was assessed against traditional early warning scores, including the National Early Warning Score (NEWS) and the Modified Early Warning Score (MEWS), and Modified Sequential Organ Failure Assessment Score (mSOFA) using the area under the curve (AUC).</p> Results <p>In the internal test set, XGB achieved the highest AUC of 0.87 (95% CI: 0.85–0.89), followed by RF 0.85 (95% CI: 0.83–0.87) and LR 0.83 (95% CI: 0.81–0.85), outperforming NEWS (AUC 0.71), MEWS (0.69), and mSOFA (0.69). In the external test set, XGB maintained the best discrimination (AUC 0.82, 95% CI: 0.80–0.83), followed by RF 0.78 (95% CI: 0.77–0.80) and LR 0.77 (95% CI: 0.76–0.79), again exceeding NEWS (0.67), MEWS (0.65), and mSOFA (0.69). SHAP analyses identified respiratory rate and oxygen support as the most influential predictors.</p> Conclusion <p>The ML-based early warning system demonstrated strong predictive performance across diverse healthcare settings, significantly surpassing the capabilities of traditional scoring systems. This approach has the potential to improve risk stratification and enable timely interventions, ultimately enhancing patient outcomes.</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

Early prediction of in-hospital deterioration after emergency department admission using machine learning models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月5日

查看全文
  • Chi-Yung Cheng,
  • Ting-Hsuan Hsu,
  • Yu-Lun Hung,
  • Ting-Yu Hsu,
  • Fu-Jen Cheng,
  • Hsiu-Yung Pan,
  • Chun-Hung Richard Lin,
  • I-Min Chiu

摘要

Background

Early prediction of clinical deterioration in patients admitted to general wards from the emergency department (ED) is crucial for timely interventions and improved outcomes. Traditional scoring systems often fail to account for dynamic physiological changes occurring during ED stays. Machine learning (ML) offers a promising alternative by integrating comprehensive patient data for enhanced predictive capabilities.

Objective

This study aimed to develop and validate an ML-based early warning system to predict adverse events, including cardiac arrest, mechanical ventilation, or intensive care unit (ICU) transfer, within 48 h of hospitalization.

Methods

This retrospective multicenter study included data from 169,807 patients across two medical centers to train ML models for predicting adverse events occurring within 48 h of hospitalization. The prediction time origin (T0) was the moment of hospital admission. All ED data obtained before T0 were included as model input, and adverse events were defined as those occurring within 48 h after T0. Three machine learning models were trained and evaluated: logistic regression (LR), random forest (RF), and extreme gradient boosting (XGB). The ML models were evaluated in external test cohorts with 54,515 patients from a regional teaching hospital. Model performance was assessed against traditional early warning scores, including the National Early Warning Score (NEWS) and the Modified Early Warning Score (MEWS), and Modified Sequential Organ Failure Assessment Score (mSOFA) using the area under the curve (AUC).

Results

In the internal test set, XGB achieved the highest AUC of 0.87 (95% CI: 0.85–0.89), followed by RF 0.85 (95% CI: 0.83–0.87) and LR 0.83 (95% CI: 0.81–0.85), outperforming NEWS (AUC 0.71), MEWS (0.69), and mSOFA (0.69). In the external test set, XGB maintained the best discrimination (AUC 0.82, 95% CI: 0.80–0.83), followed by RF 0.78 (95% CI: 0.77–0.80) and LR 0.77 (95% CI: 0.76–0.79), again exceeding NEWS (0.67), MEWS (0.65), and mSOFA (0.69). SHAP analyses identified respiratory rate and oxygen support as the most influential predictors.

Conclusion

The ML-based early warning system demonstrated strong predictive performance across diverse healthcare settings, significantly surpassing the capabilities of traditional scoring systems. This approach has the potential to improve risk stratification and enable timely interventions, ultimately enhancing patient outcomes.