Abstract

Objective

We aimed to develop a model for accurate prediction of general care inpatient deterioration.

Materials and Methods

Training and internal validation datasets were built using 2-year data from a quaternary hospital in the Midwest. Model training used gradient boosting and feature engineering (clinically relevant interactions, time-series information) to predict general care inpatient deterioration (resuscitation call, intensive care unit transfer, or rapid response team call) in 24 hours. Data from a tertiary care hospital in the Southwest were used for external validation. C-statistic, sensitivity, positive predictive value, and alert rate were calculated for different cutoffs and compared with the National Early Warning Score. Sensitivity analysis evaluated prediction of intensive care unit transfer or resuscitation call.

Results

Training, internal validation, and external validation datasets included 24 500, 25 784 and 53 956 hospitalizations, respectively. The Mayo Clinic Early Warning Score (MC-EWS) demonstrated excellent discrimination in both the internal and external validation datasets (C-statistic = 0.913, 0.937, respectively), and results were consistent in the sensitivity analysis (C-statistic = 0.932 in external validation). At a sensitivity of 73%, MC-EWS would generate 0.7 alerts per day per 10 patients, 45% less than the National Early Warning Score.

Discussion

Low alert rates are important for implementation of an alert system. Other early warning scores developed for the general care ward have achieved lower discrimination overall compared with MC-EWS, likely because MC-EWS includes both nursing assessments and extensive feature engineering.

Conclusions

MC-EWS achieved superior prediction of general care inpatient deterioration using sophisticated feature engineering and a machine learning approach, reducing alert rate.

中文翻译：

---

使用机器学习提高患者恶化预测的准确性：梅奥诊所早期预警评分 (MC-EWS)

摘要

客观的

我们的目标是开发一个模型，用于准确预测普​​通护理住院患者的恶化。

材料和方法

训练和内部验证数据集是使用来自中西部一家四级医院的 2 年数据构建的。模型训练使用梯度提升和特征工程（临床相关交互、时间序列信息）来预测 24 小时内的普通护理住院患者恶化（复苏呼叫、重症监护病房转移或快速响应团队呼叫）。来自西南地区一家三级医院的数据被用于外部验证。计算不同临界值的 C 统计量、敏感性、阳性预测值和警报率，并与国家早期预警评分进行比较。敏感性分析评估了重症监护病房转移或复苏呼叫的预测。

结果

培训、内部验证和外部验证数据集分别包括 24 500、25 784 和 53 956 次住院。Mayo Clinic 早期预警评分 (MC-EWS) 在内部和外部验证数据集中均表现出出色的辨别力（C 统计量分别为 0.913、0.937），并且在敏感性分析中结果一致（外部 C 统计量 = 0.932）验证）。在 73% 的灵敏度下，MC-EWS 每 10 名患者每天会产生 0.7 个警报，比国家早期预警评分低 45%。

讨论

低警报率对于警报系统的实施很重要。与 MC-EWS 相比，为普通护理病房开发的其他早期预警评分总体上实现了较低的识别率，这可能是因为 MC-EWS 包括护理评估和广泛的特征工程。

结论

MC-EWS 使用复杂的特征工程和机器学习方法实现了对普通护理住院患者恶化的卓越预测，从而降低了警报率。