使用机器学习预测儿科重症与常规护理住院患者的未来护理需求
该研究基于Health Facts数据库2009-2016年住院患儿(ICU组n=20,014,随机无ICU常规护理组n=20,130)开发并验证四个独立、序贯、全连接神经网络模型,预测未来6-12、12-18、18-24、24-30小时需ICU护理的风险。测试集敏感性≥0.727、特异性≥0.885、准确率>0.850、AUC≥0.917,校准良好(R²>0.98)。2017-2018独立队列(n=80,089)敏感性≥0.545、特异性≥0.972、准确率≥0.921、AUC≥0.946。模拟儿童医院及按教学状态、床位数、地理位置分层医院性能相当。结论认为该模型性能有前景,且预测时间窗延长至24-30小时性能相似。
要点
- 模型预测住院患儿未来6-12至24-30小时需ICU护理,测试集AUC≥0.917,独立2017-2018队列AUC≥0.946。
- 独立队列敏感性≥0.545、特异性≥0.972、准确率≥0.921,提示高特异性但敏感性相对较低。
- 模型性能在预测时间窗从6-12小时延长至24-30小时时保持相似,未因时间窗延长而明显下降。
- 模拟儿童医院及按教学状态、床位数、地理位置分层医院性能相当,提示初步可推广性。
- 研究为预测建模,未报告临床实施后的干预效果或患者结局改善。
适用人群与场景
- 来自Health Facts数据库2009-2016年住院患儿,ICU组为至少一次ICU入住(n=20,014),常规护理组为随机选取无ICU入住患儿(n=20,130)。
- 独立验证队列为2017-2018年住院患儿(n=80,089)。
诊断标准与关键阈值
- 主要结局为基于生理、治疗和护理强度定义的未来四个时间段(6-12、12-18、18-24、24-30小时)需ICU护理或非ICU护理。
- 原文未提及具体生理、治疗和护理强度指标及阈值。
处置流程与药物剂量
- 原文未提及
红旗征与不能漏的情况
- 原文未提及
研究设计与关键结果
- 研究类型为预测建模,使用Health Facts数据库开发并验证四个独立、序贯、全连接神经网络模型,训练集64%、验证集8%、测试集28%。
- 测试集性能:敏感性≥0.727,特异性≥0.885,准确率>0.850,AUC≥0.917,校准R²>0.98。
- 2017-2018独立队列性能:敏感性≥0.545,特异性≥0.972,准确率≥0.921,AUC≥0.946,R²≥0.979。
- 模拟儿童医院及按教学状态、床位数、地理位置分层医院性能相当。
证据类型、等级与局限
- 证据类型为预测建模研究,非RCT或系统评价;原文未给出证据等级或推荐强度。
- 局限:原文未明确列出局限;设计上为回顾性数据库建模,独立队列敏感性较低(≥0.545),需前瞻性验证。
对床旁实践的改变
- 原文未提及对急诊/ICU具体实践的改变;模型为预测工具,尚未报告临床实施效果。
- 高特异性(独立队列≥0.972)可能有助于识别低风险患儿,但敏感性≥0.545提示可能漏判部分需ICU护理者,不能单独用于降级决策。
- 预测时间窗延长至24-30小时性能相似,或可支持较长时间窗的床位与资源规划,但需前瞻性验证。
指南或共识出处
- 原文未提及
以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。
英文原文(摘要)· 点击展开
UNLABELLED: Develop and compare separate prediction models for ICU and non-ICU care for hospitalized children in four future time periods (6-12, 12-18, 18-24, and 24-30 hr) and assess these models in an independent cohort and simulated children's hospital.
DESIGN: Predictive modeling used cohorts from the Health Facts database (Cerner Corporation, Kansas City, MO).
SETTING: Children hospitalized in ICUs.
PATIENTS: Children with greater than or equal to one ICU admission (n = 20,014) and randomly selected routine care children without ICU admission (n = 20,130) from 2009 to 2016 were used for model development and validation. An independent 2017-2018 cohort consisted of 80,089 children.
INTERVENTIONS: None.
MEASUREMENT AND MAIN RESULTS: Initially, we undersampled non-ICU patients for development and comparison of the models. We randomly assigned 64% of patients for training, 8% for validation, and 28% for testing in both clinical groups. Two additional validation cohorts were tested: a simulated children's hospitals and the 2017-2018 cohort. The main outcome was ICU care or non-ICU care in four future time periods based on physiology, therapy, and care intensity. Four independent, sequential, and fully connected neural networks were calibrated to risk of ICU care at each time period. Performance for all models in the test sample were comparable including sensitivity greater than or equal to 0.727, specificity greater than or equal to 0.885, accuracy greater than 0.850, area under the receiver operating characteristic curves greater than or equal to 0.917, and all had excellent calibration (all R2 s > 0.98). Model performance in the 2017-2018 cohort was sensitivity greater than or equal to 0.545, specificity greater than or equal to 0.972, accuracy greater than or equal to 0.921, area under the receiver operating characteristic curves greater than or equal to 0.946, and R2 s greater than or equal to 0.979. Performance metrics were comparable for the simulated children's hospital and for hospitals stratified by teaching status, bed numbers, and geographic location.
CONCLUSIONS: Machine learning models using physiology, therapy, and care intensity predicting future care needs had promising performance metrics. Notably, performance metrics were similar as the prediction time periods increased from 6-12 hours to 24-30 hours.
参考来源
- Trujillo Rivera EA, Chamberlain JM, Patel AK, et al. Predicting Future Care Requirements Using Machine Learning for Pediatric Intensive and Routine Care Inpatients. Crit Care Explor. 2021. PMID: 34396143. doi:10.1097/CCE.0000000000000505
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。