基于机器学习的医疗指令在儿科急诊中加速诊疗的评估
该研究在加拿大多伦多儿童医院急诊科开展决策分析模型研究,使用2018年7月1日至2019年6月30日共77 219次0至18岁患者就诊的回顾性电子健康记录数据,训练机器学习模型预测尿液试纸检测、心电图、腹部超声、睾丸超声、胆红素水平检测和前臂X线检查的需求。模型在各用例中曲线下面积达0.89-0.99、阳性预测值达0.77-0.94;拟实施的机器学习医疗指令可简化22.3%的就诊流程,使每名受影响患者的检查结果提前165分钟(加权均值)可用。模型可解释性显示临床相关特征对预测影响最大,且模型存在极小至无性别偏倚。作者认为该结果提示机器学习医疗指令用于临床自动化的潜力,整合入临床工作流后可能自主在就诊早期开具常见急诊检查。
要点
- 机器学习模型预测6类儿科急诊常见检查需求,曲线下面积0.89-0.99、阳性预测值0.77-0.94。
- 拟实施机器学习医疗指令可简化22.3%的全部就诊流程,每名受影响患者检查结果提前165分钟(加权均值)可用。
- 模型在各用例中均由临床相关特征对预测影响最大,且表现极小至无性别偏倚。
- 研究为基于回顾性电子健康记录数据的决策分析模型研究,数据来自2018年7月1日至2019年6月30日共77 219次0至18岁患者就诊。
- 作者认为机器学习医疗指令整合入临床工作流后,可能自主在就诊早期开具常见急诊检查并向患者和临床医生提供可解释性。
适用人群与场景
- 2018年7月1日至2019年6月30日就诊于加拿大多伦多儿童医院急诊科、年龄0至18岁的全部患者,共77 219次就诊。
研究设计与关键结果
- 研究类型为决策分析模型研究,基于回顾性电子健康记录数据训练机器学习模型,数据来自加拿大多伦多儿童医院急诊科2018年7月1日至2019年6月30日共77 219次0至18岁患者就诊,其中男孩42 238名(54.7%),平均(SD)年龄5.4(4.8)岁。
- 模型预测的检查包括尿液试纸检测、心电图、腹部超声、睾丸超声、胆红素水平检测和前臂X线检查。
- 各用例模型曲线下面积0.89-0.99,阳性预测值0.77-0.94;模型决策阈值设定为限制假阳性总数并达到高阳性预测值。
- 拟实施的机器学习医疗指令可简化22.3%的全部就诊流程,并使每名受影响患者的检查结果提前165分钟(加权均值)可用。
- 各机器学习医疗指令的可解释性显示临床相关特征对模型预测影响最大;模型表现极小至无性别偏倚。
证据类型、等级与局限
- 证据类型:基于回顾性电子健康记录数据的决策分析模型研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为该研究结果提示机器学习医疗指令用于临床自动化的潜力。
- 作者认为机器学习医疗指令整合入临床工作流后,可能自主在患者就诊早期开具常见急诊检查,并向患者和临床医生提供可解释性。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
IMPORTANCE: Increased wait times and long lengths of stay in emergency departments (EDs) are associated with poor patient outcomes. Systems to improve ED efficiency would be useful. Specifically, minimizing the time to diagnosis by developing novel workflows that expedite test ordering can help accelerate clinical decision-making.
OBJECTIVE: To explore the use of machine learning-based medical directives (MLMDs) to automate diagnostic testing at triage for patients with common pediatric ED diagnoses.
DESIGN, SETTING, AND PARTICIPANTS: Machine learning models trained on retrospective electronic health record data were evaluated in a decision analytical model study conducted at the ED of the Hospital for Sick Children Toronto, Canada. Data were collected on all patients aged 0 to 18 years presenting to the ED from July 1, 2018, to June 30, 2019 (77 219 total patient visits).
EXPOSURE: Machine learning models were trained to predict the need for urinary dipstick testing, electrocardiogram, abdominal ultrasonography, testicular ultrasonography, bilirubin level testing, and forearm radiographs.
MAIN OUTCOMES AND MEASURES: Models were evaluated using area under the receiver operator curve, true-positive rate, false-positive rate, and positive predictive values. Model decision thresholds were determined to limit the total number of false-positive results and achieve high positive predictive values. The time difference between patient triage completion and test ordering was assessed for each use of MLMD. Error rates were analyzed to assess model bias. In addition, model explainability was determined using Shapley Additive Explanations values.
RESULTS: There was a total of 42 238 boys (54.7%) included in model development; mean (SD) age of the children was 5.4 (4.8) years. Models obtained high area under the receiver operator curve (0.89-0.99) and positive predictive values (0.77-0.94) across each of the use cases. The proposed implementation of MLMDs would streamline care for 22.3% of all patient visits and make test results available earlier by 165 minutes (weighted mean) per affected patient. Model explainability for each MLMD demonstrated clinically relevant features having the most influence on model predictions. Models also performed with minimal to no sex bias.
CONCLUSIONS AND RELEVANCE: The findings of this study suggest the potential for clinical automation using MLMDs. When integrated into clinical workflows, MLMDs may have the potential to autonomously order common ED tests early in a patient's visit with explainability provided to patients and clinicians.
参考来源
- Singh D, Nagaraj S, Mashouri P, et al. Assessment of Machine Learning-Based Medical Directives to Expedite Care in Pediatric Emergency Medicine. JAMA Netw Open. 2022. PMID: 35294539. doi:10.1001/jamanetworkopen.2022.2599
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。