人工智能预测急诊科就诊的计费代码等级
本研究利用健康系统2023年1月至9月的321,893例成人急诊就诊数据,开发结合自然语言处理与机器学习的集成模型,从临床记录、临床特征和医嘱预测评估与管理专业计费代码(2至5级及重症监护)。模型预测4级和5级的AUC分别为0.94和0.95,准确率0.80和0.92,F1分数0.79和0.91。在95%决策边界阈值下,5级预测的精确率/阳性预测值为0.99,召回率/敏感度为0.57。结论认为当前AI模型能准确预测急诊计费代码等级,有潜力自动化编码并节省行政成本和时间。
要点
- 模型预测专业计费代码4级和5级的AUC分别为0.94和0.95,准确率0.80和0.92,F1分数0.79和0.91。
- 在95%决策边界阈值下,5级预测图表的精确率/阳性预测值为0.99,召回率/敏感度为0.57。
- 最重要的模型特征(Shapley Additive Explanations值)为重症监护记录、医嘱数量、出院去向、心内科和精神科。
- 就诊计费等级分布:2级<1%、3级5%、4级38%、5级51%、重症监护5%。
- 结论认为当前AI模型可准确预测急诊计费代码等级,有潜力自动化编码并节省行政成本和时间。
适用人群与场景
- 2023年1月至9月本健康系统的成人急诊就诊者。
研究设计与关键结果
- 研究类型为利用自然语言处理和机器学习技术开发集成模型,数据为2023年1月至9月本健康系统的321,893例成人急诊就诊。
- 主要终点为预测评估与管理专业计费代码(2至5级[Current Procedural Terminology代码99282至99285]及重症监护)。
- 就诊计费等级分布:2级<1%、3级5%、4级38%、5级51%、重症监护5%。
- 模型预测专业计费代码4级和5级的受试者工作特征曲线下面积分别为0.94和0.95,准确率分别为0.80和0.92,F1分数分别为0.79和0.91。
- 在95%决策边界阈值下,5级预测图表的精确率/阳性预测值为0.99,召回率/敏感度为0.57。
- 使用Shapley Additive Explanations值确定的最重要特征为重症监护记录、医嘱数量、出院去向、心内科和精神科。
- 次要终点包括在不同决策边界阈值下预测专业计费代码以及模型在其他急诊科的泛化能力。
证据类型、等级与局限
- 证据类型:基于健康系统急诊就诊数据的模型开发研究;原文未报告证据等级。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为当前可用的AI模型能基于临床记录、临床特征和医嘱准确预测急诊计费代码等级,有潜力自动化急诊编码并节省行政成本和时间。
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
STUDY OBJECTIVE: To use artificial intelligence (AI) to predict billing code levels for emergency department (ED) encounters.
METHODS: We accessed ED encounters from our health system from January to September 2023. We developed an ensemble model using natural language processing and machine learning techniques to predict billing codes from clinical notes combined with clinical characteristics and orders. Explainable AI techniques were used to help determine the important model features. The main endpoint was to predict evaluation and management professional billing codes (levels 2 to 5 [Current Procedural Terminology codes 99282 to 99285] and critical care). Secondary endpoints included predicting professional billing codes at different decision boundary thresholds and generalizability of the model at other EDs.
RESULTS: There were 321,893 adult ED encounters coded at levels 2 (<1%), 3 (5%), 4 (38%), 5 (51%), and critical care (5%). Model performance for professional billing code levels of 4 and 5 yielded area under the receiver operating characteristic curve values of 0.94 and 0.95, accuracy values of 0.80 and 0.92, and F1-scores of 0.79 and 0.91, respectively. At a 95% decision boundary threshold, level 5 predicted charts had a precision/positive predictive value of 0.99 and recall/sensitivity of 0.57. The most important features using Shapley Additive Explanations values were critical care note, number of orders, discharge disposition, cardiology, and psychiatry.
CONCLUSION: Currently available AI models accurately predict billing code levels for ED encounters based on clinical notes, clinical characteristics, and orders. This has the potential to automate coding of ED encounters and save administrative costs and time.
参考来源
- Morey J, Winters R, Jones D, et al. Artificial Intelligence to Predict Billing Code Levels of Emergency Department Encounters. Ann Emerg Med. 2024. PMID: 39320279. doi:10.1016/j.annemergmed.2024.07.011
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。