预测肝素治疗结局并提供剂量推荐的临床预测模型:开发与验证研究
本研究采用浅层神经网络,在MIMIC III数据库3607例与北京协和医院1549例符合标准的患者中,以亚治疗、正常、超治疗aPTT为结局建模,并设计剂量推荐模块。模型F1分数在MIMIC III为0.887、PUMCH为0.925。与实际处方相比,模型建议对72.2%(MIMIC III,1240/1718)和64.7%(PUMCH,281/434)的亚治疗患者增加剂量,对80.9%(MIMIC III,504/623)和76.7%(PUMCH,277/361)的超治疗患者减少剂量。作者认为该模型可能有助于减少肝素剂量不当并为临床医生提供决策推荐。
要点
- 模型将肝素治疗患者分为亚治疗、正常、超治疗3种aPTT治疗状态,F1分数MIMIC III 0.887、PUMCH 0.925。
- 与实际处方相比,模型建议72.2%(MIMIC III,1240/1718)和64.7%(PUMCH,281/434)的亚治疗患者增加剂量。
- 模型建议80.9%(MIMIC III,504/623)和76.7%(PUMCH,277/361)的超治疗患者减少剂量。
- 作者认为该模型可能有助于减少肝素剂量不当,并为临床医生提供适当的决策推荐。
适用人群与场景
- MIMIC III数据库中符合标准的ICU患者3607例,以及北京协和医院(PUMCH)符合标准的患者1549例。
研究设计与关键结果
- 研究类型:回顾性队列研究,开发并验证基于浅层神经网络的模型,数据来自MIMIC III数据库与北京协和医院(PUMCH)。
- 样本量:MIMIC III 3607例,PUMCH 1549例,均为符合研究标准的患者。
- 干预与对照:模型以亚治疗、正常、超治疗活化部分凝血活酶时间(aPTT)为肝素治疗结局,使用一组临床特征建模,将患者分为3种治疗状态;并与实际处方剂量进行比较。
- 主要终点:模型预测性能,F1分数MIMIC III 0.887、PUMCH 0.925;同时使用准确率、kappa系数、精确率、召回率评估。
- 剂量推荐模块结果:与实际处方相比,模型建议对亚治疗患者增加剂量的比例分别为MIMIC III 72.2%(1240/1718)、PUMCH 64.7%(281/434);建议对超治疗患者减少剂量的比例分别为MIMIC III 80.9%(504/623)、PUMCH 76.7%(277/361)。
- 作者认为这些推荐可能有助于临床改善,并可能有效减少临床环境中达到最佳剂量的时间。
证据类型、等级与局限
- 证据类型:回顾性队列研究(模型开发与验证研究)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为该模型可能有助于减少肝素剂量不当,并为临床医生提供适当的决策推荐。
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
BACKGROUND: Unfractionated heparin is widely used in the intensive care unit as an anticoagulant. However, weight-based heparin dosing has been shown to be suboptimal and may place patients at unnecessary risk during their intensive care unit stay.
OBJECTIVE: In this study, we intended to develop and validate a machine learning-based model to predict heparin treatment outcomes and to provide dosage recommendations to clinicians.
METHODS: A shallow neural network model was adopted in a retrospective cohort of patients from the Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC III) database and patients admitted to the Peking Union Medical College Hospital (PUMCH). We modeled the subtherapeutic, normal, and supratherapeutic activated partial thromboplastin time (aPTT) as the outcomes of heparin treatment and used a group of clinical features for modeling. Our model classifies patients into 3 different therapeutic states. We tested the prediction ability of our model and evaluated its performance by using accuracy, the kappa coefficient, precision, recall, and the F1 score. Furthermore, a dosage recommendation module was designed and evaluated for clinical decision support.
RESULTS: A total of 3607 patients selected from MIMIC III and 1549 patients admitted to the PUMCH who met our criteria were included in this study. The shallow neural network model showed results of F1 scores 0.887 (MIMIC III) and 0.925 (PUMCH). When compared with the actual dosage prescribed, our model recommended increasing the dosage for 72.2% (MIMIC III, 1240/1718) and 64.7% (PUMCH, 281/434) of the subtherapeutic patients and decreasing the dosage for 80.9% (MIMIC III, 504/623) and 76.7% (PUMCH, 277/361) of the supratherapeutic patients, suggesting that the recommendations can contribute to clinical improvements and that they may effectively reduce the time to optimal dosage in the clinical setting.
CONCLUSIONS: The evaluation of our model for predicting heparin treatment outcomes demonstrated that the developed model is potentially applicable for reducing the misdosage of heparin and for providing appropriate decision recommendations to clinicians.
参考来源
- Li D, Gao J, Hong N, et al. A Clinical Prediction Model to Predict Heparin Treatment Outcomes and Provide Dosage Recommendations: Development and Validation Study. J Med Internet Res. 2021. PMID: 34014171. doi:10.2196/27118
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。