智能手机应用模型预测大量输血需求的外部验证:采用五种不同定义
该研究利用PRospective, Observational, Multicenter, Major Trauma Transfusion数据库对先前基于单中心数据开发的智能手机应用模型进行外部验证,该模型用于预测大量输血方案启动或大量输血实施。研究纳入1,245例患者,采用五种大量输血定义评估模型预测概率与观察结局的受试者工作特征曲线。结果显示,预测大量输血方案启动的AUC为0.694,预测大量输血实施的AUC范围为0.695至0.711,无论采用何种定义预测能力一致。作者认为该应用模型在外部同质人群中预测大量输血需求的能力为中等,且应用允许模型迭代重新校准(「机器学习」),随着数据积累可能改善预测能力。
要点
- 在1,245例患者中,预测大量输血方案启动的AUC为0.694,预测大量输血实施的AUC为0.695至0.711,预测能力为中等。
- 五种大量输血定义下模型预测能力一致:定义1(24小时10单位PRBC)297例(24%)、定义2(复苏强度评分≥4)570例(47%)、定义3(临界给药阈值)364例(33%)、定义4(4小时4单位PRBC)599例(49.1%)、定义5(6小时6单位PRBC)395例(32.4%)。
- 该应用模型允许迭代重新校准(「机器学习」),随着额外数据积累可能改善预测能力。
- 证据等级为诊断试验研究/预后研究,level III。
适用人群与场景
- PRospective, Observational, Multicenter, Major Trauma Transfusion数据库中的1,245例患者。
诊断标准与关键阈值
- 大量输血定义1:24小时内输注10单位浓缩红细胞。
- 大量输血定义2:复苏强度评分≥4。
- 大量输血定义3:临界给药阈值。
- 大量输血定义4:4小时内输注4单位浓缩红细胞。
- 大量输血定义5:6小时内输注6单位浓缩红细胞。
研究设计与关键结果
- 研究类型为诊断试验研究/预后研究,利用PRospective, Observational, Multicenter, Major Trauma Transfusion数据库对应用模型进行外部验证,样本量1,245例。
- 预测大量输血方案启动的AUC为0.694;预测大量输血实施的AUC范围为0.695至0.711。
- 定义1(24小时10单位PRBC)297例(24%),定义2(复苏强度评分≥4)570例(47%),定义3(临界给药阈值)364例(33%),定义4(4小时4单位PRBC)599例(49.1%),定义5(6小时6单位PRBC)395例(32.4%)。
证据类型、等级与局限
- 证据类型:诊断试验研究/预后研究,证据等级level III。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,该应用模型在外部同质人群中预测大量输血需求的能力为中等,且应用允许模型迭代重新校准(「机器学习」),随着额外数据积累可能改善预测能力。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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: Previously, a model to predict massive transfusion protocol (MTP) (activation) was derived using a single-institution data set. The PRospective, Observational, Multicenter, Major Trauma Transfusion database was used to externally validate this model's ability to predict both MTP activation and massive transfusion (MT) administration using multiple MT definitions.
METHODS: The app model was used to calculate the predicted probability of MTP activation or MT delivery. The five definitions of MT used were: (1) 10 units packed red blood cells (PRBCs) in 24 hours, (2) Resuscitation Intensity score ≥ 4, (3) critical administration threshold, (4) 4 units PRBCs in 4 hours; and (5) 6 units PRBCs in 6 hours. Receiver operating curves were plotted to compare the predicted probability of MT with observed outcomes.
RESULTS: Of 1,245 patients in the data set, 297 (24%) met definition 1, 570 (47%) met definition 2, 364 (33%) met definition 3, 599 met definition 4 (49.1%), and 395 met definition 5 (32.4%). Regardless of the outcome (MTP activation or MT administration), the predictive ability of the app model was consistent: when predicting activation of the MTP, the area under the curve for the model was 0.694 and when predicting MT administration, the area under the curve ranged from 0.695 to 0.711.
CONCLUSION: Regardless of the definition of MT used, the app model demonstrates moderate ability to predict the need for MT in an external, homogenous population. Importantly, the app allows the model to be iteratively recalibrated ("machine learning") and thus could improve its predictive capability as additional data are accrued.
LEVEL OF EVIDENCE: Diagnostic test study/Prognostic study, level III.
参考来源
- Hodgman EI, Cripps MW, Mina MJ, et al. External validation of a smartphone app model to predict the need for massive transfusion using five different definitions. J Trauma Acute Care Surg. 2018. PMID: 29200079. doi:10.1097/TA.0000000000001756
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。