预测脓毒症首24小时特定治疗反应的数字孪生患者模型的开发与验证
该研究在美国一家四级学术医疗中心的内科ICU开发并前瞻性验证基于因果人工智能(有向无环图、代理建模、离散事件仿真和贝叶斯网络)的数字孪生患者模型,用于预测脓毒症首24小时对特定治疗的反应。在29例成人脓毒症患者(中位年龄60岁,中位SOFA 9.5)的145次观察中,模型预测与真实反应的一致性 primary response kappa 0.41(fair),secondary response kappa 0.65(good)。最常见的错误为编码错误(50次观察,35%)、专家规则错误(29次,20%)和时机错误(7次,5%)。结论认为在ICU早期脓毒症中开发和前瞻性测试因果AI模型可行,但模型准确性仍需提升。
要点
- 在29例成人脓毒症患者首24小时145次观察中,数字孪生预测治疗反应的一致性 primary kappa 0.41、secondary kappa 0.65。
- 模型基于有向无环图定义器官系统与治疗因果关系,采用代理建模、离散事件仿真和贝叶斯网络混合方法。
- 最常见的模型错误为编码错误(50/145次观察,35%),其次为专家规则错误(29次,20%)和时机错误(7次,5%)。
- 研究仅做标准治疗,未额外干预,模型预测与真实患者反应比较采用一致性统计。
- ICU环境因有定性定量数据和较短周转时间,被认为是开发和测试数字孪生模型的理想场所。
适用人群与场景
- 成人(>18岁)内科ICU患者,处于脓毒症首24小时。
- 排除人群原文未提及。
诊断标准与关键阈值
- 脓毒症诊断标准原文未提及,仅提及中位SOFA评分9.5(IQR 5.0-14.0)。
- 模型预测一致性评价采用kappa系数:primary response 0.41,secondary response 0.65。
处置流程与药物剂量
- 原文未提及具体药物剂量、给药途径、频次或目标值;研究仅观察标准治疗,未额外干预。
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:模型开发与前瞻性验证研究;单中心(美国四级学术医疗中心内科ICU);样本量29例患者、145次观察。
- 人群:成人(>18岁)内科ICU脓毒症患者,中位年龄60岁(54-66),中位SOFA 9.5(IQR 5.0-14.0),最常见感染源为肺炎,其次肝胆。
- 干预与对照:无额外干预,比较数字孪生预测的反应与真实患者反应。
- 主要结果:primary response一致性kappa 0.41(fair),secondary response一致性kappa 0.65(good)。
- 错误类型:编码错误50次观察(35%),专家规则错误29次(20%),时机错误7次(5%)。
证据类型、等级与局限
- 证据类型:单中心前瞻性模型验证研究(非RCT)。
- 局限:样本量小(29例)、单中心、便利抽样、原文未提及证据等级或推荐强度;模型错误率较高(编码错误35%)。
对床旁实践的改变
- 原文结论认为该数字孪生模型尚处于可行性验证阶段,不能直接用于床旁治疗决策;需进一步改进编码和专家规则以减少错误。
- ICU环境适合开发和测试数字孪生模型,但当前一致性仅fair至good,适用人群为成人内科ICU脓毒症首24小时患者。
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: To develop and verify a digital twin model of critically ill patient using the causal artificial intelligence approach to predict the response to specific treatment during the first 24 hours of sepsis.
DESIGN: Directed acyclic graphs were used to define explicitly the causal relationship among organ systems and specific treatments used. A hybrid approach of agent-based modeling, discrete-event simulation, and Bayesian network was used to simulate treatment effect across multiple stages and interactions of major organ systems (cardiovascular, neurologic, renal, respiratory, gastrointestinal, inflammatory, and hematology). Organ systems were visualized using relevant clinical markers. The application was iteratively revised and debugged by clinical experts and engineers. Agreement statistics was used to test the performance of the model by comparing the observed patient response versus the expected response (primary and secondary) predicted by digital twin.
SETTING: Medical ICU of a large quaternary- care academic medical center in the United States.
PATIENTS OR SUBJECTS: Adult (> 18 year yr old), medical ICU patients were included in the study.
INTERVENTIONS: No additional interventions were made beyond the standard of care for this study.
MEASUREMENTS AND MAIN RESULTS: During the verification phase, model performance was prospectively tested on 145 observations in a convenience sample of 29 patients. Median age was 60 years (54-66 d) with a median Sequential Organ Failure Assessment score of 9.5 (interquartile range, 5.0-14.0). The most common source of sepsis was pneumonia, followed by hepatobiliary. The observations were made during the first 24 hours of the ICU admission with one-step interventions, comparing the output in the digital twin with the real patient response. The agreement between the observed versus and the expected response ranged from fair (kappa coefficient of 0.41) for primary response to good (kappa coefficient of 0.65) for secondary response to the intervention. The most common error detected was coding error in 50 observations (35%), followed by expert rule error in 29 observations (20%) and timing error in seven observations (5%).
CONCLUSIONS: We confirmed the feasibility of development and prospective testing of causal artificial intelligence model to predict the response to treatment in early stages of critical illness. The availability of qualitative and quantitative data and a relatively short turnaround time makes the ICU an ideal environment for development and testing of digital twin patient models. An accurate digital twin model will allow the effect of an intervention to be tested in a virtual environment prior to use on real patients.
参考来源
- Lal A, Li G, Cubro E, et al. Development and Verification of a Digital Twin Patient Model to Predict Specific Treatment Response During the First 24 Hours of Sepsis. Crit Care Explor. 2020. PMID: 33225302. doi:10.1097/CCE.0000000000000249
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。