Roy Shivaal K, Hom Jason, Mackey Lester, Shah Neil, Chen Jonathan H
Department of Computer Science, Stanford University, Stanford, CA, USA.
Department of Medicine, Stanford University, Stanford, CA, USA.
AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:217-226. eCollection 2018.
Escalating healthcare costs and inconsistent quality is exacerbated by clinical practice variability. Diagnostic testing is the highest volume medical activity, but human intuition is typically unreliable for inferences on diagnostic performance characteristics. Electronic medical records from a tertiary academic hospital (2008-2014) allow us to systematically predict laboratory pre-test probabilities of being normal under different conditions. We find that low yield laboratory tests are common (e.g., ~90% of blood cultures are normal). Clinical decision support could triage cases based on available data, such as consecutive use (e.g., lactate, potassium, and troponin are >90% normal given two previously normal results) or more complex patterns assimilated through common machine learning methods (nearly 100% precision for the top 1% of several example labs).
临床实践的变异性加剧了医疗成本的不断攀升和质量的参差不齐。诊断测试是开展量最大的医疗活动，但仅凭人类直觉推断诊断性能特征通常并不可靠。一家三级学术医院2008年至2014年的电子病历使我们能够系统地预测不同条件下实验室检测前结果正常的概率。我们发现低产出的实验室检测很常见（例如，约90%的血培养结果正常）。临床决策支持可以根据现有数据对病例进行分类，比如连续检测结果（例如，如果前两次检测结果正常，那么乳酸、钾和肌钙蛋白检测结果正常的概率>90%），或者通过常见机器学习方法归纳出的更复杂模式（几个示例实验室中排名前1%的检测结果，其准确率接近100%）。
