School of Biomedical Informatics, UTHealth, United States; Department of Mathematical Sciences, Tsinghua University, China.
Department of Pediatric Surgery, McGovern Medical School, UTHealth, United States.
Int J Med Inform. 2020 Dec;144:104282. doi: 10.1016/j.ijmedinf.2020.104282. Epub 2020 Sep 22.
To build a machine-learning model that predicts laboratory test results and provides a promising lab test reduction strategy, using spatial-temporal correlations.
We developed a global prediction model to treat laboratory testing as a series of decisions by considering contextual information over time and across modalities. We validated our method using a critical care database (MIMIC III), which includes 4,570,709 observations of 12 standard laboratory tests, among 38,773 critical care patients. Our deep-learning model made real-time laboratory reduction recommendations and predicted the properties of lab tests, including values, normal/abnormal (whether labs were within the normal range) and transition (normal to abnormal or abnormal to normal from the latest lab test). We reported area under the receiver operating characteristic curve (AUC) for predicting normal/abnormal, evaluated accuracy and absolute bias on prediction vs. observation against lab test reduction proportion. We compared our model against baseline models and analyzed the impact of variations on the recommended reduction strategy.
Our best model offered a 20.26 % reduction in the number of laboratory tests. By applying the recommended reduction policy on the hold-out dataset (7755 patients), our model predicted normality/abnormality of laboratory tests with a 98.27 % accuracy (AUC, 0.9885; sensitivity, 97.84 %; specificity, 98.80 %; PPV, 99.01 %; NPV, 97.39 %) on 20.26 % reduced lab tests, and recommended 98.10 % of transitions to be checked. Our model performed better than the greedy models, and the recommended reduction strategy was robust.
Strong spatial and temporal correlations between laboratory tests can be used to optimize policies for reducing laboratory tests throughout the hospital course. Our method allows for iterative predictions and provides a superior solution for the dynamic decision-making laboratory reduction problem.
This work demonstrates a machine-learning model that assists physicians in determining which laboratory tests may be omitted.
利用时空相关性构建机器学习模型，预测实验室检测结果，并提供有前景的实验室检测减少策略。
我们开发了一个全局预测模型，通过考虑随时间和模态的上下文信息，将实验室检测视为一系列决策。我们使用包含 38773 名危重症患者的 12 项标准实验室检测的 4570709 个观测值的 MIMIC III 数据库验证了我们的方法。我们的深度学习模型实时提供实验室检测减少建议，并预测实验室检测的特性，包括值、正常/异常（实验室检测值是否在正常范围内）和转变（从最新的实验室检测结果看，正常转为异常或异常转为正常）。我们报告了预测正常/异常的受试者工作特征曲线下面积（AUC），并针对实验室检测减少比例评估了预测与观察的准确性和绝对偏差。我们将我们的模型与基线模型进行了比较，并分析了变化对推荐减少策略的影响。
我们的最佳模型提供了 20.26%的实验室检测减少数量。通过将推荐的减少策略应用于保留数据集（7755 名患者），我们的模型对实验室检测的正常/异常预测的准确率为 98.27%（AUC 为 0.9885；敏感性为 97.84%；特异性为 98.80%；PPV 为 99.01%；NPV 为 97.39%），减少了 20.26%的实验室检测，建议 98.10%的转变需要进行检查。我们的模型优于贪心模型，推荐的减少策略具有鲁棒性。
实验室检测之间存在很强的空间和时间相关性，可以用于优化整个医院病程中的实验室检测减少策略。我们的方法允许迭代预测，并为动态决策实验室检测减少问题提供了更好的解决方案。
这项工作展示了一种机器学习模型，可以帮助医生确定哪些实验室检测可以省略。
