Abstract

Objective

The study sought to determine whether machine learning can predict initial inpatient total daily dose (TDD) of insulin from electronic health records more accurately than existing guideline-based dosing recommendations.

Materials and Methods

Using electronic health records from a tertiary academic center between 2008 and 2020 of 16,848 inpatients receiving subcutaneous insulin who achieved target blood glucose control of 100-180 mg/dL on a calendar day, we trained an ensemble machine learning algorithm consisting of regularized regression, random forest, and gradient boosted tree models for 2-stage TDD prediction. We evaluated the ability to predict patients requiring more than 6 units TDD and their point-value TDDs to achieve target glucose control.

Results

The method achieves an area under the receiver-operating characteristic curve of 0.85 (95% confidence interval [CI], 0.84-0.87) and area under the precision-recall curve of 0.65 (95% CI, 0.64-0.67) for classifying patients who require more than 6 units TDD. For patients requiring more than 6 units TDD, the mean absolute percent error in dose prediction based on standard clinical calculators using patient weight is in the range of 136%-329%, while the regression model based on weight improves to 60% (95% CI, 57%-63%), and the full ensemble model further improves to 51% (95% CI, 48%-54%).

Discussion

Owingto the narrow therapeutic window and wide individual variability, insulin dosing requires adaptive and predictive approaches that can be supported through data-driven analytic tools.

Conclusions

Machine learning approaches based on readily available electronic medical records can discriminate which inpatients will require more than 6 units TDD and estimate individual doses more accurately than standard guidelines and practices.

中文翻译：

---

用于住院患者初始胰岛素估计的机器学习

 抽象的

 客观的

该研究试图确定机器学习是否可以比现有基于指南的剂量建议更准确地从电子健康记录中预测住院患者每日总胰岛素剂量 (TDD)。

 材料和方法

使用 2008 年至 2020 年间来自一家三级学术中心的 16,848 名接受皮下注射胰岛素的住院患者的电子健康记录，这些患者在一个日历日实现了 100-180 mg/dL 的目标血糖控制，我们训练了一种集成机器学习算法，该算法包括正则回归、随机回归和随机回归。用于 2 阶段 TDD 预测的森林和梯度提升树模型。我们评估了预测需要超过 6 个单位 TDD 的患者及其点值 TDD 以实现目标血糖控制的能力。

 结果

该方法的受试者操作特征曲线下面积为 0.85（95% 置信区间 [CI]，0.84-0.87），精确回忆曲线下面积为 0.65（95% CI，0.64-0.67），用于对以下患者进行分类：需要超过 6 个单位的 TDD。对于需要超过 6 个单位 TDD 的患者，根据使用患者体重的标准临床计算器进行剂量预测的平均绝对百分比误差在 136%-329% 范围内，而基于体重的回归模型则提高到 60%（95% CI，57%-63%），完整集成模型进一步提高至 51%（95% CI，48%-54%）。

 讨论

由于治疗窗口窄和个体差异大，胰岛素剂量需要适应性和预测性方法，这些方法可以通过数据驱动的分析工具来支持。

 结论

基于现成电子病历的机器学习方法可以区分哪些住院患者需要超过 6 个单位的 TDD，并比标准指南和实践更准确地估计个人剂量。