Using machine learning models to predict oxygen saturation following ventilator support adjustment in critically ill children: A single center pilot study

Background
In an intensive care units, experts in mechanical ventilation are not continuously at patient’s bedside to adjust ventilation settings and to analyze the impact of these adjustments on gas exchange. The development of clinical decision support systems analyzing patients’ data in real time offers an opportunity to fill this gap.
Objective
The objective of this study was to determine whether a machine learning predictive model could be trained on a set of clinical data and used to predict transcutaneous hemoglobin oxygen saturation 5 min (5min SpO2) after a ventilator setting change.
Data sources
Data of mechanically ventilated children admitted between May 2015 and April 2017 were included and extracted from a high-resolution research database. More than 776,727 data rows were obtained from 610 patients, discretized into 3 class labels (< 84%, 85% to 91% and c92% to 100%).
Performance metrics of predictive models
Due to data imbalance, four different data balancing processes were applied. Then, two machine learning models (artificial neural network and Bootstrap aggregation of complex decision trees) were trained and tested on these four different balanced datasets. The best model predicted SpO2 with area under the curves < 0.75.
Conclusion
This single center pilot study using machine learning predictive model resulted in an algorithm with poor accuracy. The comparison of machine learning models showed that bagged complex trees was a promising approach. However, there is a need to improve these models before incorporating them into a clinical decision support systems. One potentially solution for improving predictive model, would be to increase the amount of data available to limit over-fitting that is potentially one of the cause for poor classification performances for 2 of the three class labels.

研究背景
在重症监护病房中，机械通气专家无法持续驻守患者病床旁，以调整通气参数并分析此类参数调整对气体交换的影响。实时分析患者临床数据的临床决策支持系统（clinical decision support system）的研发，为填补这一空白提供了可行路径。

研究目标
本研究旨在验证：能否基于一组临床数据训练机器学习预测模型（machine learning predictive model），并以此预测通气参数调整后5分钟的经皮血红蛋白氧饱和度（transcutaneous hemoglobin oxygen saturation，5min SpO2）。

数据来源
本研究纳入2015年5月至2017年4月期间收治的机械通气患儿数据，数据源自一套高分辨率研究数据库。最终从610例患者中获取超过776727条数据记录，并将其离散化为3个类别标签：<84%、85%~91% 以及 ≥92%~100%。

预测模型性能评估
由于存在数据类别不平衡问题，本研究采用了4种不同的数据平衡处理流程。随后，针对这4组经平衡处理的数据集，对两种机器学习模型展开训练与测试：人工神经网络（artificial neural network），以及复杂决策树的Bootstrap聚合模型（Bootstrap aggregation of complex decision trees）。性能最优的模型在预测SpO2时的曲线下面积（area under the curve, AUC）小于0.75。

研究结论
本项单中心预试验采用机器学习预测模型，所得到的算法精度欠佳。机器学习模型对比结果显示，装袋复杂决策树模型是一种颇具潜力的方案。但在将此类模型集成至临床决策支持系统之前，仍需对其进行优化。提升预测模型性能的可行思路之一，便是扩充可用数据集规模，以限制过拟合问题——该问题或是导致3个类别标签中2个的分类表现不佳的潜在原因之一。