Division of Gastroenterology and Hepatology, Stanford University, Stanford, California, USA.
Kaiser Foundation Hospitals, Pasadena, California, USA.
Clin Transl Gastroenterol. 2023 Oct 1;14(10):e00634. doi: 10.14309/ctg.0000000000000634.
Esophageal 24-hour pH/impedance testing is routinely performed to diagnose gastroesophageal reflux disease. Interpretation of these studies is time-intensive for expert physicians and has high inter-reader variability. There are no commercially available machine learning tools to assist with automated identification of reflux events in these studies.
A machine learning system to identify reflux events in 24-hour pH/impedance studies was developed, which included an initial signal processing step and a machine learning model. Gold-standard reflux events were defined by a group of expert physicians. Performance metrics were computed to compare the machine learning system, current automated detection software (Reflux Reader v6.1), and an expert physician reader.
The study cohort included 45 patients (20/5/20 patients in the training/validation/test sets, respectively). The mean age was 51 (standard deviation 14.5) years, 47% of patients were male, and 78% of studies were performed off proton-pump inhibitor. Comparing the machine learning system vs current automated software vs expert physician reader, area under the curve was 0.87 (95% confidence interval [CI] 0.85-0.89) vs 0.40 (95% CI 0.37-0.42) vs 0.83 (95% CI 0.81-0.86), respectively; sensitivity was 68.7% vs 61.1% vs 79.4%, respectively; and specificity was 80.8% vs 18.6% vs 87.3%, respectively.
We trained and validated a novel machine learning system to successfully identify reflux events in 24-hour pH/impedance studies. Our model performance was superior to that of existing software and comparable to that of a human reader. Machine learning tools could significantly improve automated interpretation of pH/impedance studies.
食管 24 小时 pH/阻抗测试通常用于诊断胃食管反流病。对于专家医生来说，解读这些研究需要花费大量时间，并且存在很高的读者间差异。目前还没有商业上可用的机器学习工具来协助自动识别这些研究中的反流事件。
我们开发了一种用于识别 24 小时 pH/阻抗研究中反流事件的机器学习系统，该系统包括一个初始信号处理步骤和一个机器学习模型。由一组专家医生定义金标准反流事件。计算了性能指标，以比较机器学习系统、当前的自动检测软件（Reflux Reader v6.1）和专家医生读者的性能。
研究队列包括 45 名患者（分别有 20/5/20 名患者在训练/验证/测试集中）。患者的平均年龄为 51 岁（标准差 14.5），47%的患者为男性，78%的研究是在停用质子泵抑制剂后进行的。与当前的自动软件和专家医生读者相比，机器学习系统的曲线下面积分别为 0.87（95%置信区间 [CI] 0.85-0.89）、0.40（95% CI 0.37-0.42）和 0.83（95% CI 0.81-0.86）；敏感性分别为 68.7%、61.1%和 79.4%；特异性分别为 80.8%、18.6%和 87.3%。
我们成功地训练和验证了一种新的机器学习系统，用于识别 24 小时 pH/阻抗研究中的反流事件。我们的模型性能优于现有软件，与人类读者相当。机器学习工具可以显著改善 pH/阻抗研究的自动解读。
