Department of Psychiatry, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung, Taiwan; Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.
School of Pharmacy, Institute of Clinical Pharmacy and Pharmaceutical Sciences, College of Medicine, National Cheng Kung University, Tainan, Taiwan.
J Affect Disord. 2024 Feb 15;347:85-91. doi: 10.1016/j.jad.2023.11.047. Epub 2023 Nov 20.
Our study employs machine learning to predict serum valproic acid (VPA) concentrations, aiming to contribute to the development of non-invasive assays for therapeutic drug monitoring.
Medical records from 2002 to 2019 were obtained from the Taiwan Chang Gung Research Database. Using various machine learning algorithms, we developed predictive models to classify serum VPA concentrations into two categories (1-50 μg/ml or 51-100 μg/ml) and predicted the exact concentration value. The models were trained on 5142 samples and tested on 644 independent samples. Accuracy was the main metric used to evaluate model performance, with a tolerance of 20 μg/ml for continuous variables. Furthermore, we identified important features and developed simplified models with fewer features.
The models achieved an average accuracy of 0.80-0.86 for binary outcomes and 0.72-0.88 for continuous outcome. Ten top features associated with higher serum VPA levels included higher VPA last and daily doses, bipolar disorder or schizophrenia spectrum disorder diagnoses, elevated levels of serum albumin, calcium, and creatinine, low platelet count, low percentage of segmented white blood cells, and low red cell distribution width-coefficient of variation. The simplified models had an average accuracy of 0.82-0.86 for binary outcome and 0.70-0.86 for continuous outcome.
The study's predictive model lacked external test data from outside the hospital for validation.
Machine learning models have the potential to integrate real-world data and predict VPA concentrations, providing a promising tool for reducing the need for frequent monitoring of serum levels in clinical practice.
本研究运用机器学习来预测血清丙戊酸（VPA）浓度，旨在为治疗药物监测的非侵入性检测方法的发展做出贡献。
从台湾长庚研究数据库中获取了 2002 年至 2019 年的病历。我们使用各种机器学习算法开发了预测模型，将血清 VPA 浓度分为两类（1-50μg/ml 或 51-100μg/ml），并预测了确切的浓度值。模型在 5142 个样本上进行训练，在 644 个独立样本上进行测试。准确性是评估模型性能的主要指标，对于连续变量的容差为 20μg/ml。此外，我们确定了重要特征并开发了具有较少特征的简化模型。
模型在二分类结果中的平均准确率为 0.80-0.86，在连续结果中的平均准确率为 0.72-0.88。与更高的血清 VPA 水平相关的十个最重要特征包括更高的 VPA 末次和日剂量、双相障碍或精神分裂症谱系障碍诊断、血清白蛋白、钙和肌酐水平升高、血小板计数降低、分叶核白细胞百分比降低以及红细胞分布宽度变异系数降低。简化模型在二分类结果中的平均准确率为 0.82-0.86，在连续结果中的平均准确率为 0.70-0.86。
研究的预测模型缺乏来自医院外的外部测试数据进行验证。
机器学习模型有可能整合真实世界的数据并预测 VPA 浓度，为减少临床实践中对血清水平进行频繁监测的需求提供了有前途的工具。
