Hao Yupei, Zhang Jinyuan, Yang Lin, Zhou Chunhua, Yu Ze, Gao Fei, Hao Xin, Pang Xiaolu, Yu Jing
Department of Clinical Pharmacy, The First Hospital of Hebei Medical University, Shijiazhuang, China.
The Technology Innovation Center for Artificial Intelligence in Clinical Pharmacy of Hebei Province, The First Hospital of Hebei Medical University, Shijiazhuang, China.
Br J Clin Pharmacol. 2023 Sep;89(9):2714-2725. doi: 10.1111/bcp.15734. Epub 2023 May 7.
This study aimed to establish a prediction model of quetiapine concentration in patients with schizophrenia and depression, based on real-world data via machine learning techniques to assist clinical regimen decisions.
A total of 650 cases of quetiapine therapeutic drug monitoring (TDM) data from 483 patients at the First Hospital of Hebei Medical University from 1 November 2019 to 31 August 2022 were included in the study. Univariate analysis and sequential forward selection (SFS) were implemented to screen the important variables influencing quetiapine TDM. After 10-fold cross validation, the algorithm with the optimal model performance was selected for predicting quetiapine TDM among nine models. SHapley Additive exPlanation was applied for model interpretation.
Four variables (daily dose of quetiapine, type of mental illness, sex and CYP2D6 competitive substrates) were selected through univariate analysis (P < .05) and SFS to establish the models. The CatBoost algorithm with the best predictive ability (mean [SD] R = 0.63 ± 0.02, RMSE = 137.39 ± 10.56, MAE = 103.24 ± 7.23) was chosen for predicting quetiapine TDM among nine models. The mean (SD) accuracy of the predicted TDM within ±30% of the actual TDM was 49.46 ± 3.00%, and that of the recommended therapeutic range (200-750 ng mL ) was 73.54 ± 8.3%. Compared with the PBPK model in a previous study, the CatBoost model shows slightly higher accuracy within ±100% of the actual value.
This work is the first real-world study to predict the blood concentration of quetiapine in patients with schizophrenia and depression using artificial intelligent techniques, which is of significance and value for clinical medication guidance.
本研究旨在基于真实世界数据，通过机器学习技术建立精神分裂症和抑郁症患者喹硫平浓度的预测模型，以协助临床用药方案决策。
纳入2019年11月1日至2022年8月31日在河北医科大学第一医院483例患者的650例喹硫平治疗药物监测（TDM）数据。采用单因素分析和序贯向前选择（SFS）筛选影响喹硫平TDM的重要变量。经过10折交叉验证，在9个模型中选择模型性能最优的算法来预测喹硫平TDM。应用SHapley加性解释进行模型解释。
通过单因素分析（P < 0.05）和SFS选择了4个变量（喹硫平日剂量、精神疾病类型、性别和CYP2D6竞争性底物）来建立模型。在9个模型中选择预测能力最佳的CatBoost算法（均值[标准差]R = 0.63±0.02，均方根误差[RMSE]=137.39±10.56，平均绝对误差[MAE]=103.24±7.23）来预测喹硫平TDM。预测的TDM在实际TDM±30%范围内的平均（标准差）准确率为49.46±3.00%，在推荐治疗范围（200 - 750 ng/mL）内的准确率为73.54±8.3%。与先前研究中的生理药代动力学（PBPK）模型相比，CatBoost模型在实际值±100%范围内的准确率略高。
本研究是首次利用人工智能技术预测精神分裂症和抑郁症患者喹硫平血药浓度的真实世界研究，对临床用药指导具有重要意义和价值。
