Yeneakal Kelemua Aschale, Teferi Gizaw Hailiye, Mihret Temesgen T, Mengistu Abraham Keffale, Tizie Sefefe Birhanu, Tadele Maru Meseret
Department of Health Informatics, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia.
Department of Water Resources and Irrigation Engineering, Asossa University, Asossa, Ethiopia.
BMC Med Inform Decis Mak. 2025 Jul 10;25(1):259. doi: 10.1186/s12911-025-03106-4.
Adherence with Anti-Retroviral Therapy (ART) reduces viral load, as well as HIV-related morbidity and mortality. Despite the expanded availability of ART, non-adherence remains a series problem, leads increased viral load, a decline CD4 cell count, and the development of drug resistance. HIV care is currently showing promise with the use of machine learning algorithms for early prediction of future non-adherence. However, as to researcher's Knowledge, there was limited research supporting this evidence in the country. Therefore, the primary aim of this study was to predict ART adherence status using machine learning models and to identify the most important predictors of Adherence at Debre Markos comprehensive specialized hospital.
Secondary data was collected from ART database of Debre Markos comprehensive specialized hospital, spanning from 2005 to 2024. The dataset was split into training (80%) and testing (20%) sets. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied to the training data. Seven machine learning algorithms: support vector machine, random forest, decision tree, logistic regression, gradient boosting, K-nearest neighbors, and artificial neural network were trained. The model performance was evaluated using ROC-AUC, F1 score, accuracy, precision, and recall. To identify important predictor we employed feature importance technique.
Out of 4640 patients, who were on antiretroviral therapy, 63.56% (n = 2949) were females, with mean age of 41.8 years (SD ± 11.50). The majority age group was between 40 and 59 years (n = 2152) 46.38% and 98.1% of patients had good adherence while 1.9% had poor adherence. Among the machine learning models tested, the gradient boosting algorithm performed better than all other algorithms with (Accuracy = 0.78, Sensitivity = 0.76, F1score = 0.78, AUC = 0.76). Age, regimen, WHO clinical stage, nutritional status, address status, sex, weight, recent CD4 cell count, viral load and ART dose per day were identified as the most important predictors for adherence status.
The study developed a gradient boosting model for predicting adherence status. Age, regimen, WHO clinical stage, nutritional status, address status, sex, weight, recent CD4 cell count, viral load and ART dose per day were the most important predictors for adherence status.
Not applicable.
坚持抗逆转录病毒疗法（ART）可降低病毒载量以及与艾滋病相关的发病率和死亡率。尽管抗逆转录病毒疗法的可及性有所提高，但不坚持治疗仍是一个严重问题，会导致病毒载量增加、CD4细胞计数下降以及耐药性的产生。目前，艾滋病护理在使用机器学习算法早期预测未来的不坚持治疗情况方面展现出了前景。然而，据研究人员所知，该国支持这一证据的研究有限。因此，本研究的主要目的是使用机器学习模型预测抗逆转录病毒疗法的坚持状态，并确定德布雷马科斯综合专科医院坚持治疗的最重要预测因素。
从德布雷马科斯综合专科医院的抗逆转录病毒疗法数据库中收集了2005年至2024年的二手数据。数据集被分为训练集（80%）和测试集（20%）。为了解决类别不平衡问题，对训练数据应用了合成少数过采样技术（SMOTE）。对七种机器学习算法进行了训练：支持向量机、随机森林、决策树、逻辑回归、梯度提升、K近邻和人工神经网络。使用ROC-AUC、F1分数、准确率、精确率和召回率评估模型性能。为了确定重要预测因素，我们采用了特征重要性技术。
在4640名接受抗逆转录病毒治疗的患者中，63.56%（n = 2949）为女性，平均年龄为41.8岁（标准差±11.50）。主要年龄组在40至59岁之间（n = （此处原文疑似有误，2152后括号内容应为重复数据）），46.38%的患者坚持情况良好，98.1%的患者坚持情况良好，而1.9%的患者坚持情况较差。在测试的机器学习模型中，梯度提升算法的表现优于所有其他算法（准确率 = 0.78，灵敏度 = 0.76，F1分数 = 0.78，AUC = 0.76）。年龄、治疗方案、世界卫生组织临床分期、营养状况、住址状况、性别、体重、最近的CD4细胞计数、病毒载量和每日抗逆转录病毒疗法剂量被确定为坚持状态的最重要预测因素。
该研究开发了一种用于预测坚持状态的梯度提升模型。年龄、治疗方案、世界卫生组织临床分期、营养状况、住址状况、性别、体重、最近的CD4细胞计数、病毒载量和每日抗逆转录病毒疗法剂量是坚持状态的最重要预测因素。
不适用。
