School of Languages and Cultures, University of Sydney, Sydney, Australia.
Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China.
Comput Intell Neurosci. 2022 Apr 15;2022:6722321. doi: 10.1155/2022/6722321. eCollection 2022.
Medication nonadherence represents a major burden on national health systems. According to the World Health Organization, increasing medication adherence may have a greater impact on public health than any improvement in specific medical treatments. More research is needed to better predict populations at risk of medication nonadherence.
To develop clinically informative, easy-to-interpret machine learning classifiers to predict people with psychiatric disorders at risk of medication nonadherence based on the syntactic and structural features of written posts on health forums.
All data were collected from posts between 2016 and 2021 on mental health forum, administered by Together 4 Change, a long-running not-for-profit organisation based in Oxford, UK. The original social media data were annotated using the Tool for the Automatic Analysis of Syntactic Sophistication and Complexity (TAASSC) system. Through applying multiple feature optimisation techniques, we developed a best-performing model using relevance vector machine (RVM) for the probabilistic prediction of medication nonadherence among online mental health forum discussants.
The best-performing RVM model reached a mean AUC of 0.762, accuracy of 0.763, sensitivity of 0.779, and specificity of 0.742 on the testing dataset. It outperformed competing classifiers with more complex feature sets with statistically significant improvement in sensitivity and specificity, after adjusting the alpha levels with Benjamini-Hochberg correction procedure. . We used the forest plot of multiple logistic regression to explore the association between written post features in the best-performing RVM model and the binary outcome of medication adherence among online post contributors with psychiatric disorders. We found that increased quantities of 3 syntactic complexity features were negatively associated with psychiatric medication adherence: "dobj_stdev" (standard deviation of dependents per direct object of nonpronouns) (OR, 1.486, 95% CI, 1.202-1.838, < 0.001), "cl_av_deps" (dependents per clause) (OR, 1.597, 95% CI, 1.202-2.122, , 0.001), and "VP_T" (verb phrases per T-unit) (OR, 2.23, 95% CI, 1.211-4.104, , 0.010). Finally, we illustrated the clinical use of the classifier with Bayes' monograph which gives the posterior odds and their 95% CI of positive (nonadherence) versus negative (adherence) cases as predicted by the best-performing classifier. The odds ratio of the posterior probability of positive cases was 3.9, which means that around 10 in every 13 psychiatric patients with a positive result as predicted by our model were following their medication regime. The odds ratio of the posterior probability of true negative cases was 0.4, meaning that around 10 in every 14 psychiatric patients with a negative test result after screening by our classifier were not adhering to their medications.
Psychiatric medication nonadherence is a large and increasing burden on national health systems. Using Bayesian machine learning techniques and publicly accessible online health forum data, our study illustrates the viability of developing cost-effective, informative decision aids to support the monitoring and prediction of patients at risk of medication nonadherence.
药物依从性是国家卫生系统的主要负担。根据世界卫生组织的说法，提高药物依从性可能对公众健康的影响比任何特定医疗治疗的改善都要大。需要更多的研究来更好地预测有药物依从性风险的人群。
基于心理健康论坛上发布的帖子的句法和结构特征，开发具有临床意义且易于解释的机器学习分类器，以预测有精神障碍风险的人群药物依从性。
所有数据均来自于英国牛津的非营利组织 Together 4 Change 管理的心理健康论坛 2016 年至 2021 年期间的帖子。原始社交媒体数据使用自动分析句法复杂性和复杂性的工具 (TAASSC) 系统进行注释。通过应用多种特征优化技术，我们使用了相关向量机 (RVM) 为在线心理健康论坛讨论者的药物依从性概率预测开发了表现最佳的模型。
表现最佳的 RVM 模型在测试数据集上的平均 AUC 为 0.762，准确率为 0.763，灵敏度为 0.779，特异性为 0.742。在调整了 Benjamini-Hochberg 校正程序的 alpha 水平后，它优于具有更复杂特征集的竞争分类器，在灵敏度和特异性方面具有统计学意义的改善。我们使用多项逻辑回归的森林图来探索表现最佳的 RVM 模型中书面帖子特征与在线帖子贡献者的精神障碍药物依从性的二进制结果之间的关联。我们发现，3 种句法复杂度特征的增加数量与精神科药物依从性呈负相关：“dobj_stdev”（非代词直接宾语的依存物的标准差）（OR，1.486，95%CI，1.202-1.838， < 0.001），“cl_av_deps”（每个子句的依存物）（OR，1.597，95%CI，1.202-2.122， < 0.001）和“VP_T”（T 单元中的动词短语）（OR，2.23，95%CI，1.211-4.104， < 0.010）。最后，我们通过贝叶斯专论说明了分类器的临床应用，该专论给出了由最佳表现分类器预测的阳性（不依从）与阴性（依从）病例的后验几率及其 95%CI。阳性病例的后验概率的优势比为 3.9，这意味着在我们的模型预测为阳性的每 13 名精神病患者中，大约有 10 名正在遵医嘱服药。阴性病例的后验概率的优势比为 0.4，这意味着在我们的分类器筛选后为阴性的每 14 名精神病患者中，大约有 10 名没有遵医嘱服药。
精神科药物依从性是国家卫生系统的一个巨大且日益增加的负担。使用贝叶斯机器学习技术和公开的在线健康论坛数据，我们的研究说明了开发具有成本效益和信息量的决策辅助工具来支持监测和预测有药物依从性风险的患者的可行性。
