Tlachac M L, Heinz Michael
IEEE J Biomed Health Inform. 2024 Dec;28(12):7683-7692. doi: 10.1109/JBHI.2024.3436654. Epub 2024 Dec 5.
Major Depressive Disorder (MDD) and Generalized Anxiety Disorder (GAD) are highly prevalent and burdensome. To increase mental health screening rates, the digital health research community has been exploring the ability to augment self reporting instruments with digital logs. Crowdsourced workers are being increasingly recruited for behavioral health research studies as demographically representative samples are desired for later translational applications. Overshadowed by predictive modeling, descriptive modeling has the ability to expand knowledge and understanding of the clinical generalizability of models trained on data from crowdsourced participants. In this study, we identify mobile communication profiles of a crowdsourced sample. To achieve this, we cluster features derived from time series of call and text logs. The psychiatric, behavioral, and demographic characteristics were notably different across the four identified mobile communication profiles. For example, the profile that had the lowest average depression and anxiety screening scores only shared incoming text logs. This cluster had statistically significantly different depression and anxiety screening scores in comparison to the cluster that shared the most outgoing text logs. These profiles expose important insights regarding the generalizability of crowdsourced samples to more general clinical populations and increase understanding regarding the limitations of crowdsourced samples for translational mental health research.
重度抑郁症（MDD）和广泛性焦虑症（GAD）极为常见且负担沉重。为提高心理健康筛查率，数字健康研究界一直在探索利用数字日志增强自我报告工具的能力。由于行为健康研究需要具有人口统计学代表性的样本以便后续进行转化应用，众包工作者越来越多地被招募参与此类研究。在预测建模的阴影下，描述性建模有能力扩展对基于众包参与者数据训练的模型临床可推广性的认识和理解。在本研究中，我们识别了一个众包样本的移动通信概况。为实现这一目标，我们对从通话和文本日志时间序列中提取的特征进行聚类。在四个识别出的移动通信概况中，精神、行为和人口统计学特征显著不同。例如，平均抑郁和焦虑筛查得分最低的概况仅共享接收的文本日志。与共享最多发出文本日志的聚类相比，该聚类的抑郁和焦虑筛查得分在统计学上有显著差异。这些概况揭示了关于众包样本对更广泛临床人群的可推广性的重要见解，并增进了对众包样本在转化心理健康研究中的局限性的理解。
