Mobile Technology to Optimize Depression Treatment

摘要 量身定制的护理，使患者与对他们最有效的治疗相匹配，有可能加速 恢复和有意义地减少抑郁症的负担。定制护理的一个关键障碍是 缺乏客观、实时的方法来有效地预测和评估治疗反应。移动的 技术有望克服这一障碍。具体来说，智能手机和可穿戴传感器收集 被动的，持续的和客观的措施，结构中央抑郁症，如睡眠，身体 活动，心血管功能和社会参与。研究表明， 从这些领域的措施与抑郁症。然而，由于大多数先前的可穿戴研究都有 由于样本量有限，他们无法综合多个领域的可操作信息， 移动的技术数据，有效指导治疗。我们的长远目标是大幅增加 抑郁症治疗的有效性和我们精神卫生保健系统的能力。我们的目标是 应用程序是确定可用于有效匹配患者治疗的因素，并跟踪其 复苏通过提供心理健康精确治疗（PROMPT）研究，我们将完成 以下具体目标：目标1）确定预测哪种治疗最有可能减少抑郁症的因素 目标2）确定基于被动移动的技术的措施， 治疗反应的信号。为达致这些目标，我们会从门诊轮候名单中招募2，200名受试者 抑郁症治疗然后，我们将通过可穿戴传感器、智能手机和 重复的调查。对于这两个目标，我们将使用机器学习方法来开发全面的 预测模型我们的方法是创新的，因为它将技术和分析工具应用于一个大的， 在真实的世界条件下接受治疗的受试者的不同样本。此外，该项目旨在 直接导致组织层面的干预，使患者与治疗相匹配， 监测他们对治疗的反应。最后，这个项目意义重大，因为它有潜力大大 通过确定每个人可能从中获得最大益处的治疗来加速康复， 最终帮助解决抑郁症的高人口负担。

Abstract Tailoring care to match patients to the treatment most effective for them has the potential to accelerate recovery and meaningfully reduce the growing burden of depression. A key barrier to tailoring care is the absence of objective, real-time methods to effectively predict and assess treatment response. Mobile technology holds promise to overcome this barrier. Specifically, smartphones and wearable sensors collect passive, continuous and objective measures of constructs central to depression, such as sleep, physical activity, cardiovascular function, and social engagement. Studies have demonstrated associations of single measures from these domains with depression. However, because most prior wearable studies have had limited sample sizes, they have not been able to synthesize actionable information across multiple domains of mobile technology data and effectively guide treatment. Our long-term goal is to substantially increase the effectiveness of depression treatments and the capacity of our mental health care system. Our objective in this application is to identify factors that can be used to effectively match patients to treatments and track their recovery. Through the PROviding Mental health Precision Treatment (PROMPT) study, we will complete the following specific aims: Aim 1) Identify factors that predict which treatment is most likely to reduce depression symptoms for a specific patient; and Aim 2) Identify passive mobile technology-based measures that serve as signals of treatment response. To achieve these aims, we will recruit 2,200 subjects from waitlist for outpatient depression treatment. We will then track patients for six months through wearable sensors, smartphones, and repeated surveys. For both aims, we will use machine learning approaches to develop comprehensive prediction models. Our approach is innovative because it applies technology and analytic tools to a large and diverse sample of subjects receiving treatment under real world conditions. Further, the project is designed to lead directly to an organization-level intervention that matches patients to treatments and continuously monitors their response to treatment. Finally, this project is significant because it has the potential to greatly accelerate recovery by identifying the treatment from which each person is likely to derive the most benefit, ultimately helping to address the high population burden of depression.