Lin David, Nazreen Tahmida, Rutowski Tomasz, Lu Yang, Harati Amir, Shriberg Elizabeth, Chlebek Piotr, Aratow Michael
Ellipsis Health, San Francisco, CA, United States.
Front Psychol. 2022 Apr 8;13:811517. doi: 10.3389/fpsyg.2022.811517. eCollection 2022.
Depression and anxiety create a large health burden and increase the risk of premature mortality. Mental health screening is vital, but more sophisticated screening and monitoring methods are needed. The Ellipsis Health App addresses this need by using semantic information from recorded speech to screen for depression and anxiety.
The primary aim of this study is to determine the feasibility of collecting weekly voice samples for mental health screening. Additionally, we aim to demonstrate portability and improved performance of Ellipsis' machine learning models for patients of various ages.
Study participants were current patients at Desert Oasis Healthcare, mean age 63 years (SD = 10.3). Two non-randomized cohorts participated: one with a documented history of depression within 24 months prior to the study (Group Positive), and the other without depression (Group Negative). Participants recorded 5-min voice samples weekly for 6 weeks the Ellipsis Health App. They also completed PHQ-8 and GAD-7 questionnaires to assess for depression and anxiety, respectively.
Protocol completion rate was 61% for both groups. Use beyond protocol was 27% for Group Positive and 9% for Group Negative. The Ellipsis Health App showed an AUC of 0.82 for the combined groups when compared to the PHQ-8 and GAD-7 with a threshold score of 10. Performance was high for senior participants as well as younger age ranges. Additionally, many participants spoke longer than the required 5 min.
The Ellipsis Health App demonstrated feasibility in using voice recordings to screen for depression and anxiety among various age groups and the machine learning models using Transformer methodology maintain performance and improve over LSTM methodology when applied to the study population.
抑郁和焦虑造成了巨大的健康负担，并增加了过早死亡的风险。心理健康筛查至关重要，但需要更精密的筛查和监测方法。Ellipsis健康应用程序通过使用录音语音中的语义信息来筛查抑郁和焦虑，满足了这一需求。
本研究的主要目的是确定收集每周语音样本用于心理健康筛查的可行性。此外，我们旨在证明Ellipsis的机器学习模型对不同年龄段患者的便携性和改进的性能。
研究参与者为沙漠绿洲医疗中心的现有患者，平均年龄63岁（标准差=10.3）。两个非随机队列参与了研究：一个队列在研究前24个月内有抑郁病史记录（阳性组），另一个队列没有抑郁（阴性组）。参与者使用Ellipsis健康应用程序每周记录5分钟语音样本，持续6周。他们还分别完成了PHQ-8和GAD-7问卷，以评估抑郁和焦虑情况。
两组的方案完成率均为61%。阳性组超出方案的使用率为27%，阴性组为9%。与阈值分数为10的PHQ-8和GAD-7相比，Ellipsis健康应用程序在合并组中的曲线下面积为0.82。老年参与者以及较年轻年龄组的表现都很高。此外，许多参与者的发言时间超过了规定的5分钟。
Ellipsis健康应用程序证明了使用语音记录在不同年龄组中筛查抑郁和焦虑的可行性，并且当应用于研究人群时，使用Transformer方法的机器学习模型保持了性能并优于LSTM方法。
