AUTHOR=Lin David , Nazreen Tahmida , Rutowski Tomasz , Lu Yang , Harati Amir , Shriberg Elizabeth , Chlebek Piotr , Aratow Michael 

TITLE=Feasibility of a Machine Learning-Based Smartphone Application in Detecting Depression and Anxiety in a Generally Senior Population

JOURNAL=Frontiers in Psychology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/psychology/articles/10.3389/fpsyg.2022.811517

DOI=10.3389/fpsyg.2022.811517

ISSN=1664-1078

ABSTRACT=Background: Depression and anxiety create a large mental 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 App addresses this need by using semantic information from recorded speech to screen for depression and anxiety. 
Objective: The aim of this study is to determine the feasibility of collecting weekly voice samples for mental health screening. Additionally, we aim to validate the existing machine learning models for patients of various ages.
Methods: Study participants were current patients at Desert Oasis Healthcare, mean age 64 years (SD=9.8). 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 (Group Negative). Participants recorded 5-minute voice samples weekly for 6 weeks via the Ellipsis App. They also completed PHQ-8 and GAD-7 questionnaires to assess for depression and anxiety, respectively.
Results: Performance of the Ellipsis App was measured in comparison to the PHQ-8 and GAD-7. Results showed an AUC of 0.82 for the combined groups and 0.83 for Group Positive. Performance was high for senior participants as well as younger age ranges. Additionally, many participants spoke longer than the required 5 minutes.
Conclusion: The Ellipsis App accurately uses voice recordings to screen for depression and anxiety among various age groups, while also engaging the patient.