Background

The novel COVID-19 disease has negatively impacted mortality, economic conditions, and mental health. These impacts are likely to continue after the COVID-19 pandemic ends. There are no methods for characterizing the mental health burden of the COVID-19 pandemic, and differentiating this burden from that of the prepandemic era. Accurate illness detection methods are critical for facilitating pandemic-related treatment and preventing the worsening of symptoms.

Objective

We aimed to identify major themes and symptom clusters in the SMS text messages that patients send to therapists. We assessed patients who were seeking treatment for pandemic-related distress on Talkspace, which is a popular telemental health platform.

Methods

We used a machine learning algorithm to identify patients' pandemic-related concerns, based on their SMS text messages in a large, digital mental health service platform (ie, Talkspace). This platform uses natural language processing methods to analyze unstructured therapy transcript data, in parallel with brief clinical assessment methods for analyzing depression and anxiety symptoms.

Results

Our results show a significant increase in the incidence of COVID-19-related intake anxiety symptoms (P<.001), but no significant differences in the incidence of intake depression symptoms (P=.79). During our transcript analyses, we identified terms that were related to 24 symptoms outside of those included in the diagnostic criteria for anxiety and depression.

Conclusions

Our findings for Talkspace suggest that people who seek treatment during the pandemic experience more severe intake anxiety than they did before the COVID-19 outbreak. It is important to monitor the symptoms that we identified in this study and the symptoms of anxiety and depression, to fully understand the effects of the COVID-19 pandemic on mental health.

Objective

Digital Mental Health Interventions (DMHI) can diminish inequities in mental health care provision. As DMHIs increase in popularity, however, older adults may be unintentionally excluded due to barriers such as lack of awareness, internet access, digital tools, technological socialization and education, physiological accessibility, and communication technology infrastructure. The aim of this study was to examine longitudinal treatment engagement patterns and 15-week clinical outcomes of depressed and anxious older adults compared to a matched cohort of younger adults seeking treatment from a large asynchronous telemedicine provider.

Methods

The 2,470 older adults (55+ years) and a matched cohort of younger adults (26-35 years) diagnosed with depression or anxiety were treated by licensed therapists via messaging 5 days a week. Patterns of treatment engagement on the platform were compared across groups by examining total number of days in treatment, days actively messaging on the platform, and average words and messages per week sent by patients over the entire period they remained in treatment. Symptoms were assessed every 3 weeks using the Patient Health Questionnaire (PHQ-9) and the Generalized Anxiety Disorder Scale (GAD-7), and changes were compared across age groups over 15 weeks.

Results

Older patients attended more days in treatment than younger patients, but there were no differences in number of days actively messaging on the platform, number of messages per week, or word count per week. The two age groups did not differ in their final anxiety or depressive symptoms when controlling for total number of weeks attended. Patients in the younger age group experienced a quicker rate of reduction than older adults in their anxiety, but not depressive symptoms.

Conclusions

Among individuals willing to initiate care through a DMHI, older adults had overall similar engagement as younger adults and they showed similar improvement in symptoms of depression and anxiety. Given the advantages of message-based care for aiding a mental health workforce in serving larger numbers of individuals in need and the expected growth of the aging population, these findings could help healthcare systems in evaluating a variety of treatment options and delivery media for meeting the healthcare needs of the future.