Analyzing Digital Evidence From a Telemental Health Platform to Assess Complex Psychological Responses to the COVID-19 Pandemic: Content Analysis of Text Messages.

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.

Just in time crisis response: suicide alert system for telemedicine psychotherapy settings.

AbstractObjective: To design a Natural Language Processing (NLP) algorithm capable of detecting suicide content from patients' written communication to their therapists, to support rapid response and clinical decision making in telehealth settings. Method: A training dataset of therapy transcripts for 1,864 patients was established by detecting patient content endorsing suicidality using a proxy-model anchored on therapists' suicide prevention interventions; human expert raters then assessed the level of suicide risk endorsed by patients identified by the proxy-model (i.e., no risk, risk factors, ideation, method, or plan). A bag-of-words classification model was then iteratively built using the annotations from the expert raters to detect suicide risk level in 85,216 labeled patients' sentences from the training dataset. Results: The final NLP model identified risk-related content from non-risk content with good accuracy (AUC = 82.78). Conclusions: Risk for suicide could be reliably identified by the NLP algorithm. The risk detection model could assist telehealth clinicians in providing crisis resources in a timely manner. This modeling approach could also be applied to other psychotherapy research tasks to assist in the understanding of how the psychotherapy process unfolds for each patient and therapist.

Diacylglycerol kinase α establishes T cell polarity by shaping diacylglycerol accumulation at the immunological synapse.

Polarization of the T cell microtubule-organizing center (MTOC) to the immunological synapse between the T cell and an antigen-presenting cell (APC) maintains the specificity of T cell effector responses by enabling directional secretion toward the APC. The reorientation of the MTOC is guided by a sharp gradient of the second messenger diacylglycerol (DAG), which is centered at the immunological synapse. We used a single-cell photoactivation approach to demonstrate that diacylglycerol kinase α (DGK-α), which catalyzes the conversion of DAG to phosphatidic acid, determined T cell polarity by limiting the diffusion of DAG. DGK-α-deficient T cells exhibited enlarged accumulations of DAG at the immunological synapse, as well as impaired reorientation of the MTOC. In contrast, T cells lacking the related isoform DGK-ζ did not display polarization defects. We also found that DGK-α localized preferentially to the periphery of the immunological synapse, suggesting that it constrained the area over which DAG accumulated. Phosphoinositide 3-kinase activity was required for the peripheral localization pattern of DGK-α, which suggests a link between DAG and phosphatidylinositol signaling during T cell activation. These results reveal a previously unappreciated function of DGK-α and provide insight into the mechanisms that determine lymphocyte polarity.

Annular PIP3 accumulation controls actin architecture and modulates cytotoxicity at the immunological synapse.

The immunological synapse formed by a T lymphocyte on the surface of a target cell contains a peripheral ring of filamentous actin (F-actin) that promotes adhesion and facilitates the directional secretion of cytokines and cytolytic factors. We show that growth and maintenance of this F-actin ring is dictated by the annular accumulation of phosphatidylinositol trisphosphate (PIP3) in the synaptic membrane. PIP3 functions in this context by recruiting the exchange factor Dock2 to the periphery of the synapse, where it drives actin polymerization through the Rho-family GTPase Rac. We also show that synaptic PIP3 is generated by class IA phosphoinositide 3-kinases that associate with T cell receptor microclusters and are activated by the GTPase Ras. Perturbations that inhibit or promote PIP3-dependent F-actin remodeling dramatically affect T cell cytotoxicity, demonstrating the functional importance of this pathway. These results reveal how T cells use lipid-based signaling to control synaptic architecture and modulate effector responses.