Left on Read: Reply Latency for Anxiety & Depression Screening

Mental health is a critical societal issue and early screening is vital to enabling timely treatment. The rise of text-based communications provides new modalities that can be used to passively screen for mental illnesses. In this paper we present an approach to screen for anxiety and depression through reply latency of text messages. We demonstrate that by constructing machine learning models with reply latency features. Our models screen for anxiety with a balanced accuracy of 0.62 and F1 of 0.73, a notable improvement over prior approaches. With the same participants, our models likewise screen for depression with a balanced accuracy of 0.70 and F1 of 0.80. We additionally compare these results to those of models trained on data collected prior to the COVID-19 pandemic. Finally, we demonstrate generalizability for screening by combining datasets which results in comparable accuracy. Latency features could thus be useful in multimodal mobile mental illness screening. © 2022 ACM.

Meeting the Behavioral Health Needs of Health Care Workers During COVID-19 by Leveraging Chatbot Technology: Development and Usability Study.

BACKGROUND: During the COVID-19 pandemic, health care systems were faced with the urgent need to implement strategies to address the behavioral health needs of health care workers. A primary concern of any large health care system is developing an easy-to-access, streamlined system of triage and support despite limited behavioral health resources. OBJECTIVE: This study provides a detailed description of the design and implementation of a chatbot program designed to triage and facilitate access to behavioral health assessment and treatment for the workforce of a large academic medical center. The University of California, San Francisco (UCSF) Faculty, Staff, and Trainee Coping and Resiliency Program (UCSF Cope) aimed to provide timely access to a live telehealth navigator for triage and live telehealth assessment and treatment, curated web-based self-management tools, and nontreatment support groups for those experiencing stress related to their unique roles. METHODS: In a public-private partnership, the UCSF Cope team built a chatbot to triage employees based on behavioral health needs. The chatbot is an algorithm-based, automated, and interactive artificial intelligence conversational tool that uses natural language understanding to engage users by presenting a series of questions with simple multiple-choice answers. The goal of each chatbot session was to guide users to services that were appropriate for their needs. Designers developed a chatbot data dashboard to identify and follow trends directly through the chatbot. Regarding other program elements, website user data were collected monthly and participant satisfaction was gathered for each nontreatment support group. RESULTS: The UCSF Cope chatbot was rapidly developed and launched on April 20, 2020. As of May 31, 2022, a total of 10.88% (3785/34,790) of employees accessed the technology. Among those reporting any form of psychological distress, 39.7% (708/1783) of employees requested in-person services, including those who had an existing provider. UCSF employees responded positively to all program elements. As of May 31, 2022, the UCSF Cope website had 615,334 unique users, with 66,585 unique views of webinars and 601,471 unique views of video shorts. All units across UCSF were reached by UCSF Cope staff for special interventions, with >40 units requesting these services. Town halls were particularly well received, with >80% of attendees reporting the experience as helpful. CONCLUSIONS: UCSF Cope used chatbot technology to incorporate individualized behavioral health triage, assessment, treatment, and general emotional support for an entire employee base (N=34,790). This level of triage for a population of this size would not have been possible without the use of chatbot technology. The UCSF Cope model has the potential to be scaled, adapted, and implemented across both academically and nonacademically affiliated medical settings.

Piloting a clinical mental health process in the intermediate school setting

The COVID-19 pandemic has highlighted the need for increased adolescent mental health support in the school setting. This evidence-based quality improvement project aimed to determine if implementing a clinical mental health pathway increases the number of mental health screenings completed and increases school nurse practitioners' comfort and confidence in completing mental health screenings. A Mental Health Toolkit was developed to include program-specific management recommendations, a school collaboration flowsheet, and educational and community resources for the nurse practitioner, students, and school community. The 15-week pilot intervention was evaluated using quantitative pre-and post-survey and qualitative interviews. The intervention increased the number of depression screenings performed compared to the previous school year. In addition, the post-intervention interview provided clarity to the persistent system-level and clinic-level barriers and provided personal insights into performing mental health screenings within the school setting. This pilot project allowed the nurse practitioner to model the normalization of mental health discussions. It also provided an opportunity for increased collaboration between the nurse practitioner and school partners, which can substantially impact adolescent mental health outcomes. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Piloting a clinical mental health process in the intermediate school setting

The COVID-19 pandemic has highlighted the need for increased adolescent mental health support in the school setting. This evidence-based quality improvement project aimed to determine if implementing a clinical mental health pathway increases the number of mental health screenings completed and increases school nurse practitioners' comfort and confidence in completing mental health screenings. A Mental Health Toolkit was developed to include program-specific management recommendations, a school collaboration flowsheet, and educational and community resources for the nurse practitioner, students, and school community. The 15-week pilot intervention was evaluated using quantitative pre-and post-survey and qualitative interviews. The intervention increased the number of depression screenings performed compared to the previous school year. In addition, the post-intervention interview provided clarity to the persistent system-level and clinic-level barriers and provided personal insights into performing mental health screenings within the school setting. This pilot project allowed the nurse practitioner to model the normalization of mental health discussions. It also provided an opportunity for increased collaboration between the nurse practitioner and school partners, which can substantially impact adolescent mental health outcomes. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Factorial Validity and Invariance of an Adolescent Depression Symptom Screening Tool.

CONTEXT: Depression is among the most common mental health disorders in youth, results in significant impairment, and is associated with a higher risk of suicide. Screening is essential, but assessment tools may not account for the complex interrelatedness of various demographic factors, such as sex, socioeconomic status, and race. OBJECTIVES: To determine the (1) the factor structure of the Patient Health Questionnaire-Adolescent (PHQ-A) for measuring depression in a group of adolescent athletes and (2) measurement invariance between Black and White patients on the PHQ-A. DESIGN: Retrospective cohort design. SETTING: Data were obtained from a secure database collected at a free, comprehensive, mass preparticipation physical examination event hosted by a large health care system. PATIENTS OR OTHER PARTICIPANTS: Participants were 683 high school athletes (Black = 416, White = 267). The independent variables were somatic and affective factors contributing to the construct of depression measured by the PHQ-A and participant race (Black or White). MAIN OUTCOME MEASURE(S): (1) Factors upon which the construct of depression is measured and (2) measurement invariance between Black and White participants. RESULTS: A 2-factor model, involving affective and somatic components, was specified and exhibited adequate fit to the data (comparative fit index >0.90). All items exhibited moderate to high squared multiple correlation values (R2 = 0.10-0.65), suggesting that these items resonated relatively well with participants. The 2-factor model demonstrated noninvariance between Black and White participants (root mean square error of approximation = 0.06-0.08). CONCLUSIONS: Overall, the structure of the PHQ-A was supported by a 2-factor model in adolescent athletes, measuring both affective and somatic symptoms of depression. However, a 2-factor PHQ-A structure was not fully invariant for the adolescents sampled across participant groups, indicating that the model functioned differently between the Black and White participants sampled.

Coronavirus Pandemic Anxiety Scale (CPAS-11): development and initial validation.

The mental health impact of the COVID-19 pandemic will increase as the outbreak continues and persist even after the pandemic passes. We developed an 11-item Coronavirus Pandemic Anxiety Scale (CPAS-11) to measure symptoms of anxiety related to the COVID-19 pandemic to help identify individuals who might need mental health services. In developing the scale items, we considered previous research and theory on anxiety symptoms and symptoms reported by clinically referred cases in the Philippines. The scale was validated in a Filipino sample (N = 925). Exploratory factor analysis indicated two factors corresponding to somatic and non-somatic symptoms; confirmatory factor analysis showed good fit for the two-factor model. CPAS-11 showed good internal consistency, convergent and divergent validity, and screening accuracy. A cutoff score of 15 showed adequate sensitivity and specificity to distinguish GAD-7 screened participants. The results support the viability of CPAS-11 as a screening tool to identify individuals experiencing COVID-19-related anxiety.

A Proposed Brain-, Spine-, and Mental- Health Screening Methodology (NEUROSCREEN) for Healthcare Systems: Position of the Society for Brain Mapping and Therapeutics.

The COVID-19 pandemic has accelerated neurological, mental health disorders, and neurocognitive issues. However, there is a lack of inexpensive and efficient brain evaluation and screening systems. As a result, a considerable fraction of patients with neurocognitive or psychobehavioral predicaments either do not get timely diagnosed or fail to receive personalized treatment plans. This is especially true in the elderly populations, wherein only 16% of seniors say they receive regular cognitive evaluations. Therefore, there is a great need for development of an optimized clinical brain screening workflow methodology like what is already in existence for prostate and breast exams. Such a methodology should be designed to facilitate objective early detection and cost-effective treatment of such disorders. In this paper we have reviewed the existing clinical protocols, recent technological advances and suggested reliable clinical workflows for brain screening. Such protocols range from questionnaires and smartphone apps to multi-modality brain mapping and advanced imaging where applicable. To that end, the Society for Brain Mapping and Therapeutics (SBMT) proposes the Brain, Spine and Mental Health Screening (NEUROSCREEN) as a multi-faceted approach. Beside other assessment tools, NEUROSCREEN employs smartphone guided cognitive assessments and quantitative electroencephalography (qEEG) as well as potential genetic testing for cognitive decline risk as inexpensive and effective screening tools to facilitate objective diagnosis, monitor disease progression, and guide personalized treatment interventions. Operationalizing NEUROSCREEN is expected to result in reduced healthcare costs and improving quality of life at national and later, global scales.

Anticipating PTSD in severe COVID survivors: the case for screen-and-treat.

Based on research from previous pandemics, studies of critical care survivors, and emerging COVID-19 data, we estimate that up to 30% of survivors of severe COVID will develop PTSD. PTSD is frequently undetected across primary and secondary care settings and the psychological needs of survivors may be overshadowed by a focus on physical recovery. Delayed PTSD diagnosis is associated with poor outcomes. There is a clear case for survivors of severe COVID to be systematically screened for PTSD, and those that develop PTSD should receive timely access to evidence-based treatment for PTSD and other mental health problems by multidisciplinary teams.

Basados en la investigación de pandemias previas, los estudios de los sobrevivientes a cuidados críticos, y los datos emergentes de COVID-19, estimamos que hasta un 30% de los sobrevivientes del COVID grave desarrollarán TEPT. El TEPT es frecuentemente subdetectado en los servicios de salud primarios y secundarios y las necesidades psicológicas de los sobrevivientes puede verse eclipsadas por un enfoque en la recuperación física. El diagnóstico tardío de TEPT se asocia con pobres resultados. Existe un caso claro para que los sobrevivientes del COVID grave sean evaluados sistemáticamente para detectar el TEPT, y aquellos que desarrollan un TEPT deben tener acceso oportuno a tratamientos basados en la evidencia para el TEPT y para otros problemas de salud mental por equipos multidisciplinarios.

"Could we have predicted this?" The association of a future mental health need in young people with a non-specific complaint and frequent emergency department visits.

OBJECTIVE: Mental health emergencies among young people are increasing. There is growing pressure for emergency departments to screen patients for mental health needs even when it is not their chief complaint. We hypothesized that young people with an initial non-specific condition and emergency department (ED) revisits have increased mental health needs. METHODS: Retrospective, observational study of the California Office of Statewide Health Planning and Development Emergency Department Discharge Dataset (2010-2014) of young people (11-24 years) with an index visit for International Classification of Diseases, Ninth Revision diagnostic codes of "Symptoms, signs, and ill-defined conditions" (Non-Specific); "Diseases of the respiratory system" (Respiratory) and "Unintentional injury" (Trauma) who were discharged from a California ED. Patients were excluded if they had a prior mental health visit, chronic disease, or were pregnant. ED visit frequency was counted over 12 months. Regression models were created to analyze characteristics associated with a mental health visit. RESULTS: Patients in the Non-Specific category compared to the Respiratory category had 1.2 times the odds of a future mental health visit (OR 1.20; 95% CI 1.17-1.24). Patients with ≥1 ED revisit, regardless of diagnostic category, had 1.3 times the odds of a future mental health visit. Patients with both a Non-Specific index visit and 1, 2, and 3 or more revisits with non-specific diagnoses had increasing odds of a mental health visit (OR 1.38; 95% CI 1.29-1.47; OR 1.70; 95% CI 1.46-1.98; OR 2.20; 95% CI 1.70-2.87, respectively.). CONCLUSIONS: Young people who go to the ED for non-specific conditions and revisits may benefit from targeted ED mental health screening.

An Assessment of Distress Levels of Patients Undergoing Lung Cancer Treatment and Surveillance During the COVID-19 Pandemic.

The purpose of this quality improvement initiative was to identify anxious/distressed lung cancer patients and address their mental health needs directly related to the COVID-19. A total of 441 patients were screened utilizing a national distress thermometer. 47% were counseled by the NP, 32% sent for referral to the social worker. Patients reported reasons for distress as fear of delaying testing, contracting the virus and changes in their lifestyle. We found that screening all patients during the pandemic, yielded a higher than normal percentage of patients who were in need of some level of mental health services.