Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
BackgroundThe rise of depression, anxiety, and suicide rates has led to increased demand for telemedicine-based mental health screening and remote patient monitoring (RPM) solutions to alleviate the burden on, and enhance the efficiency of, mental health practitioners. Multimodal dialog systems (MDS) that conduct on-demand, structured interviews offer a scalable and cost-effective solution to address this need.ObjectiveThis study evaluates the feasibility of a cloud based MDS agent, Tina, for mental state characterization in participants with depression, anxiety, and suicide risk.MethodSixty-eight participants were recruited through an online health registry and completed 73 sessions, with 15 (20.6%), 21 (28.8%), and 26 (35.6%) sessions screening positive for depression, anxiety, and suicide risk, respectively using conventional screening instruments. Participants then interacted with Tina as they completed a structured interview designed to elicit calibrated, open-ended responses regarding the participants' feelings and emotional state. Simultaneously, the platform streamed their speech and video recordings in real-time to a HIPAA-compliant cloud server, to compute speech, language, and facial movement-based biomarkers. After their sessions, participants completed user experience surveys. Machine learning models were developed using extracted features and evaluated with the area under the receiver operating characteristic curve (AUC).ResultsFor both depression and suicide risk, affected individuals tended to have a higher percent pause time, while those positive for anxiety showed reduced lip movement relative to healthy controls. In terms of single-modality classification models, speech features performed best for depression (AUC = 0.64; 95% CI = 0.51–0.78), facial features for anxiety (AUC = 0.57; 95% CI = 0.43–0.71), and text features for suicide risk (AUC = 0.65; 95% CI = 0.52–0.78). Best overall performance was achieved by decision fusion of all models in identifying suicide risk (AUC = 0.76; 95% CI = 0.65–0.87). Participants reported the experience comfortable and shared their feelings.ConclusionMDS is a feasible, useful, effective, and interpretable solution for RPM in real-world clinical depression, anxiety, and suicidal populations. Facial information is more informative for anxiety classification, while speech and language are more discriminative of depression and suicidality markers. In general, combining speech, language, and facial information improved model performance on all classification tasks.
Facebook
TwitterOpen Government Licence 3.0http://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/
License information was derived automatically
This dataset presents the prevalence of depression and anxiety among adults, serving as a key indicator of mental health within the population. It is intended to support monitoring and evaluation efforts aimed at improving mental health outcomes and reducing the burden of common mental disorders. The data is expressed as a percentage, reflecting the proportion of adults experiencing depression and/or anxiety.
Rationale
Mental health is a critical component of overall well-being. Monitoring the prevalence of depression and anxiety in adults helps inform public health strategies, allocate resources effectively, and evaluate the impact of mental health interventions. Reducing the prevalence of these conditions is a priority for improving quality of life and reducing associated social and economic costs.
Numerator
The numerator for this indicator is currently unspecified. It would typically represent the number of adults identified as experiencing depression and/or anxiety within a defined population and time period.
Denominator
The denominator is also unspecified in the current metadata. It would generally be the total number of adults in the population under study during the same time period.
Caveats
At present, the dataset lacks detailed definitions for both the numerator and denominator, as well as the data sources. This limits the interpretability and comparability of the indicator. Users should exercise caution when drawing conclusions or making comparisons based on this data.
External References
No external references have been provided. For further context or methodological guidance, users may refer to national health surveys or reports from organizations such as the World Health Organization.
Click here to explore more from the Birmingham and Solihull Integrated Care Partnerships Outcome Framework.
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Analysis of ‘Anxiety and Depression Psychological Therapies ’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/mpwolke/cusersmarildownloadsanxietycsv on 30 September 2021.
--- Dataset description provided by original source is as follows ---
National Clinical Audit of Anxiety and Depression Psychological Therapies Spotlight Audit. Data collected between October 2018 and January 2019 and aggregated by mental health services delivering psychological therapies in secondary care.
Freedom of Information (FOI) requests : Dr Alan Quirk Alan.Quirk@rcpsych.ac.uk https://www.rcpsych.ac.uk/improving-care/ccqi/national-clinical-audits/national-clinical-audit-of-anxiety-and-depression
Photo by Sarah Kilian on Unsplash (Covid-19 times)
The Implications of COVID-19 for Mental Health . The COVID-19 pandemic and resulting economic downturn have negatively affected many people’s mental health and created new barriers for people already suffering from mental illness and substance use disorders. Therefore this Pandemic affects not only the infected persons but all the World, with repercussions that can persists beyond 2020.
--- Original source retains full ownership of the source dataset ---
Facebook
TwitterOpen Government Licence 3.0http://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/
License information was derived automatically
Number and proportion of people with neurotic disorders including phobias, depressive episodes, generalised anxiety disorder, obsessive compulsive disorder and panic disorder Source: Department of Health (DoH): National Psychiatric Morbidity Survey Publisher: Mental Health Observatory: North East Public Health Observatory Geographies: Local Authority District (LAD), County/Unitary Authority, Government Office Region (GOR), National, Primary Care Trust (PCT) Geographic coverage: England Time coverage: 2006 Type of data: Modelled data
Facebook
TwitterCC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
This is a development key figure, see questions and answers on kolada.se for more information. Number of people aged 65 and older living in special public housing who reported having severe anxiety, anxiety or anxiety divided by all persons aged 65 years and older, residents in special housing under public authority who responded to the survey of older people’s perceptions. “Do not know/No opinion” is excluded from the denominator. Data from 2012.
Facebook
TwitterMany individuals who experience persistent problems with anxiety or depression do not seek treatment. The aim of this randomized controlled trial was to test the efficacy of a brief online social-cognitive intervention designed to increase help-seeking behavior and decrease psychological distress. The trial involving randomly assigning a distressed sample of 276 participants (151 females, 123 males, 2 others) aged 18-77 years (M = 36.64, SD = 13.08) either to a modeling and vicarious reinforcement condition focused on help-seeking or to a waitlist control. The study measured help-seeking self-efficacy, help-seeking outcome expectancy, help-seeking behavior, and distress at pre- and post-intervention. At post-intervention the treatment group, compared to the control group, showed significant effects on overall distress levels but not on the other variables. The positive effect on distress was maintained in the intervention group at two-month follow-up. The results show that an online intervention based on help-seeking modelling and reinforcement can decrease psychological distress but they do not show the mechanism of the effect.
Facebook
TwitterOpen Government Licence 3.0http://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/
License information was derived automatically
The Improving Access to Psychological Therapies (IAPT) programme is designed to support the NHS in delivering by 2014/2015: Evidence-based psychological therapies, as approved by the National Institute for Health and Clinical Excellence (NICE), for people with depression and anxiety disorders; Access to services and treatments by people experiencing depression and anxiety disorders from all communities within the local population; Increased health and well-being, with at least 50 per cent of those completing treatment moving to recovery and most experiencing a meaningful improvement in their condition; Patient choice and high levels of satisfaction from people using services and their carers; Timely access, with people waiting no longer than locally agreed waiting times standards; Improved employment, benefit, and social inclusion status including help for people to retain employment, return to work, improve their vocational situation, and participate in the activities of daily living. The vision for the IAPT programme over the next spending review cycle was set out in the Department of Health publication “Talking Therapies: A four-year plan of action” and the IAPT KPIs will support measurement of the following objectives: 3.2 million people will access IAPT, receiving brief advice or a course of therapy for depression or anxiety disorders; Access to services will increase and by 2014/15 a minimum of 15 per cent per annum (3.75 per cent per quarter) of those in need will be able to access psychological therapy services; 2.6 million patients will complete a course of treatment; Up to 1.3 million (50 per cent of those treated) will move to measurable recovery. From quarter one of 2011/12 IAPT KPIs will also be used to support the NHS Operating Framework. Two IAPT indicators are included in the NHS Operating Framework to measure quarter-on-quarter improvement in: 1.Number of people entering treatment over the level of need, i.e. the number of people with depression and anxiety disorders in the population; 2.The number of people entering treatment over the number of people with depression and anxiety disorders referred for psychological therapies. The level of need in the general adult population is known as the rate of prevalence, defined by the Psychiatric Morbidity Survey. For common mental health conditions treated in IAPT services, it is expected that a minimum of 15 per cent of those in need would willingly enter treatment if available.
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Social Anxiety Disorder (SAD) and Alcohol Use Disorder (AUD) are highly prevalent and frequently co-occur. The results of population studies suggest that SAD tends to precede AUD, and the results of laboratory studies suggest that alcohol use facilitates social behaviors in socially anxious individuals. Therefore, we posited that, in a modern context, a tendency to consume alcohol may be positively selected for among socially anxious individuals by its effect on the likelihood of finding a partner and reproducing. We tested the hypothesis that a higher proportion of individuals with a lifetime diagnosis of SAD and AUD reproduce (i.e., have at least one child) relative to individuals with SAD absent AUD in an individual participant meta-analysis based on over 65,000 adults derived from four nationally representative cross-sectional samples. We then cross-validated these findings against the results of a 10-year follow up of one of these surveys. Lifetime history of SAD was not associated with reproduction whereas lifetime history of AUD was positively associated with reproduction. There was no statistically detectable difference in the proportion of individuals with a lifetime history of SAD with or without AUD who reproduced. There was considerable heterogeneity in all of the analyses involving SAD, suggesting that there are likely to be other pertinent variables relating to SAD and reproduction that should be delineated.
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
ObjectiveCare patterns and Traditional Chinese Medicine (TCM) constitution affects the emotion and health of patients with systemic sclerosis (SSc) while the prevalence of COVID-19 may aggravate such patients’ emotion and health. We investigated the depression and anxiety levels of patients with SSc during the pandemic to identify the correlation between care patterns, TCM constitution, and patients’ emotion.Materials and methodsThis was a cross-sectional study. Patients with SSc and healthy individuals were surveyed using the patient health questionnaire-9, generalized anxiety disorder-7, and constitution in Chinese medicine questionnaire and a modified care pattern questionnaire. Factors correlated with depression and anxiety were screened using univariate and multivariate logistic regression analyses.ResultsA total of 273 patients with SSc and 111 healthy individuals were included in the analysis. The proportion of patients with SSc who were depressed was 74.36%, who had anxiety was 51.65%, and who experienced disease progression during the pandemic was 36.99%. The proportion of income reduction in the online group (56.19%) was higher than that in the hospital group (33.33%) (P = 0.001). Qi-deficiency [adjusted odds ratio (OR) = 2.250] and Qi-stagnation (adjusted OR = 3.824) constitutions were significantly associated with depression. Remote work during the outbreak (adjusted OR = 1.920), decrease in income (adjusted OR = 3.556), and disease progression (P = 0.030) were associated with the occurrence of depression.ConclusionChinese patients with SSc have a high prevalence of depression and anxiety. The COVID-19 pandemic has changed the care patterns of Chinese patients with SSc, and work, income, disease progression, and change of medications were correlates of depression or anxiety in patients with SSc. Qi-stagnation and Qi-deficiency constitutions were associated with depression, and Qi-stagnation constitution was associated with anxiety in patients with SSc.Trial registrationhttp://www.chictr.org.cn/showproj.aspx?proj=62301, identifier ChiCTR2000038796.
Facebook
TwitterThe Associated Press is sharing data from the COVID Impact Survey, which provides statistics about physical health, mental health, economic security and social dynamics related to the coronavirus pandemic in the United States.
Conducted by NORC at the University of Chicago for the Data Foundation, the probability-based survey provides estimates for the United States as a whole, as well as in 10 states (California, Colorado, Florida, Louisiana, Minnesota, Missouri, Montana, New York, Oregon and Texas) and eight metropolitan areas (Atlanta, Baltimore, Birmingham, Chicago, Cleveland, Columbus, Phoenix and Pittsburgh).
The survey is designed to allow for an ongoing gauge of public perception, health and economic status to see what is shifting during the pandemic. When multiple sets of data are available, it will allow for the tracking of how issues ranging from COVID-19 symptoms to economic status change over time.
The survey is focused on three core areas of research:
Instead, use our queries linked below or statistical software such as R or SPSS to weight the data.
If you'd like to create a table to see how people nationally or in your state or city feel about a topic in the survey, use the survey questionnaire and codebook to match a question (the variable label) to a variable name. For instance, "How often have you felt lonely in the past 7 days?" is variable "soc5c".
Nationally: Go to this query and enter soc5c as the variable. Hit the blue Run Query button in the upper right hand corner.
Local or State: To find figures for that response in a specific state, go to this query and type in a state name and soc5c as the variable, and then hit the blue Run Query button in the upper right hand corner.
The resulting sentence you could write out of these queries is: "People in some states are less likely to report loneliness than others. For example, 66% of Louisianans report feeling lonely on none of the last seven days, compared with 52% of Californians. Nationally, 60% of people said they hadn't felt lonely."
The margin of error for the national and regional surveys is found in the attached methods statement. You will need the margin of error to determine if the comparisons are statistically significant. If the difference is:
The survey data will be provided under embargo in both comma-delimited and statistical formats.
Each set of survey data will be numbered and have the date the embargo lifts in front of it in the format of: 01_April_30_covid_impact_survey. The survey has been organized by the Data Foundation, a non-profit non-partisan think tank, and is sponsored by the Federal Reserve Bank of Minneapolis and the Packard Foundation. It is conducted by NORC at the University of Chicago, a non-partisan research organization. (NORC is not an abbreviation, it part of the organization's formal name.)
Data for the national estimates are collected using the AmeriSpeak Panel, NORC’s probability-based panel designed to be representative of the U.S. household population. Interviews are conducted with adults age 18 and over representing the 50 states and the District of Columbia. Panel members are randomly drawn from AmeriSpeak with a target of achieving 2,000 interviews in each survey. Invited panel members may complete the survey online or by telephone with an NORC telephone interviewer.
Once all the study data have been made final, an iterative raking process is used to adjust for any survey nonresponse as well as any noncoverage or under and oversampling resulting from the study specific sample design. Raking variables include age, gender, census division, race/ethnicity, education, and county groupings based on county level counts of the number of COVID-19 deaths. Demographic weighting variables were obtained from the 2020 Current Population Survey. The count of COVID-19 deaths by county was obtained from USA Facts. The weighted data reflect the U.S. population of adults age 18 and over.
Data for the regional estimates are collected using a multi-mode address-based (ABS) approach that allows residents of each area to complete the interview via web or with an NORC telephone interviewer. All sampled households are mailed a postcard inviting them to complete the survey either online using a unique PIN or via telephone by calling a toll-free number. Interviews are conducted with adults age 18 and over with a target of achieving 400 interviews in each region in each survey.Additional details on the survey methodology and the survey questionnaire are attached below or can be found at https://www.covid-impact.org.
Results should be credited to the COVID Impact Survey, conducted by NORC at the University of Chicago for the Data Foundation.
To learn more about AP's data journalism capabilities for publishers, corporations and financial institutions, go here or email kromano@ap.org.
Facebook
Twitterhttps://digital.nhs.uk/about-nhs-digital/terms-and-conditionshttps://digital.nhs.uk/about-nhs-digital/terms-and-conditions
This publication contains the official statistics about uses of the Mental Health Act ('the Act') in England during 2023-24. Under the Act, people with a mental disorder may be formally detained in hospital (or 'sectioned') in the interests of their own health or safety, or for the protection of other people. They can also be treated in the community but subject to recall to hospital for assessment and/or treatment under a Community Treatment Order (CTO). In 2016-17, the way we source and produce these statistics changed. Previously these statistics were produced from the KP90 aggregate data collection. They are now primarily produced from the Mental Health Services Data Set (MHSDS). The MHSDS provides a much richer data source for these statistics, allowing for new insights into uses of the Act. People may be detained in secure psychiatric hospitals, other NHS Trusts or at Independent Service Providers (ISPs). All organisations that detain people under the Act must be registered with the Care Quality Commission (CQC). In recent years, the number of detentions under the Act have been rising. An independent review has examined how the Act is used and has made recommendations for improving the Mental Health Act legislation. In responding to the review, the government said it would introduce a new Mental Health Bill to reform practice. This publication does not cover: 1. People in hospital voluntarily for mental health treatment, as they have not been detained under the Act (see the Mental Health Bulletin). 2. Uses of section 136 where the place of safety was a police station; these are published by the Home Office.
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Survey-based studies suggest naturalistic psychedelic use provides mental health benefits similar to those observed in clinical trials. The current study sought to confirm these findings in a large group of psychedelic users and to conduct a novel examination of associations between amount of psychedelic use and behavioral outcomes, as well as frequency of harms ascribed to psychedelic use. A cross-sectional, online survey was completed by 2,510 adults reporting at least one lifetime psychedelic experience. Participants retrospectively completed a battery of instruments assessing depression, anxiety, and emotional well-being prior to and following psychedelic exposure. Participants also reported preferred psychedelic agent, number of uses, and harms attributed to psychedelic use. Psychedelic use was associated with significant improvements in depressive and anxious symptoms and with increased emotional well-being. These improvements increased in magnitude with increasing psychedelic exposure, with a ceiling effect. However, improvements were noted following a single lifetime use. Strong evidence for benefit of one preferred psychedelic agent over another was not observed, but enduring increases in factors related to mystical-experience and prosocial perspective taking associated with enhanced mental health. Thirteen percent of the survey sample (n = 330) endorsed at least one harm from psychedelic use, and these participants reported less mental health benefit. Results from the current study add to a growing database indicating that psychedelic use—even outside the context of clinical trials—may provide a wide range of mental health benefits, while also posing some risk for harm in a minority of individuals.
Facebook
TwitterBackgroundNepal has been devastated by an unprecedented COVID-19 outbreak, affecting people emotionally, physically, and socially, resulting in significant morbidity and mortality. Approximately 10% of COVID-19 affected people have symptoms that last more than 3–4 weeks and experience numerous symptoms causing an impact on everyday functioning, social, and cognitive function. Thus, it is vital to know about the recovered patient’s health status and undertake rigorous examinations to detect and treat infections. Hence, this study aims to assess the health status of COVID-19 post-recovery patients in Nepal.MethodA descriptive cross-sectional mixed-method study was conducted in all seven provinces of Nepal. A total of 552 interviews were conducted for the quantitative study, and 25 in-depth interviews were conducted for the qualitative study among above 18 years COVID-19-recovered patients. The data was gathered over the phone through the purposive sampling method The results of a descriptive and thematic analysis were interpreted.FindingThe majority (more than 80%) of the recovered patients could routinely perform household duties, activities outside the home, and financial job accounting. However, a few of them required assistance in carrying out all of those tasks. Prior and then after COVID-19 infection, smoking habits reduced by about one-tenth and alcohol intake decreased by a twelve percent. A qualitative finding revealed that the majority of COVID-19 symptomatic patients experienced a variety of physical symptoms such as fever, headache, body pain, fatigue, tiredness, sore throat, cough, loss of taste, loss of smell, sneezing, loss of appetite, and difficulty breathing, while others felt completely fine after being recovered. Furthermore, there was no variation in the daily functional activities of the majority of the recovered patients, while a few were found conducting fewer activities than usual because they were concerned about their health. For social health, quantitative data indicated that more than half of the participants’ social health was severely impacted. According to the IDI, the majority of the interviewees perceived society’s ignorance and misbehavior. Family members were the most often solicited sources of support. Some participants got care and assistance, but the majority did not get affection or love from their relatives. Moreover, regarding mental health, 15 percent of participants had repeated disturbing and unwanted thoughts about COVID-19 after being recovered, 16 percent tried to avoid information on COVID-19 and 7 .7 percent of people had unfavorable ideas or sentiments about themselves. More than 16 percent of participants reported feeling some level of stress related to the workplace and home. While in-depth interviews participants revealed that COVID-infected patients who were asymptomatic didn’t experience any emotional change in them but recovered patients who are symptomatic symptoms had anxiety and still being conscious of COVID-19 in fear of getting infected again Additionally, it was discovered that participants’ mental health is influenced by ignorance of society, as well as by fake news posted to social media.ConclusionCOVID-19 infection has had an impact on physical, mental, and social well-being. Hence, to aid in the early recovery of COVID-19 patients, provision of evaluating and reporting the clinical features, early detection and management of long COVID case is needed from the local and provincial and central government of Nepal.
Facebook
TwitterJasminum sambac (L.) Aiton, commonly known as Arabian jasmine, is widely used in Thai traditional medicine for mental health ailments. However, studies in humans and animals have yielded mixed results on the effects of J. sambac on anxiety-related behaviors with some studies finding it to be anxiolytic, and others, paradoxically, finding it to be anxiogenic. Using adult zebrafish, we sought to determine whether factors like strain, sex, and personality might contribute to the variable effects of J. sambac on anxiety-related behavior. The flowers of J. sambac were extracted by ultrasonic-assisted extraction with optimal air pressure. Headspace solid-phase microextraction with gas chromatography-mass spectrometry (HS-SPME-GC-MS) identified the main components in the Arabian jasmine flower extract, including linalool (an anxiolytic compound) and benzaldehyde (an anxiogenic compound). We fed three strains of zebrafish (AB, TL, and WIK) a gelatin pellet containing different concentrations of J. sambac (5-20 mg kg-1) and assessed 3-dimensional swim behavior in the novel tank and mirror biting tests. We found that in female AB fish, J. sambac resulted in a decrease in both bottom distance and percent explored during the novel tank test, consistent with an anxiogenic effect; there was no effect in WIK or TL fish. We also found that behavioral/personality type influenced the effect of J. sambac during a second exposure to the novel tank where shy AB females increased their percent explored and low activity males to increase their bottom distance, consistent with anxiolytic effects. Thus, we find that sex, genetics, and personality interact to influence the anxiety-related effects of Arabian jasmine, which may contribute to the opposing effects previously reported in the literature.Files and DescriptionS1 Table_GC-MS profiling of Arabian jasmine water extract.csvThis file contains all the data underlying Fig. 1C. It includes GC-MS data of Arabian jasmine extractsS2 Table_novel tank test dose results.csvThis file contains all the data underlying Fig. 2A, C.S3 Table_mirror biting test dose results.csvThis file contains all the data underlying Fig. 2B, D.S4 Table_personality results.csvThis file contains all the data underlying Fig. 3A-B.S5 Table_novel tank test personality results.csvThis file contains all the data underlying Fig. 3D-G.S6 Table_mirror biting test personality results.csvThis file contains all the data underlying Fig. S1
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
a Valid percent is reported, i.e. the rate of those who provided data.Descriptive statistics of examined predictor variables within the family history of mental illness domain.
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Prevalence of disability among Syrian refugees living in Sultanbeyli, Istanbul.
Not seeing a result you expected?
Learn how you can add new datasets to our index.
Facebook
TwitterAttribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
BackgroundThe rise of depression, anxiety, and suicide rates has led to increased demand for telemedicine-based mental health screening and remote patient monitoring (RPM) solutions to alleviate the burden on, and enhance the efficiency of, mental health practitioners. Multimodal dialog systems (MDS) that conduct on-demand, structured interviews offer a scalable and cost-effective solution to address this need.ObjectiveThis study evaluates the feasibility of a cloud based MDS agent, Tina, for mental state characterization in participants with depression, anxiety, and suicide risk.MethodSixty-eight participants were recruited through an online health registry and completed 73 sessions, with 15 (20.6%), 21 (28.8%), and 26 (35.6%) sessions screening positive for depression, anxiety, and suicide risk, respectively using conventional screening instruments. Participants then interacted with Tina as they completed a structured interview designed to elicit calibrated, open-ended responses regarding the participants' feelings and emotional state. Simultaneously, the platform streamed their speech and video recordings in real-time to a HIPAA-compliant cloud server, to compute speech, language, and facial movement-based biomarkers. After their sessions, participants completed user experience surveys. Machine learning models were developed using extracted features and evaluated with the area under the receiver operating characteristic curve (AUC).ResultsFor both depression and suicide risk, affected individuals tended to have a higher percent pause time, while those positive for anxiety showed reduced lip movement relative to healthy controls. In terms of single-modality classification models, speech features performed best for depression (AUC = 0.64; 95% CI = 0.51–0.78), facial features for anxiety (AUC = 0.57; 95% CI = 0.43–0.71), and text features for suicide risk (AUC = 0.65; 95% CI = 0.52–0.78). Best overall performance was achieved by decision fusion of all models in identifying suicide risk (AUC = 0.76; 95% CI = 0.65–0.87). Participants reported the experience comfortable and shared their feelings.ConclusionMDS is a feasible, useful, effective, and interpretable solution for RPM in real-world clinical depression, anxiety, and suicidal populations. Facial information is more informative for anxiety classification, while speech and language are more discriminative of depression and suicidality markers. In general, combining speech, language, and facial information improved model performance on all classification tasks.