Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Monday, March 11, 2019 at 4:00 PM to 4:30 PM EST. We apologize in advance for any inconvenience this may cause you.
Who will be affected?
Readers: No access to all 28 journals. We recommend accessing our articles via PubMed Central
Authors: No access to the submission form or your user account.
Reviewers: No access to your user account. Please download manuscripts you are reviewing for offline reading before Monday, March 11, 2019 at 4:00 PM.
Editors: No access to your user account to assign reviewers or make decisions.
Copyeditors: No access to user account. Please download manuscripts you are copyediting before Monday, March 11, 2019 at 4:00 PM.
Background: New technologies are changing the access to medical records and the relationship between physicians and patients. Professionals can now use e-mental health tools to provide prompt and personalized responses to patients with mental illness. However, there is a lack of knowledge about the digital phenotype of patients that use e-mental health. Objective: To reveal the profiles of users of a mental health app through machine learning techniques. Methods: We have applied a non-parametric model, the Sparse Poisson Factorization Model (SPFM), to discover latent features in the response patterns made by 2254 psychiatric outpatients to a short self-assessment on general health. The assessment was completed through a mental health app after the first login. Results: The results show four different profiles of patients: 1) the common pattern for all patients included feelings of worthlessness, aggressiveness and suicidal ideas; 2) one in four reported also low energy and difficulties to cope with problems; 3) less than a quarter of the sample described depressive symptoms with extremely high scores in suicidal thoughts and aggressiveness, and 4) a small number, possibly with the most severe conditions, reported a combination of all these features. Conclusions: E-mental-health user profiles do not overlap with clinician-made diagnoses. Since each profile seems to be associated with a different level of severity, they could be useful for the prediction of behavioural risks among users of e-mental health apps.
(Toronto, Aug 29, 2019) Clarivate Analytics has now confirmed that JMIR Mental Health has (finally) been admitted to SCIE/JCR, meaning that it will receive its first official 2019 Impact Factor, to be released by Clarivate in June 2020, reflecting the number of citations in 2019 to articles published in 2018 or 2017. We expect the IF to place the journal firmly in the Q1 (top 25% of journals).
JMIR Mental Health (JMH, ISSN 2368-7959, Editor-in-Chief: John Torous MD MBI) is a PubMed-indexed, peer-reviewed journal which has a unique focus on digital health and Internet/mobile interventions, technologies and electronic innovations (software and hardware) for mental health, addictions, online counselling and behaviour change. This includes formative evaluation and system descriptions, theoretical papers, review papers, viewpoint/vision papers, and rigorous evaluations related to digital psychiatry, e-mental health, and clinical informatics in psychiatry/psychology. The main themes/topics covered by this journal can be found here.
JMIR Mental Health has an international author- and readership and welcomes submissions from around the world.
JMIR Mental Health features a rapid and thorough peer-review process, professional copyediting, professional production of PDF, XHTML, and XML proofs.
The journal is indexed in PubMed, PubMed Central, and SCIE (Science Citation Index Expanded)/WoS/JCR (Journal Citation Reports).
Background: New technologies are set to profoundly change the way we understand and manage psychiatric disorders, including obsessive-compulsive disorder (OCD). Developments in imaging and biomarkers, along with medical informatics, may well allow for better assessments and interventions in the future. Recent advances in the concept of digital phenotype, which involves using computerized measurement tools to capture the characteristics of a given psychiatric disorder, is one paradigmatic example.
Objective: The impact of new technologies on health professionals’ practice in OCD care remains to be determined. Recent developments could disrupt not just their clinical practices, but also their beliefs, ethics, and representations, even going so far as to question their professional culture. This study aimed to conduct an extensive review of new technologies in OCD.
Methods: We conducted the review by looking for titles in the PubMed database up to December 2017 that contained the following terms: [Obsessive] AND [Smartphone] OR [phone] OR [Internet] OR [Device] OR [Wearable] OR [Mobile] OR [Machine learning] OR [Artificial] OR [Biofeedback] OR [Neurofeedback] OR [Momentary] OR [Computerized] OR [Heart rate variability] OR [actigraphy] OR [actimetry] OR [digital] OR [virtual reality] OR [Tele] OR [video].
Results: We analyzed 364 articles, of which 62 were included. Our review was divided into 3 parts: prediction, assessment (including diagnosis, screening, and monitoring), and intervention.
Conclusions: The review showed that the place of connected objects, machine learning, and remote monitoring has yet to be defined in OCD. Smartphone assessment apps and the Web Screening Questionnaire demonstrated good sensitivity and adequate specificity for detecting OCD symptoms when compared with a full-length structured clinical interview. The ecological momentary assessment procedure may also represent a worthy addition to the current suite of assessment tools. In the field of intervention, CBT supported by smartphone, internet, or computer may not be more effective than that delivered by a qualified practitioner, but it is easy to use, well accepted by patients, reproducible, and cost-effective. Finally, new technologies are enabling the development of new therapies, including biofeedback and virtual reality, which focus on the learning of coping skills. For them to be used, these tools must be properly explained and tailored to individual physician and patient profiles.
Background: Social media data can be explored as a tool to detect sleep deprivation. First-year undergraduate students in their first quarter were invited to wear sleep-tracking devices (Basis; Intel), allow us to follow them on Twitter, and complete weekly surveys regarding their sleep.
Objective: This study aimed to determine whether social media data can be used to monitor sleep deprivation.
Methods: The sleep data obtained from the device were utilized to create a tiredness model that aided in labeling the tweets as sleep deprived or not at the time of posting. Labeled data were used to train and test a gated recurrent unit (GRU) neural network as to whether or not study participants were sleep deprived at the time of posting.
Results: Results from the GRU neural network suggest that it is possible to classify the sleep-deprivation status of a tweet’s author with an average area under the curve of 0.68.
Conclusions: It is feasible to use social media to identify students’ sleep deprivation. The results add to the body of research suggesting that social media data should be further explored as a potential source for monitoring health.
Background: Self-monitoring of symptoms is a cornerstone of psychological interventions in bipolar disorder (BD), but individuals with lived experience also value tracking holistic outcomes, such as quality of life (QoL). Importantly, self-monitoring is not always experienced positively by people with BD and may have lower than expected rates of engagement. Therefore, before progressing into QoL tracking tools, it is important to explore user perspectives to identify possible risks and benefits, optimal methods to support engagement, and possible avenues to integrate QoL self-monitoring practices into clinical work.
Objective: This study aimed to conduct a qualitative exploration of how individuals with BD engaged with a Web-based version of a BD-specific QoL self-monitoring instrument, the QoL tool.
Methods: A total of 43 individuals with BD engaged with a self-management intervention with an optional Web-based QoL self-assessment tool as part of an overarching mixed method study. Individuals were later interviewed about personal experiences of engagement with the intervention, including experiences of gauging their own QoL. A thematic analysis was used to identify salient aspects of the experience of QoL self-monitoring in BD.
Results: In total, 4 categories describing people’s experiences of QoL self-monitoring were identified: (1) breadth of QoL monitoring, (2) highlighting the positive, (3) connecting self-monitoring to action, and (4) self-directed patterns of use.
Conclusions: The findings of this research generate novel insights into ways in which individuals with BD experience the Web-based QoL self-assessment tool. The value of tracking the breadth of domains was an overarching aspect, facilitating the identification of both areas of strength and life domains in need of intervention. Importantly, monitoring QoL appeared to have an inherently therapeutic quality, through validating flourishing areas and reinforcing self-management efforts. This contrasts the evidence suggesting that symptom tracking may be distressing because of its focus on negative experiences and positions QoL as a valuable adjunctive target of observation in BD. Flexibility and personalization of use of the QoL tool were key to engagement, informing considerations for health care providers wishing to support self-monitoring and future research into Web- or mobile phone–based apps.
The modern omnipresence of social media and social networking sites (SNSs) brings with it a range of important research questions. One of these concerns the impact of SNS use on mental health and well-being, a question that has been pursued in depth by scholars in the psychological sciences and the field of human-computer interaction. Despite this attention, the design choices made in the development of SNSs and the notion of well-being employed to evaluate such systems require further scrutiny. In this viewpoint paper, we examine the strategic design choices made in our development of an enclosed SNS for young people experiencing mental ill-health in terms of ethical and persuasive design and in terms of how it fosters well-being. In doing so, we critique the understanding of well-being that is used in much of the existing literature to make claims about the impact of a given technology on well-being. We also demonstrate how the holistic concept of eudaimonic well-being and ethical design of SNSs can complement one another.
Background: The acceptability of electronic mental (e-mental) health apps has already been studied. However, the attitudes of medical experts, students, and patients taking into account their knowledge of and previous experiences with e-mental health apps have not been investigated.
Objective: The aim of this study was to explore the attitudes, expectations, and concerns of medical experts, including physicians, psychotherapists and nursing staff, students of medicine or psychology, and patients toward e-mental health apps when considering their knowledge of and former experiences with e-mental health apps.
Methods: This cross-sectional quantitative and qualitative survey was based on a self-developed questionnaire. A total of 269 participants were included (104 experts, 80 students, and 85 patients), and 124 eligible participants answered a paper version and 145 answered an identical online version of the questionnaire. The measures focused on existing knowledge of and experiences with e-mental health apps, followed by a question on whether electronic health development was generally accepted or disliked. Further, we asked about the expectations for an ideal e-mental health app and possible concerns felt by the participants. All items were either presented on a 5-point Likert scale or as multiple-choice questions. Additionally, 4 items were presented as open text fields.
Results: Although 33.7% (35/104) of the experts, 15.0% (12/80) of the students, and 41.2% (35/85) of the patients knew at least one e-mental health app, few had already tried one (9/104 experts [8.7%], 1/80 students [1.3%], 22/85 patients [25.9%]). There were more advocates than skeptics in each group (advocates: 71/104 experts [68.3%], 50/80 students [62.5%], 46/85 patients [54.1%]; skeptics: 31/104 experts [29.8%], 20/80 students [25.0%], 26/85 patients [30.6%]). The experts, in particular, believed, that e-mental health apps will gain importance in the future (mean 1.08, SD 0.68; 95% CI 0.94-1.21). When asked about potential risks, all groups reported slight concerns regarding data security (mean 0.85, SD 1.09; 95% CI 0.72-0.98). Patient age was associated with several attitudes toward e-mental health apps (future expectations: r=–0.31, P=.005; total risk score: r=0.22, P=.05). Attitudes toward e-mental health apps correlated negatively with the professional experience of the experts (rs(94)=–0.23, P=.03).
Conclusions: As opposed to patients, medical experts and students lack knowledge of and experience with e-mental health apps. If present, the experiences were assessed positively. However, experts show a more open-minded attitude with less fear of risks. Although some risks were perceived regarding data security, the attitudes and expectations of all groups were rather positive. Older patients and medical experts with long professional experience tend to express more skepticism.
Clinical Trial: German Clinical Trials Register DRKS00013095; https://www.drks.de/drks_web/navigate.do? navigationId=trial.HTML&TRIAL_ID=DRKS00013095
Background: Disfigurement (visible difference) from wide-ranging congenital or acquired conditions, injuries, or treatments can negatively impact adolescents’ psychological well-being, education and health behaviours. Alongside medical interventions, appearance-specific cognitive behavioural and social skills training to manage stigma and appearance anxiety may improve psychosocial outcomes. YP Face IT (YPF), is a Web-based seven session self-help program plus booster quiz, utilising cognitive behavioural and social skills training for young people (YP) struggling with a visible difference. Co-designed by adolescents and psychologists, it includes interactive multimedia and automated reminders to complete sessions/homework. Adolescents access YPF via a health professional who determines its suitability and remotely monitors clients’ usage.
Objective: To establish the feasibility of evaluating YPF for 12-17 year olds self-reporting appearance-related distress and/or bullying associated with a visible difference.
Methods: Randomized controlled trial with nested qualitative and economic study evaluating YPF compared with usual care (UC). Feasibility outcomes included: viability of recruiting via general practitioner (GP) practices (face to face and via patient databases) and charity advertisements; intervention acceptability and adherence; feasibility of study and data collection methods; and health professionals’ ability to monitor users’ online data for safeguarding issues. Primary psychosocial self-reported outcomes collected online at baseline, 13, 26, and 52 weeks were as follows: appearance satisfaction (Appearance Subscale from Mendleson et al’s (2001) Body Esteem Scale); social anxiety (La Greca’s (1999) Social Anxiety Scale for Adolescents). Secondary outcomes were; self-esteem; romantic concerns; perceived stigmatization; social skills and healthcare usage. Participants were randomised using remote Web-based allocation.
Results: Thirteen charities advertised the study yielding 11 recruits, 13 primary care practices sent 687 invitations to patients on their databases with a known visible difference yielding 17 recruits (2.5% response rate), 4 recruits came from GP consultations. Recruitment was challenging, therefore four additional practices mass-mailed 3,306 generic invitations to all 12-17 year old patients yielding a further 15 participants (0.5% response rate). Forty-seven YP with a range of socioeconomic backgrounds and conditions were randomised (26% male, 91% white, mean age 14 years (SD 1.7)); 23 to YPF, 24 to UC). At 52 weeks, 16 (70%) in the intervention and 20 (83%) in UC groups completed assessments. There were no intervention-related adverse events; most found YPF acceptable with three withdrawing because they judged it was for higher-level concerns; 12 (52%) completed seven sessions. The study design was acceptable and feasible, with multiple recruitment strategies. Preliminary findings indicate no changes from baseline in outcome measures among the UC group and positive changes in appearance satisfaction and fear of negative evaluation among the YPF group when factoring in baseline scores and intervention adherence.
Conclusions: YPF is novel, safe and potentially helpful. Its full psychosocial benefits should be evaluated in a large-scale RCT, which would be feasible with wide-ranging recruitment strategies.
Clinical Trial: ISRCTN registry ISRCTN40650639; http://www.isrctn.com/ISRCTN40650639
Background: Eating disorders severely impact psychological, physical, and social functioning, and yet, the majority of individuals with eating disorders do not receive treatment. Mobile health apps have the potential to decrease access barriers to care and reach individuals who have been underserved by traditional treatment modalities.
Objective: The objective of this study was to evaluate the effectiveness of a tailored, fully automated self-help version of Recovery Record, an app developed for eating disorders management. We examined differences in eating disorder symptom change in app users that were randomized to receive either a standard, cognitive behavioral therapy–based version of the app or a tailored version that included algorithmically determined clinical content aligned with baseline and evolving user eating disorder symptom profiles.
Methods: Participants were people with eating disorder symptoms who did not have access to traditional treatment options and were recruited via the open-access Recovery Record app to participate in this randomized controlled trial. We examined both continuous and categorical clinical improvement outcomes (measured with the self-report Eating Disorder Examination Questionnaire [EDE-Q]) in both intervention groups.
Results: Between December 2016 and August 2018, 3294 Recovery Record app users were recruited into the study, out of which 959 were considered engaged, completed follow-up assessments, and were included in the analyses. Both study groups achieved significant overall outcome improvement, with 61.6% (180/292) of the tailored group and 55.4% (158/285) of the standard group achieving a clinically meaningful change in the EDE-Q, on average. There were no statistically significant differences between randomized groups for continuous outcomes, but a pattern of improvement being greater in the tailored group was evident. The rate of remission on the EDE-Q at 8 weeks was significantly greater in the group receiving the tailored version (d=0.22; P≤.001).
Conclusions: This is the first report to compare the relative efficacy of two versions of a mobile app for eating disorders. The data suggest that underserved individuals with eating disorder symptoms may benefit clinically from a self-help app and that personalizing app content to specific clinical presentations may be more effective in promoting symptomatic remission on the EDE-Q than content that offers a generic approach.
Clinical Trial: ClinicalTrials.gov NCT02503098; https://clinicaltrials.gov/ct2/show/NCT02503098.
Background: Mental health is integral to our salubrity, but mental disorders are very debilitating and common. Therefore, it is critical to provide accessible, timely, and inexpensive mental care. This can be done through mobile health (mHealth), namely, mobile medical apps, which are gaining popularity among clinicians and patients. mHealth is a fast-paced field, and there is significant variation in the number of installs among psychiatry apps. However, the factors that influence psychiatry app installs have yet to be studied.
Objective: This study aimed to identify predictors of the number of app installs in psychiatry.
Methods: A literature review identified which factors influence app installs. Psychiatry apps available in the Google Play Store were reviewed, and publicly available data were collected. A multivariate ordinal logistic regression analysis was performed to evaluate the effect of said factors on the number of installs.
Results: Our search identified 128 psychiatry apps: 2.3% (3/128) had never been installed, approximately half (53.1%, 68/128) had less than 500 installs, and only 0.8% (1/128) had over 10,000,000 installs. A multivariate logistic regression analysis identified that apps with a lower price (P<.001), a higher rating (P<.001), optional in-app purchases (P<.001), and age restriction (P=.04) had a higher number of installs. The involvement of a psychiatrist or other health care professional (HCP) had no statistically significant influence on the number of installs. Only data from the Google Play Store and the developers’ websites were available for analysis, and the depth of involvement of HCPs was impossible to document.
Conclusions: Psychiatry apps with a lower price, optional in-app purchases, age restriction, and a higher rating are expected to have a higher number of installs. Unlike other medical fields, in this study, the explicit participation of psychiatrists in app development was not a significant predictor of the number of installs. Research is needed to identify other factors that may influence the number of installs, as that can help mHealth app development.
Background: Cognitive symptoms are common in major depressive disorder and may help to identify patients who need treatment or who are not experiencing adequate treatment response. Digital tools providing real-time data assessing cognitive function could help support patient treatment and remediation of cognitive and mood symptoms.
Objective: The aim of this study was to examine feasibility and validity of a wearable high-frequency cognitive and mood assessment app over 6 weeks, corresponding to when antidepressant pharmacotherapy begins to show efficacy.
Methods: A total of 30 patients (aged 19-63 years; 19 women) with mild-to-moderate depression participated in the study. The new Cognition Kit app was delivered via the Apple Watch, providing a high-resolution touch screen display for task presentation and logging responses. Cognition was assessed by the n-back task up to 3 times daily and depressed mood by 3 short questions once daily. Adherence was defined as participants completing at least 1 assessment daily. Selected tests sensitive to depression from the Cambridge Neuropsychological Test Automated Battery and validated questionnaires of depression symptom severity were administered on 3 occasions (weeks 1, 3, and 6). Exploratory analyses examined the relationship between mood and cognitive measures acquired in low- and high-frequency assessment.
Results: Adherence was excellent for mood and cognitive assessments (95% and 96%, respectively), did not deteriorate over time, and was not influenced by depression symptom severity or cognitive function at study onset. Analyses examining the relationship between high-frequency cognitive and mood assessment and validated measures showed good correspondence. Daily mood assessments correlated moderately with validated depression questionnaires (r=0.45-0.69 for total daily mood score), and daily cognitive assessments correlated moderately with validated cognitive tests sensitive to depression (r=0.37-0.50 for mean n-back).
Conclusions: This study supports the feasibility and validity of high-frequency assessment of cognition and mood using wearable devices over an extended period in patients with major depressive disorder.
Background: The therapist-patient therapeutic alliance is known to be an important factor in cognitive behavioral therapy (CBT). However, findings by previous studies for obsessive-compulsive disorder (OCD), panic disorder (PD), and social anxiety disorder (SAD) have not been consistent regarding whether this alliance provides symptomatic improvements.
Objective: This study investigated predictors of symptom improvement in patients receiving CBT via video conferencing.
Methods: A total of 29 patients who participated in a previous clinical trial were recruited for the current study. Therapeutic alliance and clinical background in patients with OCD, PD, and SAD were measured at first session or the eighth session, which were calculated by multiple regression analyses to estimate the impact on therapeutic response percentage change.
Results: The multiple regression analyses showed that, among the independent variables, only patients’ agreement in the therapeutic alliance remained viable, as other variables were a best fit for the excluded model (P=.002). The results show that patients’ agreement on therapeutic goals and tasks explains the prognosis, as the normalization factor beta was 0.54 (SE 32.73; 95% CI 1.23-5.17; P=.002) and the adjusted R2 was .266.
Conclusions: Patients' agreement on therapeutic goals and tasks predicts improvement after CBT via video conferencing.
Background: The privacy of patients with mental health conditions is prominent in health information exchange (HIE) discussions, given that their potentially sensitive personal health information (PHI) may be electronically shared for various health care purposes. Currently, the patient privacy perspective in the mental health context is not well understood because of the paucity of in-depth patient privacy research; however, the evidence suggests that patient privacy perspectives are more nuanced than what has been assumed in the academic and health care community.
Objective: This study aimed to generate an understanding on how patients with mental health conditions feel about privacy in the context of HIE in Canada. This study also sought to identify the factors underpinning their privacy perspectives and explored how their perspectives influenced their attitudes toward HIE.
Methods: Semistructured interviews were conducted with patients at a Canadian academic hospital for addictions and mental health. Guided by the Antecedent-Privacy Concern-Outcome macro-model, interview transcripts underwent deductive and inductive thematic analyses.
Results: We interviewed 14 participants. Their privacy concerns varied, depending on the participant’s privacy experiences and health care perceptions. Media reports of privacy breaches and hackers had little impact on participants’ privacy concerns because of a fatalistic belief that privacy breaches are a reality in the digital age. Rather, direct observations and experiences with the mistreatment of PHI in health care settings caused concern. Decisions to trust others with PHI depended on past experiences with the individual (or institution) and health care needs. Participants had little knowledge of patient privacy rights and legislation but were willing to participate in HIE because of perceived individual and societal benefits.
Conclusions: This study introduces evidence that patients with mental health conditions would support HIE. Participants were pragmatic, supporting HIE because they wanted the best care possible. They also understood that their PHI was critical in supporting the single-payer Canadian health care system. Participant health care experiences informed their privacy perspectives, trust, and PHI sharing attitudes—all accentuating the importance of the patient experience in building trust in HIE. Their lack of knowledge about patient rights and PHI uses highlights the degree of trust they have in the health care system to protect their privacy. These findings suggest that the patient privacy discourse should extend beyond the oft-cited barrier of patient privacy concerns to include discussions about building trust, communicating the benefits of HIE, and improving patient experiences. Although our findings are in the Canadian context, this study highlights the importance of engaging patients in privacy policy discussions, regardless of jurisdiction, to ensure their nuanced perspectives are reflected in policy decisions on their PHI.
Background: Depression is a common disorder that still remains underdiagnosed and undertreated in the UK National Health Service. Charities and voluntary organizations offer mental health services, but they are still struggling to promote these services to the individuals who need them. By analyzing social media (SM) content using machine learning techniques, it may be possible to identify which SM users are currently experiencing low mood, thus enabling the targeted advertising of mental health services to the individuals who would benefit from them.
Objective: This study aimed to understand SM users’ opinions of analysis of SM content for depression and targeted advertising on SM for mental health services.
Methods: A Web-based, mixed methods, cross-sectional survey was administered to SM users aged 16 years or older within the United Kingdom. It asked participants about their demographics, their usage of SM, and their history of depression and presented structured and open-ended questions on views of SM content being analyzed for depression and views on receiving targeted advertising for mental health services.
Results: A total of 183 participants completed the survey, and 114 (62.3%) of them had previously experienced depression. Participants indicated that they posted less during low moods, and they believed that their SM content would not reflect their depression. They could see the possible benefits of identifying depression from SM content but did not believe that the risks to privacy outweighed these benefits. A majority of the participants would not provide consent for such analysis to be conducted on their data and considered it to be intrusive and exposing.
Conclusions: In a climate of distrust of SM platforms’ usage of personal data, participants in this survey did not perceive that the benefits of targeting advertisements for mental health services to individuals analyzed as having depression would outweigh the risks to privacy. Future work in this area should proceed with caution and should engage stakeholders at all stages to maximize the transparency and trustworthiness of such research endeavors.
Background: New technologies are changing the access to medical records and the relationship between physicians and patients. Professionals can now use e-mental health tools to provide prompt and pers...
Background: New technologies are changing the access to medical records and the relationship between physicians and patients. Professionals can now use e-mental health tools to provide prompt and personalized responses to patients with mental illness. However, there is a lack of knowledge about the digital phenotype of patients that use e-mental health. Objective: To reveal the profiles of users of a mental health app through machine learning techniques. Methods: We have applied a non-parametric model, the Sparse Poisson Factorization Model (SPFM), to discover latent features in the response patterns made by 2254 psychiatric outpatients to a short self-assessment on general health. The assessment was completed through a mental health app after the first login. Results: The results show four different profiles of patients: 1) the common pattern for all patients included feelings of worthlessness, aggressiveness and suicidal ideas; 2) one in four reported also low energy and difficulties to cope with problems; 3) less than a quarter of the sample described depressive symptoms with extremely high scores in suicidal thoughts and aggressiveness, and 4) a small number, possibly with the most severe conditions, reported a combination of all these features. Conclusions: E-mental-health user profiles do not overlap with clinician-made diagnoses. Since each profile seems to be associated with a different level of severity, they could be useful for the prediction of behavioural risks among users of e-mental health apps.
