Learnings from user feedback of a novel digital mental health assessment.

Digital mental health interventions (DMHI) have the potential to address barriers to face-to-face mental healthcare. In particular, digital mental health assessments offer the opportunity to increase access, reduce strain on services, and improve identification. Despite the potential of DMHIs there remains a high drop-out rate. Therefore, investigating user feedback may elucidate how to best design and deliver an engaging digital mental health assessment. The current study aimed to understand 1304 user perspectives of (1) a newly developed digital mental health assessment to determine which features users consider to be positive or negative and (2) the Composite International Diagnostic Interview (CIDI) employed in a previous large-scale pilot study. A thematic analysis method was employed to identify themes in feedback to three question prompts related to: (1) the questions included in the digital assessment, (2) the homepage design and reminders, and (3) the assessment results report. The largest proportion of the positive and negative feedback received regarding the questions included in the assessment (n = 706), focused on the quality of the assessment (n = 183, 25.92% and n = 284, 40.23%, respectively). Feedback for the homepage and reminders (n = 671) was overwhelmingly positive, with the largest two themes identified being positive usability (i.e., ease of use; n = 500, 74.52%) and functionality (i.e., reminders; n = 278, 41.43%). The most frequently identified negative theme in results report feedback (n = 794) was related to the report content (n = 309, 38.92%), with users stating it was lacking in-depth information. Nevertheless, the most frequent positive theme regarding the results report feedback was related to wellbeing outcomes (n = 145, 18.26%), with users stating the results report, albeit brief, encouraged them to seek professional support. Interestingly, despite some negative feedback, most users reported that completing the digital mental health assessment has been worthwhile (n = 1,017, 77.99%). Based on these findings, we offer recommendations to address potential barriers to user engagement with a digital mental health assessment. In summary, we recommend undertaking extensive co-design activities during the development of digital assessment tools, flexibility in answering modalities within digital assessment, customizable additional features such as reminders, transparency of diagnostic decision making, and an actionable results report with personalized mental health resources.

mHealth Solutions for Mental Health Screening and Diagnosis: A Review of App User Perspectives Using Sentiment and Thematic Analysis.

Mental health screening and diagnostic apps can provide an opportunity to reduce strain on mental health services, improve patient well-being, and increase access for underrepresented groups. Despite promise of their acceptability, many mental health apps on the market suffer from high dropout due to a multitude of issues. Understanding user opinions of currently available mental health apps beyond star ratings can provide knowledge which can inform the development of future mental health apps. This study aimed to conduct a review of current apps which offer screening and/or aid diagnosis of mental health conditions on the Apple app store (iOS), Google Play app store (Android), and using the m-health Index and Navigation Database (MIND). In addition, the study aimed to evaluate user experiences of the apps, identify common app features and determine which features are associated with app use discontinuation. The Apple app store, Google Play app store, and MIND were searched. User reviews and associated metadata were then extracted to perform a sentiment and thematic analysis. The final sample included 92 apps. 45.65% (n = 42) of these apps only screened for or diagnosed a single mental health condition and the most commonly assessed mental health condition was depression (38.04%, n = 35). 73.91% (n = 68) of the apps offered additional in-app features to the mental health assessment (e.g., mood tracking). The average user rating for the included apps was 3.70 (SD = 1.63) and just under two-thirds had a rating of four stars or above (65.09%, n = 442). Sentiment analysis revealed that 65.24%, n = 441 of the reviews had a positive sentiment. Ten themes were identified in the thematic analysis, with the most frequently occurring being performance (41.32%, n = 231) and functionality (39.18%, n = 219). In reviews which commented on app use discontinuation, functionality and accessibility in combination were the most frequent barriers to sustained app use (25.33%, n = 19). Despite the majority of user reviews demonstrating a positive sentiment, there are several areas of improvement to be addressed. User reviews can reveal ways to increase performance and functionality. App user reviews are a valuable resource for the development and future improvements of apps designed for mental health diagnosis and screening.

Personality, symptom, and demographic correlates of perceived efficacy of selective serotonin reuptake inhibitor monotherapy among current users with low mood: A data-driven approach.

BACKGROUND: Selective serotonin reuptake inhibitors (SSRIs) are often the first-line treatment option for depressive symptoms, however their efficacy varies across patients. Identifying predictors of response to SSRIs could facilitate personalised treatment of depression and improve treatment outcomes. The aim of this study was to develop a data-driven formulation of demographic, personality, and symptom-level factors associated with subjective response to SSRI treatment. METHODS: Participants were recruited online and data were collected retrospectively through an extensive digital mental health questionnaire. Extreme gradient boosting classification with nested cross-validation was used to identify factors distinguishing between individuals with low (n=37) and high (n=111) perceived benefit from SSRI treatment. RESULTS: The algorithm demonstrated a good predictive performance (test AUC=.88±.07). Positive affectivity was the strongest predictor of response to SSRIs and a major confounder of the remaining associations. After controlling for positive affectivity, as well as current wellbeing, severity of current depressive symptoms, and multicollinearity, only low positive affectivity, chronic pain, sleep problems, and unemployment remained significantly associated with diminished subjective response to SSRIs. LIMITATIONS: This was an exploratory analysis of data collected at a single time point, for a study which had a different primary aim. Therefore, the results may not reflect causal relationships, and require validation in future prospective studies. Furthermore, the data were self-reported by internet users, which could affect integrity of the dataset and limit generalisability of the results. CONCLUSIONS: Our findings suggest that demographic, personality, and symptom data may offer a potential cost-effective and efficient framework for SSRI treatment outcome prediction.

A machine learning algorithm to differentiate bipolar disorder from major depressive disorder using an online mental health questionnaire and blood biomarker data.

The vast personal and economic burden of mood disorders is largely caused by their under- and misdiagnosis, which is associated with ineffective treatment and worsening of outcomes. Here, we aimed to develop a diagnostic algorithm, based on an online questionnaire and blood biomarker data, to reduce the misdiagnosis of bipolar disorder (BD) as major depressive disorder (MDD). Individuals with depressive symptoms (Patient Health Questionnaire-9 score ≥5) aged 18-45 years were recruited online. After completing a purpose-built online mental health questionnaire, eligible participants provided dried blood spot samples for biomarker analysis and underwent the World Health Organization World Mental Health Composite International Diagnostic Interview via telephone, to establish their mental health diagnosis. Extreme Gradient Boosting and nested cross-validation were used to train and validate diagnostic models differentiating BD from MDD in participants who self-reported a current MDD diagnosis. Mean test area under the receiver operating characteristic curve (AUROC) for separating participants with BD diagnosed as MDD (N = 126) from those with correct MDD diagnosis (N = 187) was 0.92 (95% CI: 0.86-0.97). Core predictors included elevated mood, grandiosity, talkativeness, recklessness and risky behaviour. Additional validation in participants with no previous mood disorder diagnosis showed AUROCs of 0.89 (0.86-0.91) and 0.90 (0.87-0.91) for separating newly diagnosed BD (N = 98) from MDD (N = 112) and subclinical low mood (N = 120), respectively. Validation in participants with a previous diagnosis of BD (N = 45) demonstrated sensitivity of 0.86 (0.57-0.96). The diagnostic algorithm accurately identified patients with BD in various clinical scenarios, and could help expedite accurate clinical diagnosis and treatment of BD.