Creighton Heaukulani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Creighton Heaukulani has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
- Robert J. T. Morris
Office for Healthcare Transformation, Ministry of Health, Singapore, Singapore
11 shared publications - Jimmy Lee
Institute of Mental Health, Singapore
5 shared publications - Ye Sheng Phang
MOH Office for Healthcare Transformation, Singapore, Singapore
5 shared publications - Thisum Buddhika
MOH Office for Healthcare Transformation
4 shared publications - Wijaya Martanto
MOH Office for Healthcare Transformation Singapore Singapore
4 shared publications - Janice Huiqin Weng
MOH Office for Healthcare Transformation, Singapore, Singapore
3 shared publications
Latest Publications
- Open Access
- 8 February 2026
- Published by JMIR Publications Inc. in JMIR Preprints
The let’s talk Digital Peer Support Forum for Youth Mental Health and Wellbeing in Singapore: A Three-Year Process Evaluation and Framework Description (Preprint)
BACKGROUND Many countries face challenges in youth mental health, including stigma around help-seeking, limited accessibility to services, and undersupply of trained professionals. Online peer support platforms show promise in addressing these barriers. A government-supported platform called let’s talk launched in Singapore in 2022 to support youth aged 17-35. The anonymous and moderated forum allows youth to discuss mental health topics and life challenges with peers, peer supporters, and professionals. OBJECTIVE The objectives are to (1) describe the design framework for let’s talk, including its Theory of Change; (2) conduct a process evaluation on data collected over the first three years of operation; and (3) summarize and discuss our learnings. The findings provide a replicable framework that may guide the design of similar platforms and inform impact evaluation studies. METHODS Key features of let’s talk include co-development with youths and mental health professionals, anonymity, trust and safety through moderation and government endorsement, and five dedicated pathways for key user journeys. Most notably, the Ask-A-Therapist pathway provides access to professional support on the forum and the Peer Supporter pathway trains and empowers youths to provide meaningful support to their peers. Process evaluation data were collected from 1 July 2022 to 30 June 2025. We analyzed platform-wide and feature-specific reach, engagement, and growth metrics by year. We documented learnings from implementation described by the platform development team. RESULTS In its first three years, let’s talk received an estimated 51,636 non-bounced (meaningful activity) visitors, representing 5.2% of the platform’s target population of 17–35-year-olds in Singapore. In total, 17,158 users (33.2% of non-bounced visitors) created an account and 3,489 (20.3%) of those users posted at least once. The most popular feature of the platform was Ask-A-Therapist, which saw 1,548 original (thread-starting) questions posted from 1,037 unique users and a total of 6,865 posts (61.9% of all posting activity). The 156 Peer Supporters were the most active users, representing 0.9% of all registered users yet contributing 2,175 posts (19.6% of all posting activity). The let’s talk features aiming to bridge the online-offline divide and to encourage self-care training were not popularly used. Engagement patterns revealed that professionally-moderated peer support and direct access to professionals were the primary drivers of sustained use, while features promoting self-directed activities had limited uptake. CONCLUSIONS let’s talk achieved meaningful reach (5.2% of target population) and engagement through two key design principles: (1) low-barrier access to professional support via Ask-A-Therapist, and (2) training and empowering peer supporters as highly engaged community leaders. Our findings suggest that the core value proposition of platforms like let’s talk is human connection and expert guidance. Our framework and implementation learnings provide practical guidance for adapting this model to diverse cultural contexts.
- 8 February 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessThe let’s talk Digital Peer Support Forum for Youth Mental Health and Wellbeing in Singapore: A Three-Year Process Evaluation and Framework Description (Preprint)
BACKGROUND Many countries face challenges in youth mental health, including stigma around help-seeking, limited accessibility to services, and undersupply of trained professionals. Online peer support platforms show promise in addressing these barriers. A government-supported platform called let’s talk launched in Singapore in 2022 to support youth aged 17-35. The anonymous and moderated forum allows youth to discuss mental health topics and life challenges with peers, peer supporters, and professionals. OBJECTIVE The objectives are to (1) describe the design framework for let’s talk, including its Theory of Change; (2) conduct a process evaluation on data collected over the first three years of operation; and (3) summarize and discuss our learnings. The findings provide a replicable framework that may guide the design of similar platforms and inform impact evaluation studies. METHODS Key features of let’s talk include co-development with youths and mental health professionals, anonymity, trust and safety through moderation and government endorsement, and five dedicated pathways for key user journeys. Most notably, the Ask-A-Therapist pathway provides access to professional support on the forum and the Peer Supporter pathway trains and empowers youths to provide meaningful support to their peers. Process evaluation data were collected from 1 July 2022 to 30 June 2025. We analyzed platform-wide and feature-specific reach, engagement, and growth metrics by year. We documented learnings from implementation described by the platform development team. RESULTS In its first three years, let’s talk received an estimated 51,636 non-bounced (meaningful activity) visitors, representing 5.2% of the platform’s target population of 17–35-year-olds in Singapore. In total, 17,158 users (33.2% of non-bounced visitors) created an account and 3,489 (20.3%) of those users posted at least once. The most popular feature of the platform was Ask-A-Therapist, which saw 1,548 original (thread-starting) questions posted from 1,037 unique users and a total of 6,865 posts (61.9% of all posting activity). The 156 Peer Supporters were the most active users, representing 0.9% of all registered users yet contributing 2,175 posts (19.6% of all posting activity). The let’s talk features aiming to bridge the online-offline divide and to encourage self-care training were not popularly used. Engagement patterns revealed that professionally-moderated peer support and direct access to professionals were the primary drivers of sustained use, while features promoting self-directed activities had limited uptake. CONCLUSIONS let’s talk achieved meaningful reach (5.2% of target population) and engagement through two key design principles: (1) low-barrier access to professional support via Ask-A-Therapist, and (2) training and empowering peer supporters as highly engaged community leaders. Our findings suggest that the core value proposition of platforms like let’s talk is human connection and expert guidance. Our framework and implementation learnings provide practical guidance for adapting this model to diverse cultural contexts.
- Open Access
- 5 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
A Unified Strategy for an Agentic Artificial Intelligence (AI)-assisted Clinical Decision Support (CDS) System for Primary Care: A Mixed-Method Study in Singapore (Preprint)
BACKGROUND Primary care providers (PCPs) must consolidate diverse sources of data (clinical, laboratory, administrative etc.) to make clinical decisions. As these sense-making tasks become increasingly challenging, artificial intelligence (AI) offer potential to prioritise guideline-recommended tasks based on clinical benefit. OBJECTIVE To demonstrate a participatory approach to the conception, design, and development of such AI-assisted clinical decision support (CDS) systems for primary care. METHODS A mixed methods study was performed, including in-clinic observations at primary care clinics and a focus group involving 20 PCPs in Singapore. The design thinking double diamond process model was applied to define care delivery challenges and conceptualise digital tools. Participants periodically evaluated data saturation, defined as saturation ratio <5% on two consecutive occasions. RESULTS In-clinic observations produced a patient journey map (Figure 1) highlighting current workflows, data sources and challenges. PCPs described consolidating patients’ medical records, presenting complaint, financial and sociobehavioral considerations before formulating a management plan based on multiple guidelines and the latest literature. PCPs also reported that core challenges included rapid guideline adaptation, repeated manual entry across multiple systems, complex claims processes, and limited patient health ownership (Figure 3). Participants further conceived AI tools that could automate eligibility checks for recommended interventions (e.g. screening and vaccinations), deliver just-in-time reminders at the point-of-care, consolidate actionable sociobehavioral data, contextualise relevant literature, and develop personalised risk-based action lists (Figure 5). CONCLUSIONS This study describes Singapore’s primary care delivery challenges and identifies parallels from international reports in the United States and Europe. Key providers’ considerations for AI-assisted CDS tools to best support care delivery are described. Additional findings include provider concerns over AI-scribes, highlighting a need for robust evaluation and privacy-preserving approaches. A blended implementation strategy for developed countries was developed using AI agents to aggregate and analyse data, suggest “next best action” lists, and prioritise recommended tasks based on AI-predicted health benefit.
- 5 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA Unified Strategy for an Agentic Artificial Intelligence (AI)-assisted Clinical Decision Support (CDS) System for Primary Care: A Mixed-Method Study in Singapore (Preprint)
BACKGROUND Primary care providers (PCPs) must consolidate diverse sources of data (clinical, laboratory, administrative etc.) to make clinical decisions. As these sense-making tasks become increasingly challenging, artificial intelligence (AI) offer potential to prioritise guideline-recommended tasks based on clinical benefit. OBJECTIVE To demonstrate a participatory approach to the conception, design, and development of such AI-assisted clinical decision support (CDS) systems for primary care. METHODS A mixed methods study was performed, including in-clinic observations at primary care clinics and a focus group involving 20 PCPs in Singapore. The design thinking double diamond process model was applied to define care delivery challenges and conceptualise digital tools. Participants periodically evaluated data saturation, defined as saturation ratio <5% on two consecutive occasions. RESULTS In-clinic observations produced a patient journey map (Figure 1) highlighting current workflows, data sources and challenges. PCPs described consolidating patients’ medical records, presenting complaint, financial and sociobehavioral considerations before formulating a management plan based on multiple guidelines and the latest literature. PCPs also reported that core challenges included rapid guideline adaptation, repeated manual entry across multiple systems, complex claims processes, and limited patient health ownership (Figure 3). Participants further conceived AI tools that could automate eligibility checks for recommended interventions (e.g. screening and vaccinations), deliver just-in-time reminders at the point-of-care, consolidate actionable sociobehavioral data, contextualise relevant literature, and develop personalised risk-based action lists (Figure 5). CONCLUSIONS This study describes Singapore’s primary care delivery challenges and identifies parallels from international reports in the United States and Europe. Key providers’ considerations for AI-assisted CDS tools to best support care delivery are described. Additional findings include provider concerns over AI-scribes, highlighting a need for robust evaluation and privacy-preserving approaches. A blended implementation strategy for developed countries was developed using AI agents to aggregate and analyse data, suggest “next best action” lists, and prioritise recommended tasks based on AI-predicted health benefit.
- Open Access
Harnessing Digital Phenotyping to Advance University Student Mental Health (Brightline): Study Protocol for a Prospective Observational Study
Introduction: Mental health issues such as depression and anxiety are highly and disproportionally prevalent among university students. Beyond the academic rigor, stressors imposed by a new environment result in them being vulnerable to the onset and manifestation of mental health symptomatology. Leveraging smartphones and wearables for digital phenotyping capabilities is an innovative approach for monitoring and intervening in the mental health conditions of university students. This provides a unique opportunity to collect and identify digital and behavioral biomarkers, subsequently enabling the development of predictive models to identify university students at risk. Methods and analysis: This study — Brightline— will employ an observational study design over a 6-month period, recruiting 500 students from a major public university in Singapore. Passive data collection will occur continuously throughout the monitoring period through a wearable device (Fitbit Charge 6) and smartphone sensors via the Brightline app, which utilizes a digital phenotyping data collection platform. Active data collection will consist of self-report questionnaires to be completed at the beginning of the study and follow-up assessments at one, three, and six months after. The passive and active data collected will be analyzed to identify the digital biomarkers associated with depression, anxiety, stress, loneliness, and affect among university students. Predictive models of these mental health issues will also be developed. Ethics and dissemination: This study was approved by the Nanyang Technological University Institutional Review Board (IRB-2023-894). Findings from this study will be published in peer-reviewed journals and presented at academic conferences. Trial registration: NCT06770075. Strengths and limitations of this study: Brightline is a large-scale longitudinal study that aims to examine the mental health of university students over time using smartphones and wearables. This study has significant clinical implications, offering insights into the early warning signs and trajectories of university student’s mental health. These findings may inform the development of personalized and preventative interventions for integration into university mental health services. Challenges in adhering to active and passive data collection may lead to missing data and participant dropout, potentially affecting the development of predictive models.
Open AccessHarnessing Digital Phenotyping to Advance University Student Mental Health (Brightline): Study Protocol for a Prospective Observational Study
Introduction: Mental health issues such as depression and anxiety are highly and disproportionally prevalent among university students. Beyond the academic rigor, stressors imposed by a new environment result in them being vulnerable to the onset and manifestation of mental health symptomatology. Leveraging smartphones and wearables for digital phenotyping capabilities is an innovative approach for monitoring and intervening in the mental health conditions of university students. This provides a unique opportunity to collect and identify digital and behavioral biomarkers, subsequently enabling the development of predictive models to identify university students at risk. Methods and analysis: This study — Brightline— will employ an observational study design over a 6-month period, recruiting 500 students from a major public university in Singapore. Passive data collection will occur continuously throughout the monitoring period through a wearable device (Fitbit Charge 6) and smartphone sensors via the Brightline app, which utilizes a digital phenotyping data collection platform. Active data collection will consist of self-report questionnaires to be completed at the beginning of the study and follow-up assessments at one, three, and six months after. The passive and active data collected will be analyzed to identify the digital biomarkers associated with depression, anxiety, stress, loneliness, and affect among university students. Predictive models of these mental health issues will also be developed. Ethics and dissemination: This study was approved by the Nanyang Technological University Institutional Review Board (IRB-2023-894). Findings from this study will be published in peer-reviewed journals and presented at academic conferences. Trial registration: NCT06770075. Strengths and limitations of this study: Brightline is a large-scale longitudinal study that aims to examine the mental health of university students over time using smartphones and wearables. This study has significant clinical implications, offering insights into the early warning signs and trajectories of university student’s mental health. These findings may inform the development of personalized and preventative interventions for integration into university mental health services. Challenges in adhering to active and passive data collection may lead to missing data and participant dropout, potentially affecting the development of predictive models.
- Open Access
- 5 February 2025
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 13 (1) , e56185
Utility of Digital Phenotyping Based on Wrist Wearables and Smartphones in Psychosis: Observational Study
Background: Digital phenotyping provides insights into an individual’s digital behaviors and has potential clinical utility. Objective: In this observational study, we explored digital biomarkers collected from wrist-wearable devices and smartphones and their associations with clinical symptoms and functioning in patients with schizophrenia. Methods: We recruited 100 outpatients with schizophrenia spectrum disorder, and we collected various digital data from commercially available wrist wearables and smartphones over a 6-month period. In this report, we analyzed the first week of digital data on heart rate, sleep, and physical activity from the wrist wearables and travel distance, sociability, touchscreen tapping speed, and screen time from the smartphones. We analyzed the relationships between these digital measures and patient baseline measurements of clinical symptoms assessed with the Positive and Negative Syndrome Scale, Brief Negative Symptoms Scale, and Calgary Depression Scale for Schizophrenia, as well as functioning as assessed with the Social and Occupational Functioning Assessment Scale. Linear regression was performed for each digital and clinical measure independently, with the digital measures being treated as predictors. Results: Digital data were successfully collected from both the wearables and smartphones throughout the study, with 91% of the total possible data successfully collected from the wearables and 82% from the smartphones during the first week of the trial—the period under analysis in this report. Among the clinical outcomes, negative symptoms were associated with the greatest number of digital measures (10 of the 12 studied here), followed by overall measures of psychopathology symptoms, functioning, and positive symptoms, which were each associated with at least 3 digital measures. Cognition and cognitive/disorganization symptoms were each associated with 1 or 2 digital measures. Conclusions: We found significant associations between nearly all digital measures and a wide range of symptoms and functioning in a community sample of individuals with schizophrenia. These findings provide insights into the digital behaviors of individuals with schizophrenia and highlight the potential of using commercially available wrist wearables and smartphones for passive monitoring in schizophrenia.
- 5 February 2025
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 13 (1) , e56185
Open AccessUtility of Digital Phenotyping Based on Wrist Wearables and Smartphones in Psychosis: Observational Study
Background: Digital phenotyping provides insights into an individual’s digital behaviors and has potential clinical utility. Objective: In this observational study, we explored digital biomarkers collected from wrist-wearable devices and smartphones and their associations with clinical symptoms and functioning in patients with schizophrenia. Methods: We recruited 100 outpatients with schizophrenia spectrum disorder, and we collected various digital data from commercially available wrist wearables and smartphones over a 6-month period. In this report, we analyzed the first week of digital data on heart rate, sleep, and physical activity from the wrist wearables and travel distance, sociability, touchscreen tapping speed, and screen time from the smartphones. We analyzed the relationships between these digital measures and patient baseline measurements of clinical symptoms assessed with the Positive and Negative Syndrome Scale, Brief Negative Symptoms Scale, and Calgary Depression Scale for Schizophrenia, as well as functioning as assessed with the Social and Occupational Functioning Assessment Scale. Linear regression was performed for each digital and clinical measure independently, with the digital measures being treated as predictors. Results: Digital data were successfully collected from both the wearables and smartphones throughout the study, with 91% of the total possible data successfully collected from the wearables and 82% from the smartphones during the first week of the trial—the period under analysis in this report. Among the clinical outcomes, negative symptoms were associated with the greatest number of digital measures (10 of the 12 studied here), followed by overall measures of psychopathology symptoms, functioning, and positive symptoms, which were each associated with at least 3 digital measures. Cognition and cognitive/disorganization symptoms were each associated with 1 or 2 digital measures. Conclusions: We found significant associations between nearly all digital measures and a wide range of symptoms and functioning in a community sample of individuals with schizophrenia. These findings provide insights into the digital behaviors of individuals with schizophrenia and highlight the potential of using commercially available wrist wearables and smartphones for passive monitoring in schizophrenia.
- Open Access
- 23 December 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26, e55924
Characteristics and Outcomes of mHealth Interventions in Psychosis: Systematic Mapping Review
Background: Mobile health (mHealth) interventions have gained popularity in augmenting psychiatric care for adults with psychosis. Interest has grown in leveraging mHealth to empower individuals living with severe mental illness and extend continuity of care beyond the hospital to the community. However, reported outcomes have been mixed, likely attributed in part to the intervention and adopted outcomes, which affected between-study comparisons. Objective: This study aimed to critically review outcome measures used to evaluate mHealth interventions for adults with psychosis in relation to the characteristics of mHealth interventions. Methods: A systematic mapping review was conducted. We searched PubMed, CINAHL, Embase, PsycINFO, and Cochrane Libraries from 1973 to the present. Selection criteria included randomized controlled studies of mHealth interventions in adults diagnosed with schizophrenia spectrum disorders. Reviewers worked in pairs to screen and extract data from included studies independently using a standardized form; disagreements were resolved by consensus with an independent reviewer. We report our findings in line with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Results: A total of 1703 citations were screened; 29 publications reporting on 23 studies were included in this review. mHealth interventions for psychosis span a wide range, with psychological therapy being the most-deployed intervention (12/23, 52%), followed by psychoeducation (8/23, 35%) and active self-monitoring (8/23, 35%). Several mHealth interventions for psychosis targeted multiple pillars of biopsychosocial well-being (10/23, 43%); the bulk of interventions (16/23, 70%) incorporated features promoting users’ self-management. The majority of mHealth interventions were delivered through applications (14/23, 61%) as the main medium and smartphones (17/23, 74%) as the main channel of delivery. Interventions were primarily administered in the outpatient and community settings (16/23, 70%); many were also blended with in-person sessions (11/23, 48%) or guided remotely (6/23, 26%) by persons, including health care providers or trained peer supporters. The severity of psychosis-related symptoms (21/23, 91%) was the most prevalent outcome, of which positive symptoms (13/23, 57%), mood and anxiety (10/23, 43%), and overall psychopathology severity (9/23, 39%) were most commonly measured. Patient-centric outcomes, including well-being (17/23, 74%)—particularly quality of life (10/23, 43%)—and user experience (15/23, 65%), including feasibility (7/23, 30%), acceptability (7/23, 30%), and engagement (7/23, 26%). Notably, outcome choices remained diverse despite stratification by type of mHealth intervention. Conclusions: mHealth interventions for psychosis encompass a wide range of modalities and use outcome measures that probe various social and behavioral determinants of health. These should be considered complex interventions, and a holistic evaluation approach combining clinical and patient-centric outcomes is recommended.
- 23 December 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26, e55924
Open AccessCharacteristics and Outcomes of mHealth Interventions in Psychosis: Systematic Mapping Review
Background: Mobile health (mHealth) interventions have gained popularity in augmenting psychiatric care for adults with psychosis. Interest has grown in leveraging mHealth to empower individuals living with severe mental illness and extend continuity of care beyond the hospital to the community. However, reported outcomes have been mixed, likely attributed in part to the intervention and adopted outcomes, which affected between-study comparisons. Objective: This study aimed to critically review outcome measures used to evaluate mHealth interventions for adults with psychosis in relation to the characteristics of mHealth interventions. Methods: A systematic mapping review was conducted. We searched PubMed, CINAHL, Embase, PsycINFO, and Cochrane Libraries from 1973 to the present. Selection criteria included randomized controlled studies of mHealth interventions in adults diagnosed with schizophrenia spectrum disorders. Reviewers worked in pairs to screen and extract data from included studies independently using a standardized form; disagreements were resolved by consensus with an independent reviewer. We report our findings in line with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Results: A total of 1703 citations were screened; 29 publications reporting on 23 studies were included in this review. mHealth interventions for psychosis span a wide range, with psychological therapy being the most-deployed intervention (12/23, 52%), followed by psychoeducation (8/23, 35%) and active self-monitoring (8/23, 35%). Several mHealth interventions for psychosis targeted multiple pillars of biopsychosocial well-being (10/23, 43%); the bulk of interventions (16/23, 70%) incorporated features promoting users’ self-management. The majority of mHealth interventions were delivered through applications (14/23, 61%) as the main medium and smartphones (17/23, 74%) as the main channel of delivery. Interventions were primarily administered in the outpatient and community settings (16/23, 70%); many were also blended with in-person sessions (11/23, 48%) or guided remotely (6/23, 26%) by persons, including health care providers or trained peer supporters. The severity of psychosis-related symptoms (21/23, 91%) was the most prevalent outcome, of which positive symptoms (13/23, 57%), mood and anxiety (10/23, 43%), and overall psychopathology severity (9/23, 39%) were most commonly measured. Patient-centric outcomes, including well-being (17/23, 74%)—particularly quality of life (10/23, 43%)—and user experience (15/23, 65%), including feasibility (7/23, 30%), acceptability (7/23, 30%), and engagement (7/23, 26%). Notably, outcome choices remained diverse despite stratification by type of mHealth intervention. Conclusions: mHealth interventions for psychosis encompass a wide range of modalities and use outcome measures that probe various social and behavioral determinants of health. These should be considered complex interventions, and a holistic evaluation approach combining clinical and patient-centric outcomes is recommended.
- Open Access
- 17 August 2024
- Published by BMJ in BMJ Health & Care Informatics
- Vol. 31 (1) , e101045-12
User perceptions and utilisation of features of an AI-enabled workplace digital mental wellness platform ‘mindline at work’
Background: The working population encounters unique work-related stressors. Despite these challenges, accessibility to mental healthcare remains limited. Digital technology-enabled mental wellness tools can offer much-needed access to mental healthcare. However, existing literature has given limited attention to their relevance and user engagement, particularly for the working population.Aim: This study aims to assess user perceptions and feature utilisation ofmindline at work, a nationally developed AI-enabled digital platform designed to improve mental wellness in the working population.Methods: This study adopted a mixed-methods design comprising a survey (n=399) and semistructured interviews (n=40) with office-based working adults. Participants were asked to usemindline at workfor 4 weeks. We collected data about utilisation of the platform features, intention for sustained use and perceptions of specific features.Results: Participants under 5 years of work experience reported lower utilisation of multimedia resources but higher utilisation of emotion self-assessment tools and the AI chatbot compared with their counterparts (pmindline at workas an ‘essential’ safeguard against workplace stress, valuing its secure and non-judgmental space and user anonymity. However, they wanted greater institutional support for office workers’ mental wellness to enhance the uptake. The AI chatbot was perceived as useful for self-reflection and problem-solving, despite limited maturity.Conclusion: Identifying the unique benefits of specific features for different segments of working adults can foster a personalised user experience and promote mental well-being. Increasing workplace awareness is essential for platform adoption.
- 17 August 2024
- Published by BMJ in BMJ Health & Care Informatics
- Vol. 31 (1) , e101045-12
Open AccessUser perceptions and utilisation of features of an AI-enabled workplace digital mental wellness platform ‘mindline at work’
Background: The working population encounters unique work-related stressors. Despite these challenges, accessibility to mental healthcare remains limited. Digital technology-enabled mental wellness tools can offer much-needed access to mental healthcare. However, existing literature has given limited attention to their relevance and user engagement, particularly for the working population.Aim: This study aims to assess user perceptions and feature utilisation ofmindline at work, a nationally developed AI-enabled digital platform designed to improve mental wellness in the working population.Methods: This study adopted a mixed-methods design comprising a survey (n=399) and semistructured interviews (n=40) with office-based working adults. Participants were asked to usemindline at workfor 4 weeks. We collected data about utilisation of the platform features, intention for sustained use and perceptions of specific features.Results: Participants under 5 years of work experience reported lower utilisation of multimedia resources but higher utilisation of emotion self-assessment tools and the AI chatbot compared with their counterparts (pmindline at workas an ‘essential’ safeguard against workplace stress, valuing its secure and non-judgmental space and user anonymity. However, they wanted greater institutional support for office workers’ mental wellness to enhance the uptake. The AI chatbot was perceived as useful for self-reflection and problem-solving, despite limited maturity.Conclusion: Identifying the unique benefits of specific features for different segments of working adults can foster a personalised user experience and promote mental well-being. Increasing workplace awareness is essential for platform adoption.
- Open Access
- 4 June 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e44443
Mental Wellness Self-Care in Singapore With mindline.sg: A Tutorial on the Development of a Digital Mental Health Platform for Behavior Change
Background: Singapore, like the rest of Asia, faces persistent challenges to mental health promotion, including stigma around unwellness and seeking treatment and a lack of trained mental health personnel. The COVID-19 pandemic, which created a surge in mental health care needs and simultaneously accelerated the adoption of digital health solutions, revealed a new opportunity to quickly scale innovative solutions in the region. Objective: In June 2020, the Singaporean government launched mindline.sg, an anonymous digital mental health resource website that has grown to include >500 curated local mental health resources, a clinically validated self-assessment tool for depression and anxiety, an artificial intelligence (AI) chatbot from Wysa designed to deliver digital therapeutic exercises, and a tailored version of the website for working adults called mindline at work. The goal of the platform is to empower Singapore residents to take charge of their own mental health and to be able to offer basic support to those around them through the ease and convenience of a barrier-free digital solution. Methods: Website use is measured through click-level data analytics captured via Google Analytics and custom application programming interfaces, which in turn drive a customized analytics infrastructure based on the open-source platforms Titanium Database and Metabase. Unique, nonbounced (users that do not immediately navigate away from the site), engaged, and return users are reported. Results: In the 2 years following launch (July 1, 2020, through June 30, 2022), the website received >447,000 visitors (approximately 15% of the target population of 3 million), 62.02% (277,727/447,783) of whom explored the site or engaged with resources (referred to as nonbounced visitors); 10.54% (29,271/277,727) of those nonbounced visitors returned. The most popular features on the platform were the dialogue-based therapeutic exercises delivered by the chatbot and the self-assessment tool, which were used by 25.54% (67,626/264,758) and 11.69% (32,469/277,727) of nonbounced visitors. On mindline at work, the rates of nonbounced visitors who engaged extensively (ie, spent ≥40 seconds exploring resources) and who returned were 51.56% (22,474/43,588) and 13.43% (5,853/43,588) over a year, respectively, compared to 30.9% (42,829/138,626) and 9.97% (13,822/138,626), respectively, on the generic mindline.sg site in the same year. Conclusions: The site has achieved desired reach and has seen a strong growth rate in the number of visitors, which required substantial and sustained digital marketing campaigns and strategic outreach partnerships. The site was careful to preserve anonymity, limiting the detail of analytics. The good levels of overall adoption encourage us to believe that mild to moderate mental health conditions and the social factors that underly them are amenable to digital interventions. While mindline.sg was primarily used in Singapore, we believe that similar solutions with local customization are widely and globally applicable.
- 4 June 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e44443
Open AccessMental Wellness Self-Care in Singapore With mindline.sg: A Tutorial on the Development of a Digital Mental Health Platform for Behavior Change
Background: Singapore, like the rest of Asia, faces persistent challenges to mental health promotion, including stigma around unwellness and seeking treatment and a lack of trained mental health personnel. The COVID-19 pandemic, which created a surge in mental health care needs and simultaneously accelerated the adoption of digital health solutions, revealed a new opportunity to quickly scale innovative solutions in the region. Objective: In June 2020, the Singaporean government launched mindline.sg, an anonymous digital mental health resource website that has grown to include >500 curated local mental health resources, a clinically validated self-assessment tool for depression and anxiety, an artificial intelligence (AI) chatbot from Wysa designed to deliver digital therapeutic exercises, and a tailored version of the website for working adults called mindline at work. The goal of the platform is to empower Singapore residents to take charge of their own mental health and to be able to offer basic support to those around them through the ease and convenience of a barrier-free digital solution. Methods: Website use is measured through click-level data analytics captured via Google Analytics and custom application programming interfaces, which in turn drive a customized analytics infrastructure based on the open-source platforms Titanium Database and Metabase. Unique, nonbounced (users that do not immediately navigate away from the site), engaged, and return users are reported. Results: In the 2 years following launch (July 1, 2020, through June 30, 2022), the website received >447,000 visitors (approximately 15% of the target population of 3 million), 62.02% (277,727/447,783) of whom explored the site or engaged with resources (referred to as nonbounced visitors); 10.54% (29,271/277,727) of those nonbounced visitors returned. The most popular features on the platform were the dialogue-based therapeutic exercises delivered by the chatbot and the self-assessment tool, which were used by 25.54% (67,626/264,758) and 11.69% (32,469/277,727) of nonbounced visitors. On mindline at work, the rates of nonbounced visitors who engaged extensively (ie, spent ≥40 seconds exploring resources) and who returned were 51.56% (22,474/43,588) and 13.43% (5,853/43,588) over a year, respectively, compared to 30.9% (42,829/138,626) and 9.97% (13,822/138,626), respectively, on the generic mindline.sg site in the same year. Conclusions: The site has achieved desired reach and has seen a strong growth rate in the number of visitors, which required substantial and sustained digital marketing campaigns and strategic outreach partnerships. The site was careful to preserve anonymity, limiting the detail of analytics. The good levels of overall adoption encourage us to believe that mild to moderate mental health conditions and the social factors that underly them are amenable to digital interventions. While mindline.sg was primarily used in Singapore, we believe that similar solutions with local customization are widely and globally applicable.
- Open Access
- 7 January 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Characteristics and Outcomes of mHealth Interventions in Psychosis: Systematic Mapping Review (Preprint)
BACKGROUND Mobile health (mHealth) interventions have gained popularity in augmenting psychiatric care for adults with psychosis. Interest has grown in leveraging mHealth to empower individuals living with severe mental illness and extend continuity of care beyond the hospital to the community. However, reported outcomes have been mixed, likely attributed in part to the intervention and adopted outcomes, which affected between-study comparisons. OBJECTIVE This study aimed to critically review outcome measures used to evaluate mHealth interventions for adults with psychosis in relation to the characteristics of mHealth interventions. METHODS A systematic mapping review was conducted. We searched PubMed, CINAHL, Embase, PsycINFO, and Cochrane Libraries from 1973 to the present. Selection criteria included randomized controlled studies of mHealth interventions in adults diagnosed with schizophrenia spectrum disorders. Reviewers worked in pairs to screen and extract data from included studies independently using a standardized form; disagreements were resolved by consensus with an independent reviewer. We report our findings in line with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. RESULTS A total of 1703 citations were screened; 29 publications reporting on 23 studies were included in this review. mHealth interventions for psychosis span a wide range, with psychological therapy being the most-deployed intervention (12/23, 52%), followed by psychoeducation (8/23, 35%) and active self-monitoring (8/23, 35%). Several mHealth interventions for psychosis targeted multiple pillars of biopsychosocial well-being (10/23, 43%); the bulk of interventions (16/23, 70%) incorporated features promoting users’ self-management. The majority of mHealth interventions were delivered through applications (14/23, 61%) as the main medium and smartphones (17/23, 74%) as the main channel of delivery. Interventions were primarily administered in the outpatient and community settings (16/23, 70%); many were also blended with in-person sessions (11/23, 48%) or guided remotely (6/23, 26%) by persons, including health care providers or trained peer supporters. The severity of psychosis-related symptoms (21/23, 91%) was the most prevalent outcome, of which positive symptoms (13/23, 57%), mood and anxiety (10/23, 43%), and overall psychopathology severity (9/23, 39%) were most commonly measured. Patient-centric outcomes, including well-being (17/23, 74%)—particularly quality of life (10/23, 43%)—and user experience (15/23, 65%), including feasibility (7/23, 30%), acceptability (7/23, 30%), and engagement (7/23, 26%). Notably, outcome choices remained diverse despite stratification by type of mHealth intervention. CONCLUSIONS mHealth interventions for psychosis encompass a wide range of modalities and use outcome measures that probe various social and behavioral determinants of health. These should be considered complex interventions, and a holistic evaluation approach combining clinical and patient-centric outcomes is recommended.
- 7 January 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessCharacteristics and Outcomes of mHealth Interventions in Psychosis: Systematic Mapping Review (Preprint)
BACKGROUND Mobile health (mHealth) interventions have gained popularity in augmenting psychiatric care for adults with psychosis. Interest has grown in leveraging mHealth to empower individuals living with severe mental illness and extend continuity of care beyond the hospital to the community. However, reported outcomes have been mixed, likely attributed in part to the intervention and adopted outcomes, which affected between-study comparisons. OBJECTIVE This study aimed to critically review outcome measures used to evaluate mHealth interventions for adults with psychosis in relation to the characteristics of mHealth interventions. METHODS A systematic mapping review was conducted. We searched PubMed, CINAHL, Embase, PsycINFO, and Cochrane Libraries from 1973 to the present. Selection criteria included randomized controlled studies of mHealth interventions in adults diagnosed with schizophrenia spectrum disorders. Reviewers worked in pairs to screen and extract data from included studies independently using a standardized form; disagreements were resolved by consensus with an independent reviewer. We report our findings in line with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. RESULTS A total of 1703 citations were screened; 29 publications reporting on 23 studies were included in this review. mHealth interventions for psychosis span a wide range, with psychological therapy being the most-deployed intervention (12/23, 52%), followed by psychoeducation (8/23, 35%) and active self-monitoring (8/23, 35%). Several mHealth interventions for psychosis targeted multiple pillars of biopsychosocial well-being (10/23, 43%); the bulk of interventions (16/23, 70%) incorporated features promoting users’ self-management. The majority of mHealth interventions were delivered through applications (14/23, 61%) as the main medium and smartphones (17/23, 74%) as the main channel of delivery. Interventions were primarily administered in the outpatient and community settings (16/23, 70%); many were also blended with in-person sessions (11/23, 48%) or guided remotely (6/23, 26%) by persons, including health care providers or trained peer supporters. The severity of psychosis-related symptoms (21/23, 91%) was the most prevalent outcome, of which positive symptoms (13/23, 57%), mood and anxiety (10/23, 43%), and overall psychopathology severity (9/23, 39%) were most commonly measured. Patient-centric outcomes, including well-being (17/23, 74%)—particularly quality of life (10/23, 43%)—and user experience (15/23, 65%), including feasibility (7/23, 30%), acceptability (7/23, 30%), and engagement (7/23, 26%). Notably, outcome choices remained diverse despite stratification by type of mHealth intervention. CONCLUSIONS mHealth interventions for psychosis encompass a wide range of modalities and use outcome measures that probe various social and behavioral determinants of health. These should be considered complex interventions, and a holistic evaluation approach combining clinical and patient-centric outcomes is recommended.
- Open Access
- 21 August 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Examining a Brief Web and Longitudinal App-Based Intervention [Wysa] for Mental Health Support in Singapore during the COVID-19 Pandemic: Mixed-Methods Retrospective Observational Study (Preprint)
BACKGROUND The COVID-19 pandemic in Singapore led to limited access to mental health support services, resulting in increased distress among the population. This study aimed to assess the potential benefits of offering a digital mental health intervention (Wysa) in the form of a brief and longitudinal intervention, as part of the mindline.sg initiative launched by the MOH Office for Healthcare Transformation in Singapore. OBJECTIVE i) Evaluate the engagement and retention of Singaporean users across the brief intervention on the mindline.sg website and the longitudinal app version of Wysa; ii) Examine the types of negative thoughts and challenges managed during the pandemic; iii) Assess the impact of the conversational agent (CA) in supporting cognitive restructuring across attributional styles, and cognitive patterns. METHODS A retrospective observational design with a mixed-methods approach was utilized. The study included a sample of website users (N=69,055) and app users (N=4,547) from September 1, 2020, to July 25, 2022. App and website usage data were analyzed to evaluate engagement and retention. T-tests were employed for comparing engagement and retention levels between the app and website. A thematic analysis was examined to assess the types of negative thoughts and the success of cognitive restructuring. Logistic regression was used to estimate the likelihood of restructuring based on negative thought type and attributional style. RESULTS Those who used the longitudinal intervention after first using a brief intervention demonstrated significantly higher engagement and retention (P<.001). In user ratings received for mindline.sg (n=8,959), 83.03% rated the app 3 or higher (out of 5) on helpfulness. 91.6% of the users (n=862) who attempted cognitive restructuring (n=790) on the app successfully reframed a thought. The logistic regression analysis indicated significance in the ability to restructure future-oriented negative thoughts (P<.001), and internal, stable and global (P<.001) negative thoughts in a single conversation with Wysa, while other attributional styles required more intervention. A qualitative thematic analysis of the negative thoughts mentioned within the CA documented the psychosocial challenges being managed by users during COVID-19. CONCLUSIONS The findings demonstrated that brief interventions can facilitate enhanced engagement with digital mental health interventions and digital interventions can successfully facilitate cognitive restructuring, and improvement of mental health outcomes.
- 21 August 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessExamining a Brief Web and Longitudinal App-Based Intervention [Wysa] for Mental Health Support in Singapore during the COVID-19 Pandemic: Mixed-Methods Retrospective Observational Study (Preprint)
BACKGROUND The COVID-19 pandemic in Singapore led to limited access to mental health support services, resulting in increased distress among the population. This study aimed to assess the potential benefits of offering a digital mental health intervention (Wysa) in the form of a brief and longitudinal intervention, as part of the mindline.sg initiative launched by the MOH Office for Healthcare Transformation in Singapore. OBJECTIVE i) Evaluate the engagement and retention of Singaporean users across the brief intervention on the mindline.sg website and the longitudinal app version of Wysa; ii) Examine the types of negative thoughts and challenges managed during the pandemic; iii) Assess the impact of the conversational agent (CA) in supporting cognitive restructuring across attributional styles, and cognitive patterns. METHODS A retrospective observational design with a mixed-methods approach was utilized. The study included a sample of website users (N=69,055) and app users (N=4,547) from September 1, 2020, to July 25, 2022. App and website usage data were analyzed to evaluate engagement and retention. T-tests were employed for comparing engagement and retention levels between the app and website. A thematic analysis was examined to assess the types of negative thoughts and the success of cognitive restructuring. Logistic regression was used to estimate the likelihood of restructuring based on negative thought type and attributional style. RESULTS Those who used the longitudinal intervention after first using a brief intervention demonstrated significantly higher engagement and retention (P<.001). In user ratings received for mindline.sg (n=8,959), 83.03% rated the app 3 or higher (out of 5) on helpfulness. 91.6% of the users (n=862) who attempted cognitive restructuring (n=790) on the app successfully reframed a thought. The logistic regression analysis indicated significance in the ability to restructure future-oriented negative thoughts (P<.001), and internal, stable and global (P<.001) negative thoughts in a single conversation with Wysa, while other attributional styles required more intervention. A qualitative thematic analysis of the negative thoughts mentioned within the CA documented the psychosocial challenges being managed by users during COVID-19. CONCLUSIONS The findings demonstrated that brief interventions can facilitate enhanced engagement with digital mental health interventions and digital interventions can successfully facilitate cognitive restructuring, and improvement of mental health outcomes.
- Open Access
- 29 March 2023
- Published by JMIR Publications Inc. in JMIR Human Factors
- Vol. 10 (1) , e42167
Perceptions of a Digital Mental Health Platform Among Participants With Depressive Disorder, Anxiety Disorder, and Other Clinically Diagnosed Mental Disorders in Singapore: Usability and Acceptability Study
Background: The website mindline.sg is a stress management and coping website that can be accessed anonymously in Singapore for free. Although designed to serve individuals who are well or have mild depression and anxiety symptoms, mindline.sg may potentially be used by clinicians as an adjunct therapeutic aid for patients with clinically diagnosed mental disorders. Objective: This study aims to determine the perceived usability, acceptability, and usefulness of mindline.sg among individuals with diagnosed mental disorders in a clinical setting. Methods: A cross-sectional study with 173 participants was conducted in the waiting room of a psychiatrist’s office at the National University Hospital in Singapore. Participants waiting for an appointment were given 30 minutes and a simple set of instructions to use three features of mindline.sg. They subsequently answered a set of web-based survey questions via their smartphones, including a 16-item subset of the Post-Study System Usability Questionnaire (PSSUQ) for usability measurement and 5 questions designed to understand the perceived usefulness and acceptability of mindline.sg. Multiple linear regression is used to determine the associated demographic factors with overall PSSUQ score. A chi-square test is performed to investigate associations of psychiatric condition with users’ responses on acceptability and perceived usefulness of mindline.sg. For this study, P<.05 is considered significant. Results: We observed that the overall (mean 2.86, SD 1.46), system usefulness (mean 2.74, SD 1.46), and information quality (mean 2.98, SD 1.33) subscores of the PSSUQ survey are within a 99% CI of a literature-derived norm, which all have the interpretation of having high perceived usability. However, interface quality (mean 2.98, SD 1.33) scored lower than the literature-derived norm, although it is still better than the neutral score of 4. We find participants with lower than a General Certificate of Education O-Level or N-Level education tend to give a lower usability score as compared to others (β=.49; P=.02). Participants who have not been hospitalized previously due to their condition are also more likely to give a lower PSSUQ score as compared to individuals who have been hospitalized (β=.18; P=.03). The platform mindline.sg is also deemed to be generally useful and acceptable with all the survey questions receiving more than a 60% positive response. We found no association between the type(s) of self-reported psychiatric disorder(s) and the perceived usefulness and acceptability of mindline.sg. Conclusions: Our results show that mindline.sg is generally perceived as usable and acceptable by individuals with a diagnosed mental disorder in Singapore. The study suggests improving usability among individuals with lower education levels. Particularly promising is the finding that previously hospitalized individuals have significantly higher perceived usability and satisfaction of the website, suggesting potential impact could be found among a moderately to severely at-risk clinical population. The effectiveness of mindline.sg as an adjunct therapy for individuals with diagnosed mental disorders should therefore be explored in future studies.
- 29 March 2023
- Published by JMIR Publications Inc. in JMIR Human Factors
- Vol. 10 (1) , e42167
Open AccessPerceptions of a Digital Mental Health Platform Among Participants With Depressive Disorder, Anxiety Disorder, and Other Clinically Diagnosed Mental Disorders in Singapore: Usability and Acceptability Study
Background: The website mindline.sg is a stress management and coping website that can be accessed anonymously in Singapore for free. Although designed to serve individuals who are well or have mild depression and anxiety symptoms, mindline.sg may potentially be used by clinicians as an adjunct therapeutic aid for patients with clinically diagnosed mental disorders. Objective: This study aims to determine the perceived usability, acceptability, and usefulness of mindline.sg among individuals with diagnosed mental disorders in a clinical setting. Methods: A cross-sectional study with 173 participants was conducted in the waiting room of a psychiatrist’s office at the National University Hospital in Singapore. Participants waiting for an appointment were given 30 minutes and a simple set of instructions to use three features of mindline.sg. They subsequently answered a set of web-based survey questions via their smartphones, including a 16-item subset of the Post-Study System Usability Questionnaire (PSSUQ) for usability measurement and 5 questions designed to understand the perceived usefulness and acceptability of mindline.sg. Multiple linear regression is used to determine the associated demographic factors with overall PSSUQ score. A chi-square test is performed to investigate associations of psychiatric condition with users’ responses on acceptability and perceived usefulness of mindline.sg. For this study, P<.05 is considered significant. Results: We observed that the overall (mean 2.86, SD 1.46), system usefulness (mean 2.74, SD 1.46), and information quality (mean 2.98, SD 1.33) subscores of the PSSUQ survey are within a 99% CI of a literature-derived norm, which all have the interpretation of having high perceived usability. However, interface quality (mean 2.98, SD 1.33) scored lower than the literature-derived norm, although it is still better than the neutral score of 4. We find participants with lower than a General Certificate of Education O-Level or N-Level education tend to give a lower usability score as compared to others (β=.49; P=.02). Participants who have not been hospitalized previously due to their condition are also more likely to give a lower PSSUQ score as compared to individuals who have been hospitalized (β=.18; P=.03). The platform mindline.sg is also deemed to be generally useful and acceptable with all the survey questions receiving more than a 60% positive response. We found no association between the type(s) of self-reported psychiatric disorder(s) and the perceived usefulness and acceptability of mindline.sg. Conclusions: Our results show that mindline.sg is generally perceived as usable and acceptable by individuals with a diagnosed mental disorder in Singapore. The study suggests improving usability among individuals with lower education levels. Particularly promising is the finding that previously hospitalized individuals have significantly higher perceived usability and satisfaction of the website, suggesting potential impact could be found among a moderately to severely at-risk clinical population. The effectiveness of mindline.sg as an adjunct therapy for individuals with diagnosed mental disorders should therefore be explored in future studies.