Mobile Health Technologies for Suicide Prevention: Feature Review and Recommendations for Use in Clinical Care

The use of advanced technology and statistical methods to predict and prevent suicide

In the past decade, two themes have emerged across suicide research. First, according to meta-analyses, the ability to predict and prevent suicidal thoughts and behaviours is weaker than would be expected for the size of the field. Second, review and commentary papers propose that technological and statistical methods (such as smartphones, wearables, digital phenotyping and machine learning) might become solutions to this problem. In this Review, we aim to strike a balance between the pessimistic picture presented by these meta-analyses and the optimistic picture presented by review and commentary papers about the promise of advanced technological and statistical methods to improve the ability to understand, predict and prevent suicide. We divide our discussion into two broad categories. First, we discuss the research aimed at assessment, with the goal of better understanding or more accurately predicting suicidal thoughts and behaviours. Second, we discuss the literature that focuses on prevention of suicidal thoughts and behaviours. Ecological momentary assessment, wearables and other technological and statistical advances hold great promise for predicting and preventing suicide, but there is much yet to do.

The Googlization of Health: Invasiveness and corporate responsibility in media discourses on Facebook's algorithmic programme for suicide prevention

Big tech companies increasingly play a role in the domain of health. Also called the "Googlization of Health", this phenomenon is often studied by drawing on the notion of 'hostile worlds', where market values and common goods are incommensurable. Yet, the 'hostile worlds' theory is not uncontested; scholars for instance argue that the justifications of big tech companies are important analytical considerations as well. Building on this literature, in this paper I report on a case study of Facebook employing AI for suicide prevention, moving beyond Facebook's justifications only to study the ways in which media commentators and their audiences discussed Facebook's programme and the values they saw as being at stake. In the results, I show how invasiveness was, in different ways and forms, a main theme in thinking about Facebook using AI to do suicide prevention. Commentators and readers alike discussed how: 1) Facebook takes corporate responsibility with this initiative, or alternatively Facebook only has commercial interests and uses the notion of 'public good' to transgress spheres and sectors even further, thus being invasive; 2) Facebook's AI suicide prevention programme is invasive in relation to privacy and privacy laws, or, instead, people give up their privacy willingly in exchange for entertainment; 3) The programme undermines, rather than enhances, safety; 4) Suicide prevention in itself is already invasive. These different forms of invasiveness, I argue in the conclusion, also imply responsibility for different actors, from AI itself to Facebook through to medical professionals. Moreover, they show what values are at stake in, and transformed through, Facebook's AI suicide prevention programme, going beyond the frames of privacy and surveillance capitalism.

Risk Assessment and Crisis Intervention for Youth in a Time of Telehealth

For the last decade, there has been growing concern regarding the rising rates of youth engagement in self-injury and suicide. The worldwide outbreak of the coronavirus disease 2019 (COVID-19) has elevated these concerns due to increased risk factors pertaining to social, family, economic, and health stressors, in addition to changes to typical routines and support systems. Unfortunately, there are many barriers to at-risk youth being able to access evidence-based mental health services including cost, lack of trained providers, transportation issues, and physical distancing due to the pandemic. Providing school-based prevention and intervention programs that promote social, emotional, and behavioral well-being helps to address many of these barriers. This article highlights important considerations to providing these services in a school-based telehealth modality. Symptom clusters that put youth at risk of harm to self are described. Best practice therapeutic modalities that can be disseminated in a school-based telehealth modality, such as cognitive behavior therapy, dialectical behavior therapy, and mindfulness-based approaches, are reviewed. Although there is growing empirical literature for these school-based prevention and intervention approaches, additional research is needed to determine how to best support at-risk youth remotely.

Suicide risk assessment in UK mental health services: a national mixed-methods study

BACKGROUND

Risk assessments are a central component of mental health care. Few national studies have been done in the UK on risk assessment tools used in mental health services. We aimed to examine which suicide risk assessment tools are in use in the UK; establish the views of clinicians, carers, and service users on the use of these tools; and identify how risk assessment tools have been used with mental health patients before suicide.

METHODS

We did a mixed-methods study involving three components: collection and content analysis of risk assessment tools used by UK mental health services; an online survey of clinicians, service-users, and carers; and qualitative telephone interviews with clinicians on their use of risk assessment tools before a suicide death and their views of these tools. The online survey was advertised through the National Confidential Inquiry into Suicide and Safety in Mental Health's (NCISH) website and social media, and it included both quantitative and open-ended qualitative questions, and respondents were recruited through convenience sampling. For the telephone interviews, we examined the NCISH database to identify clinicians who had been responsible for the care of a patient who died by suicide and who had been viewed as being at low or no immediate risk of suicide.

FINDINGS

We obtained 156 risk assessment tools from all 85 National Health Service mental health organisations in the UK, and 85 (one per each organisation) were included in the analysis. We found little consistency in use of these instruments, with 33 (39%) of 85 organisations using locally developed tools. Most tools aimed to predict self-harm or suicidal behaviour (84 [99%] of 85), and scores were used to determine management decisions (80 [94%]). Clinicians described positive aspects of risk tools (facilitating communication and enhancing therapeutic relationships) but also expressed negative views (inadequate training in the use of tools and their time-consuming nature). Both patients and carers reported some positive views, but also emphasised little involvement during risk assessment, and a lack of clarity on what to do in a crisis.

INTERPRETATION

Assessment processes need to be consistent across mental health services and include adequate training on how to assess, formulate, and manage suicide risk. An emphasis on patient and carer involvement is needed. In line with national guidance, risk assessment should not be seen as a way to predict future behaviour and should not be used as a means of allocating treatment. Management plans should be personalised and collaboratively developed with patients and their families and carers.

FUNDING

The Healthcare Quality Improvement Partnership.

Clinician's Guide to Evaluating and Developing eHealth Interventions for Mental Health

Objective

This review aimed to examine key information regarding technology‐delivered interventions for patients with mental health and/or substance use disorders and to provide support for efforts by psychiatrists and other mental health professionals in recommending applications or helping to develop new technology‐delivered interventions.

Methods

The authors reviewed existing information about the appraisal, development, and evaluation of technology‐delivered interventions (eHealth interventions).

Results

High‐level guidance is available for clinicians who want to evaluate eHealth applications for their patients. Clinicians should be familiar with existing models of eHealth intervention development and with traditional as well as unique elements in the evaluation of efficacy for these approaches. However, existing intervention development models have not been empirically validated, and only one includes empirical optimization as an inherent part of its process.

Conclusions

Because of the proliferation of eHealth interventions, mental health professionals should bring to this area the same level of content knowledge, understanding of development and evaluation processes, and rigorous skepticism as they do for pharmacotherapy and therapist‐delivered behavioral interventions.

eHealth interventions are rapidly transforming mental health treatment.

Clinicians should apply the same rigor to evaluating eHealth interventions that they apply to pharmacological treatments or other behavioral therapies.

High‐level guidance and recommendations regarding ideal eHealth intervention development are available to aid in such evaluation, but empirical evidence in support of these guidelines is lacking.

Development and Feasibility of a Safety Plan Mobile Application for Adolescent Suicide Attempt Survivors

Past suicide attempts are a powerful predictor of suicide. This study developed and evaluated the feasibility of a mobile application for creating safety plans, which include coping strategies that can be immediately accessed and used by suicide attempt survivors during a crisis. A safety plan mobile application, called Brake of My Mind, was developed (study 1). Heuristic evaluation (for experts) and user evaluations (for health professionals and adolescent suicide attempt survivors) were performed. A pilot test was then conducted based on the theory of planned behavior to evaluate the feasibility of Brake of My Mind (study 2). Three adolescent suicide attempt survivors used a pilot version of Brake of My Mind. Attitude toward suicide attempts, subjective norms, perceived behavioral control, and suicide intentions were assessed before, immediately after, and 1 week after using Brake of My Mind. Brake of My Mind showed very few low-priority usability problems, and it was considered a "good" and "acceptable" application. In study 2, median scores for attitudes toward suicide attempts, perceived behavioral control, and suicide intentions decreased over time after using Brake of My Mind. The subjective norm scores did not change. Brake of My Mind is an acceptable application for adolescent suicide attempt survivors that appears effective in decreasing their positive attitude toward suicide attempts.

Acute psychiatric care for pediatric patients

Higher level or acute psychiatric care for youth is intended to be active but short-term treatment focussing on crisis stabilisation, assessment, safety monitoring, and longer-term treatment planning. The focus of this article is on describing common challenges and the effort to address these challenges through new approaches to acute psychiatric care for children and adolescents. The review finds that (1) inpatient paediatric psychiatry beds are in high demand and often difficult to access, (2) there are a number of common challenges these units face including managing length of stays, readmissions, and adverse events, and (3) there are encouraging therapeutic approaches adapted for this setting. There is still much work to be done to advance the evidence-base for acute psychiatric care for youth particularly in defining and assessing an effective admission. Paediatric psychiatry patients are a vulnerable population and call for our best tools to be put to use to improve the quality and safety of care.

Technology for Our Future? Exploring the Duty to Report and Processes of Subjectification Relating to Digitalized Suicide Prevention

Digital and networking technologies are increasingly used to predict who is at risk of attempting suicide. Such digitalized suicide prevention within and beyond mental health care raises ethical, social and legal issues for a range of actors involved. Here, I will draw on key literature to explore what issues (might) arise in relation to digitalized suicide prevention practices. I will start by reviewing some of the initiatives that are already implemented, and address some of the issues associated with these and with potential future initiatives. Rather than addressing the breadth of issues, however, I will then zoom in on two key issues: first, the duty of care and the duty to report, and how these two legal and professional standards may change within and through digitalized suicide prevention; and secondly a more philosophical exploration of how digitalized suicide prevention may alter human subjectivity. To end with the by now famous adagio, digitalized suicide prevention is neither good nor bad, nor is it neutral, and I will argue that we need sustained academic and social conversation about who can and should be involved in digitalized suicide prevention practices and, indeed, in what ways it can and should (not) happen.

Caring E-mails for Military and Veteran Suicide Prevention: A Randomized Controlled Trial

OBJECTIVE

The purpose of this multisite study was to conduct a randomized controlled trial of an e-mail version of the caring letters (CL) suicide prevention intervention to determine whether the intervention is efficacious in preventing suicide behaviors among U.S. service members and veterans.

METHOD

Psychiatric inpatients (N = 1,318) were recruited from four military medical centers and two VA hospitals and randomized to receive either 13 caring e-mails over two years or usual care.

RESULTS

There were 10 deaths from any cause in the CL group (three suicides) and 14 in the usual care group (seven suicides) during the individual two-year follow-up intervals. There was no statistically significant difference in the rate of all-cause hospital readmission between the study groups (RR = 1.13; 95% CI = 0.94, 1.36). There were no differences observed between groups on self-reported psychiatric hospital readmissions, self-reported suicide attempts, or other measures associated with risk for suicide.

CONCLUSIONS

No firm conclusions about the efficacy of the intervention can be made because the study was inadequately powered. There were no adverse events associated with the intervention, and implementation of the procedures was feasible in the military and veteran hospital settings. These results provide important methodological considerations for caring contact trials in military populations.

Suicide Prevention Mobile Apps: Descriptive Analysis of Apps from the Most Popular Virtual Stores

Background

Provision of follow-up and care during treatment of people with suicidal intentions is a challenge for health professionals and experts in information and communications technology (ICT). Therefore, health professionals and ICT experts are making efforts to carry out these activities in collaboration by using mobile apps as a technological resource.

Objective

This study aimed to descriptively analyze mobile apps aimed at suicide prevention and to determine relevant factors in their design and development. In addition, it sought to analyze their impact on the support of treatment for patients at risk for suicide.

Methods

We considered 20 apps previously listed in the article “Mobile Apps for Suicide Prevention: Review of Virtual Stores and Literature” (de la Torre et al, JMIR mHealth uHealth 2017;5[10]:e130). To find the apps in this list, the most popular app stores (Android and iOS) were searched using the keyword “suicide prevention.” The research focused on publicly available app information: language, platform, and user ratings. The results obtained were statistically evaluated using 16 parameters that establish various factors that may affect the choice of the user, and the consequent support that the app can offer to a person at risk for suicide.

Results

Of the 20 mobile apps, 4 no longer appeared in the app stores and were therefore excluded. Analysis of the remaining 16 apps sampled showed the following: (1) a high percentage of the apps analyzed in the study (n=13, 82%) are provided in English language; (2) the sampled apps were last updated in 2017, when only 45% of them were updated, but the constant and progressive update of treatments should be reflected in the apps; and (3) the technical quality of these apps cannot be determined on the basis of the distribution of scores, because their popularity indices can be subjective (according to the users). User preference for a particular operating system would require further, more specific research, including study of the differences in the technical and usability aspects between both platforms and the design of medical apps.

Conclusions

Although there are positive approaches to the use of apps for suicide prevention and follow-up, the technical and human aspects are yet to be explored and defined. For example, the design and development of apps that support suicide prevention should be strongly supported by health personnel to humanize these apps, so that the effectiveness of the treatments supported by them can be improved.

Implementation of a Heart Failure Telemonitoring System in Home Care Nursing: Feasibility Study

BACKGROUND

Telemonitoring (TM) of heart failure (HF) patients in a clinic setting has been shown to be effective if properly implemented, but little is known about the feasibility and impact of implementing TM through a home care nursing agency.

OBJECTIVE

This study aimed to determine the feasibility of implementing a mobile phone-based TM system through a home care nursing agency and to explore the feasibility of conducting a future effectiveness trial.

METHODS

A feasibility study was conducted by recruiting, through community cardiologists and family physicians, 10 to 15 HF patients who would use the TM system for 4 months by taking daily measurements of weight and blood pressure and recording symptoms. Home care nurses responded to alerts generated by the TM system through either a phone call and/or a home visit. Patients and their clinicians were interviewed poststudy to determine their perceptions and experiences of using the TM system.

RESULTS

Only one community cardiologist was recruited who was willing to refer patients to this study, even after multiple attempts were made to recruit further physicians, including family physicians. The cardiologist referred only 6 patients over a 6-month period, and half of the patients dropped out of the study. The identified barriers to implementing the TM system in home care nursing were numerous and led to the small recruitment in patients and clinicians and large dropout rate. These barriers included challenges in nurses contacting patients and physicians, issues related to retention, and challenges related to integrating the TM system into a complex home care nursing workflow. However, some potential benefits of TM through a home care nursing agency were indicated, including improved patient education, providing nurses with a better understanding of the patient's health status, and reductions in home visits.

CONCLUSIONS

Lessons learned included the need to incentivize physicians, to ensure streamlined processes for recruitment and communication, to target appropriate patient populations, and to create a core clinical group. Barriers encountered in this feasibility trial should be considered to determine their applicability when deploying innovations into different service delivery models.

Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior

Risk assessment of suicidal behavior is a time-consuming but notoriously inaccurate activity for mental health services globally. In the last 50 years a large number of tools have been designed for suicide risk assessment, and tested in a wide variety of populations, but studies show that these tools suffer from low positive predictive values. More recently, advances in research fields such as machine learning and natural language processing applied on large datasets have shown promising results for health care, and may enable an important shift in advancing precision medicine. In this conceptual review, we discuss established risk assessment tools and examples of novel data-driven approaches that have been used for identification of suicidal behavior and risk. We provide a perspective on the strengths and weaknesses of these applications to mental health-related data, and suggest research directions to enable improvement in clinical practice.

Theory-Based Text-Messaging to Reduce Methamphetamine Use and HIV Sexual Risk Behaviors Among Men Who Have Sex with Men: Automated Unidirectional Delivery Outperforms Bidirectional Peer Interactive Delivery

Project Tech Support2 was a randomized controlled trial that tested three methods of text message delivery for reducing methamphetamine use and HIV risks among MSM. From March 2014 to January 2016, 286 methamphetamine-using MSM were randomized into: (1) interactive text conversations with Peer Health Educators, plus five-times-a-day automated theory-based messages, plus a weekly self-monitoring text-message assessment (TXT-PHE; n = 94); or, (2) the daily automated messages and weekly self-monitoring assessment (TXT-Auto; n = 99); or, (3) weekly self-monitoring assessment only (AO; n = 93). All three conditions demonstrated reductions in methamphetamine use (coef. = - 0.10), sex on methamphetamine (coef. = - 0.09), and condomless anal intercourse (CAI) with casual male partners (coef. = - 0.06). Only participants in TXT-PHE and TEXT-Auto also reduced CAI with main male partners (coef_TXT-PHE = - 0.19; coef._TXT-Auto = - 0.16), and only TEXT-Auto participants reduced CAI with anonymous male partners (coef. = - 0.05). Additionally, both theory-based text-messaging interventions achieved sustained reductions in five of the six outcomes through 9 months. Overall, automated delivery outperformed peer-delivered messaging.

An Electronic Clinical Decision Support System for the Assessment and Management of Suicidality in Primary Care: Protocol for a Mixed-Methods Study

Background

Suicide is a global public health concern, but it is preventable. Increased contact with primary care before the suicide or attempted suicide raises opportunities for intervention and prevention. However, suicide assessment and management are areas that many general practitioners (GPs) find particularly challenging. Previous research has indicated significant variability in how GPs understand, operationalize, and assess suicide risk, which subsequently has an impact on clinical decision making. Clinical decision support systems (CDSS) have been widely implemented across different health care settings, including primary care to support practitioners in clinical decision making. A CDSS may reduce inconsistencies in the identification, assessment, and management of suicide risk by GPs by guiding them through the consultation and generating a risk assessment plan that can be shared with a service user or with specialized mental health services.

Objective

Our aim is to co-develop and test with end users (eg, GPs, primary care attendees, mental health professionals) an electronic clinical decision support system (e-CDSS) to support GPs in the identification, assessment, and management of suicidality in primary care.

Methods

Ours is an ongoing embedded mixed-methods study with four phases: (1) qualitative interviews with GPs to explore their views on the content, format, and use of the e-CDSS, as well as consultation with two service-user advisory groups (people aged ≤25 and people aged ≥25) to inform the content of the e-CDSS including phrasing of items and clarity; (2) participatory co-production workshops with GPs, service users, and clinical experts in suicidality to determine the content and format of the e-CDDS; gain consensus of the relevance of items; establish content validity and identify pathways to implementation, using the Consolidated Framework for Implementation Research; (3) building the e-CDSS so that it guides the GP through a consultation; and (4) usability testing of the e-CDSS with GPs and service users in one primary care practice involving a nonlive and a live stage.

Results

The study was funded for four years, to take place between 2015 and 2019, and is currently completing phase 4 data collection. The first results are expected to be submitted for publication in June 2019. The findings will enable us to evaluate the feasibility, acceptability, and usability of a suicide-specific, electronic, guided decision support system in primary care.

Conclusions

This study will be the first to explore the feasibility, acceptability, and usability of an electronic, guided decision support system for use in primary care consultations for the improved assessment and management of suicidality.

International Registered Report Identifier (IRRID)

RR1-10.2196/11135

Mobile App Tools for Identifying and Managing Mental Health Disorders in Primary Care

PURPOSE OF REVIEW

Mental health apps are intriguing yet challenging tools for addressing barriers to treatment in primary care. In the current review, we seek to assist primary care professionals with evaluating and integrating mental health apps into practice. We briefly summarize two leading frameworks for evaluating mental health apps and conduct a systematic review of mental health apps across a variety of areas commonly encountered in primary care.

RECENT FINDINGS

Existing frameworks can guide professionals and patients through the process of identifying apps and evaluating dimensions such as privacy and security, credibility, and user experience. For specific apps, several problem areas appear to have relatively more scientific evaluation in the current app landscape, including PTSD, smoking, and alcohol use. Other areas such as eating disorders not only lack evaluation, but contain a significant subset of apps providing potentially harmful advice.

SUMMARY

Overall, individuals seeking mental health apps will likely encounter strengths such as symptom tracking and psychoeducational components, while encountering common weaknesses such as insufficient privacy settings and little integration of empirically-supported techniques. While mental health apps may have more promise than ever, significant barriers to finding functional, usable, effective apps remain for health professionals and patients alike.

Embodied Conversational Agents for the Detection and Prevention of Suicidal Behaviour: Current Applications and Open Challenges

Embodied conversational agents (ECAs) are advanced computational interactive interfaces designed with the aim to engage users in the continuous and long-term use of a background application. The advantages and benefits of these agents have been exploited in several e-health systems. One of the medical domains where ECAs are recently applied is to support the detection of symptoms, prevention and treatment of mental health disorders. As ECAs based applications are increasingly used in clinical psychology, and due that one fatal consequence of mental health problems is the commitment of suicide, it is necessary to analyse how current ECAs in this clinical domain support the early detection and prevention of risk situations associated with suicidality. The present work provides and overview of the main features implemented in the ECAs to detect and prevent suicidal behaviours through two scenarios: ECAs acting as virtual counsellors to offer immediate help to individuals in risk; and ECAs acting as virtual patients for learning/training in the identification of suicide behaviours. A literature review was performed to identify relevant studies in this domain during the last decade, describing the main characteristics of the implemented ECAs and how they have been evaluated. A total of six studies were included in the review fulfilling the defined search criteria. Most of the experimental studies indicate promising results, though these types of ECAs are not yet commonly used in routine practice. The identification of some open challenges for the further development of ECAs within this domain is also discussed.

BackUp: Development and evaluation of a smart-phone application for coping with suicidal crises

Background

Suicide is a major public health issue and has large impact on the lives of many people. Innovative technologies such as smartphones could create new possibilities for suicide prevention, such as helping to overcome the barriers and stigma on help seeking in case of suicidal ideation. Due to their omnipresence, smartphone apps can offer suicide prevention tools very fast, they are easily-accessible, low-threshold and can help overcome some of the help-seeking barriers suicidal people experience. This article describes the development, testing and implementation of a mobile application for coping with suicidal crisis: BackUp.

Methods

Based on the analysis of literature and existing suicide prevention apps several tools were identified as relevant to include in a suicide prevention app. The selected tools (a safety planning tool, a hope box, a coping cards module, and a module to reach out) are evidence based in a face to face context, and could be easily transferred into a mobile app. The testing of existing apps and the literature also revealed important guidelines for the technical development of the application.

Results

BackUp was developed and tested by an expert panel (n = 9) and a panel of end users (n = 21). Both groups rated BackUp as valuable for suicide prevention. Suicidal ideation of the end user group was measured using the Beck Scale for Suicidal Ideation before and after testing BackUp, and showed a small but non-significant decrease. The majority of the testers used BackUp several times. All tools were evaluated as rather or very useable in times of suicidal crisis.

Conclusion

BackUp was positively evaluated and indicates that self-help tools can have a positive impact on suicidal ideation. Apps in particular create opportunities in approaching people that are not reached by traditional interventions; on the other hand they can contribute to suicide prevention in addition to regular care. However, more research is needed on the impact and effect of suicide prevention apps.

Integrating Smartphone Technology at the Time of Discharge from a Child and Adolescent Inpatient Psychiatry Unit

OBJECTIVE

As smartphone technology becomes an increasingly important part of youth mental health, there has been little to no examination of how to effectively integrate smartphone-based safety planning with inpatient care. Our study sought to examine whether or not we could effectively integrate smartphone-based safety planning into the discharge process on a child and adolescent inpatient psychiatry unit.

METHOD

Staff members completed a survey to determine the extent of smartphone ownership in a population of admitted child and adolescent inpatients. In addition to quantifying smartphone ownership, the survey also tracked whether youth would integrate their previously-established safety plan with a specific safety planning application on their smartphone (Be Safe) at the time of discharge.

RESULTS

Sixty-six percent (50/76) of discharged youth owned a smartphone, which is consistent with prior reports of high smartphone ownership in adult psychiatric populations. A minority of youth (18%) downloaded the Be Safe app prior to discharge, with most (68%) suggesting they would download the app after discharge. Notably, all patients who downloaded the app prior to discharge were on their first admission to a psychiatric inpatient unit.

CONCLUSION

Child and adolescent psychiatric inpatients have a clear interest in smartphone-based safety planning. Our results suggest that integrating smartphone-related interventions earlier in an admission might improve access before discharge. This highlights the tension between restricting and incorporating smartphone access for child and adolescent inpatients and may inform future study in this area.