Short-term prediction of suicidal thoughts and behaviors in adolescents: Can recent developments in technology and computational science provide a breakthrough?

Why do adolescents attempt suicide? Insights from leading ideation-to-action suicide theories: a systematic review

Suicide is a leading cause of death among adolescents, and recent suicide theories have sought to clarify the factors that facilitate the transition from suicide ideation to action. Specifically, the Interpersonal Theory of Suicide (IPTS), Integrated Motivational-Volitional Model (IMV), and Three Step Theory (3ST) have highlighted risk factors central to the formation of suicidal ideation and suicidal behaviors, which is necessary for suicide death. However, these models were initially developed and tested among adults, and given core socioemotional and neurodevelopmental differences in adolescents, the applicability of these models remains unclear. Directly addressing this gap in knowledge, this systematic review aimed to (1) describe the evidence of leading ideation-to-action theories (i.e., IPTS, IMV, 3ST) as they relate to suicide risk among adolescents, (2) integrate ideation-to-action theories within prevailing biological frameworks of adolescent suicide, and (3) provide recommendations for future adolescent suicide research. Overall, few studies provided a complete test of models in adolescent samples, and empirical research testing components of these theories provided mixed support. Future research would benefit from integrating neurodevelopmental and developmentally sensitive psychosocial frameworks to increase the applicability of ideation-to-action theories to adolescents. Further, utilizing real-time monitoring approaches may serve to further clarify the temporal association among risk factors and suicide.

Adolescent, Parent, and Provider Perceptions of a Predictive Algorithm to Identify Adolescent Suicide Risk in Primary Care

OBJECTIVE

To understand adolescent, parent, and provider perceptions of a machine learning algorithm for detecting adolescent suicide risk prior to its implementation primary care.

METHODS

We conducted semi-structured, qualitative interviews with adolescents (n = 9), parents (n = 12), and providers (n = 10; mixture of behavioral health and primary care providers) across two major health systems. Interviews were audio recorded and transcribed with analyses supported by use of NVivo. A codebook was developed combining codes derived inductively from interview transcripts and deductively from implementation science frameworks for content analysis.

RESULTS

Reactions to the algorithm were mixed. While many participants expressed privacy concerns, they believed the algorithm could be clinically useful for identifying adolescents at risk for suicide and facilitating follow-up. Parents' past experiences with their adolescents' suicidal thoughts and behaviors contributed to their openness to the algorithm. Results also aligned with several key Consolidated Framework for Implementation Research domains. For example, providers mentioned barriers inherent to the primary care setting such as time and resource constraints likely to impact algorithm implementation. Participants also cited a climate of mistrust of science and health care as potential barriers.

CONCLUSIONS

Findings shed light on factors that warrant consideration to promote successful implementation of suicide predictive algorithms in pediatric primary care. By attending to perspectives of potential end users prior to the development and testing of the algorithm, we can ensure that the risk prediction methods will be well-suited to the providers who would be interacting with them and the families who could benefit.

Machine learning-based prediction for self-harm and suicide attempts in adolescents

This study aimed to use machine learning (ML) models to predict the risk of self-harm and suicide attempts in adolescents. We conducted secondary analysis of cross-sectional data from the Longitudinal Study of Australian Children dataset. Several key variables at the age of 14-15 years were used to predict self-harm or suicide attempt at 16-17 years. Random forest classification models were used to select the optimal subset of predictors and subsequently make predictions. Among 2809 participants, 296 (10.54%) reported an act of self-harm and 145 (5.16%) reported attempting suicide at least once in the past 12 months. The area under the receiver operating curve was fair for self-harm (0.7397) and suicide attempt (0.7220), which outperformed the prediction strategy solely based on prior suicide or self-harm attempt (AUC: 0.6). The most important factors identified were similar, and included depressed feelings, strengths and difficulties questionnaire scores, perceptions of self, and school- and parent-related factors. The random forest classification algorithm, an ML technique, can effectively select the optimal subset of predictors from hundreds of variables to forecast the risks of suicide and self-harm among adolescents. Further research is needed to validate the utility and scalability of ML techniques in mental health research.

Systematic Review and Meta-analysis: International Prevalence of Suicidal Ideation and Attempt in Youth

OBJECTIVE

Globally, rates of youth suicide vary considerably. Suicidal thoughts and behaviors (STB) are consistently associated with risk of death by suicide. However, international trends in STB have not yet been compared. To address this gap, an international meta-analysis of epidemiological and school-based studies that report on STB in youth was conducted.

METHOD

Systematic searches were conducted in PubMed and PsycINFO through April 2022. Eligible studies included prevalence of active suicidal ideation (SI) or suicide attempts (SA) in community youth younger than age 22. All studies were coded by 2 authors. Mixed models accounting for shared methods and including hypothesized moderators were conducted using the metafor package in R.

RESULTS

There were 371 effect sizes for SI, 94 for SI with a plan, and 316 for SA, representing 149 regions. Year of data collection ranged from 1981 to 2021. Participants were 6 to 21 years old. The prevalence of SI ranged across regions from 14.3% to 22.6%; the prevalence of SA ranged from 4.6% to 15.8%. Year was not associated with increasing STB prevalence except for studies from the United States, which showed increasing rates of SI and SA since 2007.

CONCLUSION

This is the most comprehensive meta-analysis of STB in youth, providing valuable data about how risk factors most commonly associated with suicide vary internationally and over time. International rates of STB among youth are not improving and may be getting worse in the United States, despite efforts to reduce suicide risk. Most studies did not report rates of SI or SA separately for LGBTQIA+ (lesbian, gay, bisexual, transgender, queer, intersex, asexual, and others) youth and youth of color. A better understanding of proximal risk at the individual level will be important to informing future prevention efforts, especially for high-risk groups.

Intensive Longitudinal Assessment of Adolescents to Predict Suicidal Thoughts and Behaviors

OBJECTIVE

Suicide is a leading cause of death among adolescents. However, there are no clinical tools to detect proximal risk for suicide.

METHOD

Participants included 13- to 18-year-old adolescents (N = 103) reporting a current depressive, anxiety, and/or substance use disorder who owned a smartphone; 62% reported current suicidal ideation, with 25% indicating a past-year attempt. At baseline, participants were administered clinical interviews to assess lifetime disorders and suicidal thoughts and behaviors (STBs). Self-reports assessing symptoms and suicide risk factors also were obtained. In addition, the Effortless Assessment of Risk States (EARS) app was installed on adolescent smartphones to acquire daily mood and weekly suicidal ideation severity during the 6-month follow-up period. Adolescents completed STB and psychiatric service use interviews at the 1-, 3-, and 6-month follow-up assessments.

RESULTS

K-means clustering based on aggregates of weekly suicidal ideation scores resulted in a 3-group solution reflecting high-risk (n = 26), medium-risk (n = 47), and low-risk (n = 30) groups. Of the high-risk group, 58% reported suicidal events (ie, suicide attempts, psychiatric hospitalizations, emergency department visits, ideation severity requiring an intervention) during the 6-month follow-up period. For participants in the high-risk and medium-risk groups (n = 73), mood disturbances in the preceding 7 days predicted clinically significant ideation, with a 1-SD decrease in mood doubling participants' likelihood of reporting clinically significant ideation on a given week.

CONCLUSION

Intensive longitudinal assessment through use of personal smartphones offers a feasible method to assess variability in adolescents' emotional experiences and suicide risk. Translating these tools into clinical practice may help to reduce the needless loss of life among adolescents.

Ecological Momentary Assessments and Passive Sensing in the Prediction of Short-Term Suicidal Ideation in Young Adults

Importance

Advancements in technology, including mobile-based ecological momentary assessments (EMAs) and passive sensing, have immense potential to identify short-term suicide risk. However, the extent to which EMA and passive data, particularly in combination, have utility in detecting short-term risk in everyday life remains poorly understood.

Objective

To examine whether and what combinations of self-reported EMA and sensor-based assessments identify next-day suicidal ideation.

Design, Setting, and Participants

In this intensive longitudinal prognostic study, participants completed EMAs 4 times daily and wore a sensor wristband (Fitbit Charge 3) for 8 weeks. Multilevel machine learning methods, including penalized generalized estimating equations and classification and regression trees (CARTs) with repeated 5-fold cross-validation, were used to optimize prediction of next-day suicidal ideation based on time-varying features from EMAs (affective, cognitive, behavioral risk factors) and sensor data (sleep, activity, heart rate). Young adult patients who visited an emergency department with recent suicidal ideation and/or suicide attempt were recruited. Identified via electronic health record screening, eligible individuals were contacted remotely to complete enrollment procedures. Participants (aged 18 to 25 years) completed 14 708 EMA observations (64.4% adherence) and wore a sensor wristband approximately half the time (55.6% adherence). Data were collected between June 2020 and July 2021. Statistical analysis was performed from January to March 2023.

Main Outcomes and Measures

The outcome was presence of next-day suicidal ideation.

Results

Among 102 enrolled participants, 83 (81.4%) were female; 6 (5.9%) were Asian, 5 (4.9%) were Black or African American, 9 (8.8%) were more than 1 race, and 76 (74.5%) were White; mean (SD) age was 20.9 (2.1) years. The best-performing model incorporated features from EMAs and showed good predictive accuracy (mean [SE] cross-validated area under the receiver operating characteristic curve [AUC], 0.84 [0.02]), whereas the model that incorporated features from sensor data alone showed poor prediction (mean [SE] cross-validated AUC, 0.56 [0.02]). Sensor-based features did not improve prediction when combined with EMAs. Suicidal ideation-related features were the strongest predictors of next-day ideation. When suicidal ideation features were excluded, an alternative EMA model had acceptable predictive accuracy (mean [SE] cross-validated AUC, 0.76 [0.02]). Both EMA models included features at different timescales reflecting within-day, end-of-day, and time-varying cumulative effects.

Conclusions and Relevance

In this prognostic study, self-reported risk factors showed utility in identifying near-term suicidal thoughts. Best-performing models required self-reported information, derived from EMAs, whereas sensor-based data had negligible predictive accuracy. These results may have implications for developing decision algorithms identifying near-term suicidal thoughts to guide risk monitoring and intervention delivery in everyday life.

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.

Predicting short-term suicidal thoughts in adolescents using machine learning: developing decision tools to identify daily level risk after hospitalization

BACKGROUND

Mobile technology offers unique opportunities for monitoring short-term suicide risk in daily life. In this study of suicidal adolescent inpatients, theoretically informed risk factors were assessed daily following discharge to predict near-term suicidal ideation and inform decision algorithms for identifying elevations in daily level risk, with implications for real-time suicide-focused interventions.

METHODS

Adolescents (N = 78; 67.9% female) completed brief surveys texted daily for 4 weeks after discharge (n = 1621 observations). Using multi-level classification and regression trees (CARTSs) with repeated 5-fold cross-validation, we tested (a) a simple prediction model incorporating previous-day scores for each of 10 risk factors, and (b) a more complex model incorporating, for each of these factors, a time-varying person-specific mean over prior days together with deviation from that mean. Models also incorporated missingness and contextual (study week, day of the week) indicators. The outcome was the presence/absence of next-day suicidal ideation.

RESULTS

The best-performing model (cross-validated AUC = 0.86) was a complex model that included ideation duration, hopelessness, burdensomeness, and self-efficacy to refrain from suicidal action. An equivalent model that excluded ideation duration had acceptable overall performance (cross-validated AUC = 0.78). Models incorporating only previous-day scores, with and without ideation duration (cross-validated AUC of 0.82 and 0.75, respectively), showed relatively weaker performance.

CONCLUSIONS

Results suggest that specific combinations of dynamic risk factors assessed in adolescents' daily life have promising utility in predicting next-day suicidal thoughts. Findings represent an important step in the development of decision tools identifying short-term risk as well as guiding timely interventions sensitive to proximal elevations in suicide risk in daily life.

Clinical Considerations for Digital Resources in Care for Patients With Suicidal Ideation

Smartphone apps offer accessible new tools that may help prevent suicide and that offer support for individuals with active suicidal ideation. Numerous smartphone apps for mental health conditions exist; however, their functionality is limited, and evidence is nascent. A new generation of apps using smartphone sensors and integrating real-time data on evolving risk offers the potential of more personalized support, but these apps present ethical risks and currently remain more in the research domain than in the clinical domain. Nevertheless, clinicians can use apps to benefit patients. This article outlines practical strategies to select safe and effective apps for the creation of a digital toolkit that can augment suicide prevention and safety plans. By creating a unique digital toolkit for each patient, clinicians can help ensure that the apps selected will be most relevant, engaging, and effective.

Improving Suicide Prevention Through Evidence-Based Strategies: A Systematic Review

Objective

The authors sought to identify scalable evidence-based suicide prevention strategies.

Methods

A search of PubMed and Google Scholar identi- fied 20,234 articles published between September 2005 and December 2019, of which 97 were randomized controlled trials with suicidal behavior or ideation as primary outcomes or epidemiological studies of limiting access to lethal means, using educational approaches, and the impact of antidepressant treatment.

Results

Training primary care physicians in depression rec- ognition and treatment prevents suicide. Educating youths on depression and suicidal behavior, as well as active out- reach to psychiatric patients after discharge or a suicidal crisis, prevents suicidal behavior. Meta-analyses find that antidepressants prevent suicide attempts, but individual randomized controlled trials appear to be underpowered. Ketamine reduces suicidal ideation in hours but is untested for suicidal behavior prevention. Cognitive-behavioral therapy and dialectical behavior therapy prevent suicidal behavior. Active screening for suicidal ideation or behavior is not proven to be better than just screening for depression. Education of gatekeepers about youth suicidal behavior lacks effectiveness. No randomized trials have been reported for gatekeeper training for prevention of adult suicidal behavior. Algorithm-driven electronic health record screening, Internet-based screening, and smartphone passive monitoring to identify high-risk patients are under-studied. Means restriction, including of firearms, prevents suicide but is sporadically employed in the United States, even though firearms are used in half of all U.S. suicides.

Conclusions

Training general practitioners warrants wider implementation and testing in other nonpsychiatrist physi- cian settings. Active follow-up of patients after discharge or a suicide-related crisis should be routine, and restricting firearm access by at-risk individuals warrants wider use. Combination approaches in health care systems show promise in reducing suicide in several countries, but evaluating the benefit attributable to each component is essential. Further suicide rate reduction requires evaluating newer approaches, such as electronic health record-derived algorithms, Internet-based screening methods, ketamine's potential benefit for preventing attempts, and passive monitoring of acute suicide risk change.Reprinted from Am J Psychiatry 2021; 178:611-624, with permission from American Psychiatric Association Publishing. Copyright © 2021.

Screen time and suicidal behaviors among U.S. children 9-11 years old: A prospective cohort study

Suicide is a leading cause of death among adolescents. Emerging literature has described relationships between excessive screen time and suicidal behaviors, though findings have been mixed. The objective of this study is to determine the prospective associations between screen time and suicidal behaviors two-years later in a national (U.S.) cohort of 9-11-year-old-children. We analyzed prospective cohort data from the Adolescent Brain Cognitive Development (ABCD) Study (N = 11,633). Logistic regression analyses were estimated to determine the associations between baseline self-reported screen time (exposure) and suicidal behaviors (outcome) based on the Kiddie Schedule for Affective Disorders and Schizophrenia (KSADS-5) at two-year-follow-up. Participants reported an average of 4.0 h of total screen time per day at baseline. At two-year-follow-up, 1.38% of the sample reported at least one suicidal behavior. Each additional hour of total screen time was prospectively associated with 1.09 higher odds of suicidal behaviors at 2-year-follow-up (95% CI 1.03-1.14), after adjusting for covariates. For specific screen time modalities, each additional hour of texting (aOR 1.36, 95% CI 1.06-1.74), video chatting (aOR 1.30, 95% CI 1.03-1.65), watching videos (aOR 1.21, 95% CI 1.04-1.39), and playing video games (aOR 1.18, 95% CI 1.01-1.38) was associated with higher odds of subsequent suicidal behaviors. Higher screen time is associated with higher odds of reporting suicidal behaviors at two-year-follow-up. Future research should seek to identify how specific screen time experiences may influence suicidal behaviors.

A Bayesian network analysis of psychosocial risk and protective factors for suicidal ideation

Background

The aim of this study was to investigate and model the interactions between a range of risk and protective factors for suicidal ideation using general population data collected during the critical phase of the COVID-19 pandemic.

Methods

Bayesian network analyses were applied to cross-sectional data collected 1 month after the COVID-19 lockdown measures were implemented in Austria and the United Kingdom. In nationally representative samples (n = 1,005 Austria; n = 1,006 UK), sociodemographic features and a multi-domain battery of health, wellbeing and quality of life (QOL) measures were completed. Predictive accuracy was examined using the area under the curve (AUC) within-sample (country) and out-of-sample.

Results

The AUC of the Bayesian network models were ≥ 0.84 within-sample and ≥0.79 out-of-sample, explaining close to 50% of variability in suicidal ideation. In total, 15 interrelated risk and protective factors were identified. Seven of these factors were replicated in both countries: depressive symptoms, loneliness, anxiety symptoms, self-efficacy, resilience, QOL physical health, and QOL living environment.

Conclusions

Bayesian network models had high predictive accuracy. Several psychosocial risk and protective factors have complex interrelationships that influence suicidal ideation. It is possible to predict suicidal risk with high accuracy using this information.

Passive Sensing in the Prediction of Suicidal Thoughts and Behaviors: Protocol for a Systematic Review

BACKGROUND

Suicide is a severe public health problem, resulting in a high number of attempts and deaths each year. Early detection of suicidal thoughts and behaviors (STBs) is key to preventing attempts. We discuss passive sensing of digital and behavioral markers to enhance the detection and prediction of STBs.

OBJECTIVE

The paper presents the protocol for a systematic review that aims to summarize existing research on passive sensing of STBs and evaluate whether the STB prediction can be improved using passive sensing compared to prior prediction models.

METHODS

A systematic search will be conducted in the scientific databases MEDLINE, PubMed, Embase, PsycINFO, and Web of Science. Eligible studies need to investigate any passive sensor data from smartphones or wearables to predict STBs. The predictive value of passive sensing will be the primary outcome. The practical implications and feasibility of the studies will be considered as secondary outcomes. Study quality will be assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). If studies are sufficiently homogenous, we will conduct a meta-analysis of the predictive value of passive sensing on STBs.

RESULTS

The review process started in July 2022 with data extraction in September 2022. Results are expected in December 2022.

CONCLUSIONS

Despite intensive research efforts, the ability to predict STBs is little better than chance. This systematic review will contribute to our understanding of the potential of passive sensing to improve STB prediction. Future research will be stimulated since gaps in the current literature will be identified and promising next steps toward clinical implementation will be outlined.

TRIAL REGISTRATION

OSF Registries osf-registrations-hzxua-v1; https://osf.io/hzxua.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/42146.

Digital phenotyping in psychiatry: A scoping review

BACKGROUND

Digital phenotyping has been defined as the moment-by-moment assessment of an illness state through digital means, promising objective, quantifiable data on psychiatric patients' conditions, and could potentially improve diagnosis and management of mental illness. As it is a rapidly growing field, it is to be expected that new literature is being published frequently.

OBJECTIVE

We conducted this scoping review to assess the current state of literature on digital phenotyping and offer some discussion on the current trends and future direction of this area of research.

METHODS

We searched four databases, PubMed, Ovid MEDLINE, PsycINFO and Web of Science, from inception to August 25th, 2021. We included studies written in English that 1) investigated or applied their findings to diagnose psychiatric disorders and 2) utilized passive sensing for management or diagnosis. Protocols were excluded. A narrative synthesis approach was used, due to the heterogeneity and variability in outcomes and outcome types reported.

RESULTS

Of 10506 unique records identified, we included a total of 107 articles. The number of published studies has increased over tenfold from 2 in 2014 to 28 in 2020, illustrating the field's rapid growth. However, a significant proportion of these (49% of all studies and 87% of primary studies) were proof of concept, pilot or correlational studies examining digital phenotyping's potential. Most (62%) of the primary studies published evaluated individuals with depression (21%), BD (18%) and SZ (23%) (Appendix 1).

CONCLUSION

There is promise shown in certain domains of data and their clinical relevance, which have yet to be fully elucidated. A consensus has yet to be reached on the best methods of data collection and processing, and more multidisciplinary collaboration between physicians and other fields is needed to unlock the full potential of digital phenotyping and allow for statistically powerful clinical trials to prove clinical utility.

Don't Miss the Moment: A Systematic Review of Ecological Momentary Assessment in Suicide Research

Suicide and suicide-related behaviors are prevalent yet notoriously difficult to predict. Specifically, short-term predictors and correlates of suicide risk remain largely unknown. Ecological momentary assessment (EMA) may be used to assess how suicidal thoughts and behaviors (STBs) unfold in real-world contexts. We conducted a systematic literature review of EMA studies in suicide research to assess (1) how EMA has been utilized in the study of STBs (i.e., methodology, findings), and (2) the feasibility, validity and safety of EMA in the study of STBs. We identified 45 articles, detailing 23 studies. Studies mainly focused on examining how known longitudinal predictors of suicidal ideation perform within shorter (hourly, daily) time frames. Recent studies have explored the prospects of digital phenotyping of individuals with suicidal ideation. The results indicate that suicidal ideation fluctuates substantially over time (hours, days), and that individuals with higher mean ideation also have more fluctuations. Higher suicidal ideation instability may represent a phenotypic indicator for increased suicide risk. Few studies succeeded in establishing prospective predictors of suicidal ideation beyond prior ideation itself. Some studies show negative affect, hopelessness and burdensomeness to predict increased ideation within-day, and sleep characteristics to impact next-day ideation. The feasibility of EMA is encouraging: agreement to participate in EMA research was moderate to high (median = 77%), and compliance rates similar to those in other clinical samples (median response rate = 70%). More individuals reported suicidal ideation through EMA than traditional (retrospective) self-report measures. Regarding safety, no evidence was found of systematic reactivity of mood or suicidal ideation to repeated assessments of STBs. In conclusion, suicidal ideation can fluctuate substantially over short periods of time, and EMA is a suitable method for capturing these fluctuations. Some specific predictors of subsequent ideation have been identified, but these findings warrant further replication. While repeated EMA assessments do not appear to result in systematic reactivity in STBs, participant burden and safety remains a consideration when studying high-risk populations. Considerations for designing and reporting on EMA studies in suicide research are discussed.

Geolocation features differentiate healthy from remitted depressed adults

Depression recurrence is debilitating, and there is a pressing need to develop clinical tools that detect the reemergence of symptoms with the aim of bridging patients to treatment before recurrences. At baseline, remitted depressed adults (n = 22) and healthy controls (n = 24) were administered clinical interviews and completed self-report symptom measures. Then, smartphone apps were installed on personal smartphones to acquire geolocation data over 21 days and ecological momentary assessment of positive and negative affect during the initial 14-day period. Compared with healthy controls, remitted depressed adults exhibited reduced circadian routine (regularity of one's daily routine) and lower average daily distance traveled. Further, reduced distance traveled associated with greater daily negative affect after controlling for depression severity; however, this effect was not more pronounced among remitted adults. A least absolute shrinkage and selection operator (LASSO) regression indicated that a linear combination of circadian routine, average distance traveled, and baseline depression severity classified remitted depressed individuals with 72% accuracy; outperforming models restricted to either geolocation or clinical measures alone. Mobile sensing approaches hold enormous promise to improve clinical care for depressive disorders. Although barriers remain, leveraging technological advancements related to real-time monitoring can improve treatment for depressed patients and potentially, reduce high rates of recurrence. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Concurrent and prospective associations between fitbit wearable-derived RDoC arousal and regulatory constructs and adolescent internalizing symptoms

BACKGROUND

Adolescence is characterized by alterations in biobehavioral functioning, during which individuals are at heightened risk for onset of psychopathology, particularly internalizing disorders. Researchers have proposed using digital technologies to index daily biobehavioral functioning, yet there is a dearth of research examining how wearable metrics are associated with mental health.

METHODS

We preregistered analyses using the Adolescent Brain Cognitive Development Study dataset using wearable data collection in 5,686 adolescents (123,862 person-days or 2,972,688 person-hours) to determine whether wearable indices of resting heart rate (RHR), step count, and sleep duration and variability in these measures were cross-sectionally associated with internalizing symptomatology. All models were also run controlling for age, sex, body mass index, socioeconomic status, and race. We then performed prospective analyses on a subset of this sample (n = 143) across 25 months that had Fitbit data available at baseline and follow-up in order to explore directionality of effects.

RESULTS

Cross-sectional analyses revealed a small, yet significant, effect size (R²  = .053) that higher RHR, lower step count and step count variability, and greater variability in sleep duration were associated with greater internalizing symptoms. Cross-lagged panel model analysis revealed that there were no prospective associations between wearable variables and internalizing symptoms (partial R²  = .026), but greater internalizing symptoms and higher RHR predicted lower step count 25 months later (partial R²  = .010), while higher RHR also predicted lower step count variability 25 months later (partial R²  = .008).

CONCLUSIONS

Findings indicate that wearable indices concurrently associate with internalizing symptoms during early adolescence, while a larger sample size is likely required to accurately assess prospective or directional effects between wearable indices and mental health. Future research should capitalize on the temporal resolution provided by wearable devices to determine the intensive longitudinal relations between biobehavioral risk factors and acute changes in mental health.

A Comprehensive Review of the Literature on Sleep Difficulties and Suicidality in Youth to Inform an Integrative Developmental Model and Future Directions

Purpose of Review

Suicide is currently the second leading cause of death among youth. Identification of modifiable near-term risk factors can inform suicide prevention strategies. One promising, readily assessed factor is sleep. We critically review the literature on sleep and suicidal thoughts and behaviors among youth.

Recent Findings

Most studies examining the youth sleep-suicidality relationship are from epidemiological samples in which both sleep problems and suicidality were assessed over variable timeframes using limited items from scales not designed to measure these constructs. Nonetheless, these data overwhelmingly support an association between suicidality and a range of sleep difficulties (e.g., insomnia, short/long sleep, weekend oversleep), above and beyond depressive symptoms. Limited studies include clinical samples or prospective designs. We review potential mechanisms and present a developmentally-informed integrative model.

Summary

Literature supports a clear association between sleep difficulties and youth suicidality. Future directions include prospective longitudinal studies and targeted prevention efforts.

Translating promise into practice: a review of machine learning in suicide research and prevention

In ever more pressured health-care systems, technological solutions offering scalability of care and better resource targeting are appealing. Research on machine learning as a technique for identifying individuals at risk of suicidal ideation, suicide attempts, and death has grown rapidly. This research often places great emphasis on the promise of machine learning for preventing suicide, but overlooks the practical, clinical implementation issues that might preclude delivering on such a promise. In this Review, we synthesise the broad empirical and review literature on electronic health record-based machine learning in suicide research, and focus on matters of crucial importance for implementation of machine learning in clinical practice. The challenge of preventing statistically rare outcomes is well known; progress requires tackling data quality, transparency, and ethical issues. In the future, machine learning models might be explored as methods to enable targeting of interventions to specific individuals depending upon their level of need-ie, for precision medicine. Primarily, however, the promise of machine learning for suicide prevention is limited by the scarcity of high-quality scalable interventions available to individuals identified by machine learning as being at risk of suicide.

Anhedonia and Suicide

Suicide is a leading cause of death, and presently, there is no definitive clinical indicator of future suicide behaviors. Anhedonia, a transdiagnostic symptom reflecting diminished ability to experience pleasure, has recently emerged as a risk factor for suicidal thoughts and behaviors (STBs). This overview, therefore, has the following aims. First, prior research relating anhedonia to STBs will be reviewed, with a particular focus on clarifying whether anhedonia is more closely associated with suicidal thoughts versus behaviors. Second, the National Institute of Mental Health's Research Domain Criteria Positive Valence Systems provide a useful heuristic to probe anhedonia across different units of analysis, including clinical symptoms, behaviors, neural mechanisms, and molecular targets. Accordingly, anhedonia-related constructs linked to STBs will be detailed as well as promising next steps for future research. Third, although anhedonia is not directly addressed in leading suicide theories, this review will provide potential inroads to explore anhedonia within diathesis-stress and interpersonal suicide frameworks. Last, novel approaches to treat anhedonia as a means of reducing STBs will be examined.

Delivering Anticipatory Guidance About Technology Use to Adolescents in Primary Care: Rates in a Representative California Sample

PURPOSE

This study aimed to investigate rates of anticipatory guidance about technology use in primary care, as recommended by the American Academy of Pediatrics Bright Futures Guidelines, in a representative sample of California adolescents.

METHODS

Adolescents 12-17 years of age were interviewed as part of the California Health Interview Survey, the largest state health surveillance survey in the U.S. Participants who reported seeing a doctor for a physical examination or checkup in the prior year were asked if their doctor had talked to them about technology use.

RESULTS

Overall, 29.7% of the 742 participants reported that their doctor talked to them about technology use. There were no statistically significant differences in rates by age, sex, race/ethnicity, household income, or family type.

CONCLUSIONS

While the American Academy of Pediatrics recommends that providers deliver anticipatory guidance about technology use to adolescents in primary care, less than one-third of adolescents surveyed reported having conversations about this topic with their doctor. Given concerns about potential impacts of technology use on adolescent health, medical education should facilitate provider screening and counseling of adolescents about technology use in primary care settings.

Suicide Risk in Emerging Adulthood: Associations with Screen Time over 10 years

Suicide rates have increased over the past decade, and screen media (and social media in particular) are often blamed for this marked increase. However, there is little longitudinal research on this topic. The current study examined the link between various types of screen media use over a 10-year period (from adolescence to emerging adulthood) to suicide risk in emerging adulthood. Participants included 500 adolescents (51% female) who were first surveyed in 2009, when they were an average of 13.82 years old (range 12-15 years). For girls, a high level of social media or television use in early adolescence followed by a marked increase over time was most predictive of suicide risk in emerging adulthood. Additionally, video game use that increased over time was also associated with a higher risk for developing suicide risk for girls. A passive sensing measurement was also included at the final wave of data collection to obtain a more accurate and complete picture of phone use in particular. The use of entertainment apps was risky for girls while reading apps were risky for boys. Additionally, video game use (for boys) was associated with suicide risk when cyberbullying was also high. Identifying nonnormative patterns of media during adolescence may be instructive in terms of suicide prevention efforts.

Opening the Black Box of Daily Life in Nonsuicidal Self-injury Research: With Great Opportunity Comes Great Responsibility

Although nonsuicidal self-injury (NSSI)-deliberate damaging of body tissue without suicidal intent-is a behavior that occurs in interaction with real-world contexts, studying NSSI in the natural environment has historically been impossible. Recent advances in real-time monitoring technologies have revolutionized our ability to do exactly that, providing myriad research and clinical practice opportunities. In this viewpoint paper, we review new research pathways to improve our ability to understand, predict, and prevent NSSI, and provide critical perspectives on the responsibilities inherent to conducting real-time monitoring studies on NSSI. Real-time monitoring brings unique opportunities to advance scientific understanding about (1) the dynamic course of NSSI, (2) the real-time predictors thereof and ability to detect acute risk, (3) the ecological validity of theoretical models, (4) the functional mechanisms and outcomes of NSSI, and (5) the promotion of person-centered care and novel technology-based interventions. By considering the opportunities of real-time monitoring research in the context of the accompanying responsibilities (eg, inclusive recruitment, sound and transparent research practices, participant safety and engagement, measurement reactivity, researcher well-being and training), we provide novel insights and resources to open the black box of daily life in the next decade(s) of NSSI research.

A novel model to predict mental distress among medical graduate students in China

BACKGROUND

Poor mental health was reported among medical graduate students in some studies. Identification of risk factors for predicting the mental health is capable of reducing psychological distress among medical graduate students. Therefore, the aim of the study was to identify potential risk factors relating to mental health and further create a novel prediction model to calculate the risk of mental distress among medical graduate students.

METHODS

This study collected and analyzed 1079 medical graduate students via an online questionnaire. Included participants were randomly classified into a training group and a validation group. A model was developed in the training group and validation of the model was performed in the validation group. The predictive performance of the model was assessed using the discrimination and calibration.

RESULTS

One thousand and fifteen participants were enrolled and then randomly divided into the training group (n = 508) and the validation group (n = 507). The prevalence of severe mental distress was 14.96% in the training group, and 16.77% in the validation group. The model was developed using the six variables, including the year of study, type of student, daily research time, monthly income, scientific learning style, and feeling of time stress. The area under the receiver operating characteristic curve (AUROC) and calibration slope for the model were 0.70 and 0.90 (95% CI: 0.65 ~ 1.15) in the training group, respectively, and 0.66 and 0.80 (95% CI, 0.51 ~ 1.09) in the validation group, respectively.

CONCLUSIONS

The study identified six risk factors for predicting anxiety and depression and successfully created a prediction model. The model may be a useful tool that can identify the mental status among medical graduate students.

TRIAL REGISTRATION

No. ChiCTR2000039574 , prospectively registered on 1 November 2020.

Affective and Autonomic Reactivity During Parent-Child Interactions in Depressed and Non-Depressed Mothers and Their Adolescent Offspring

Depression presents risks that are profound and intergenerational, yet research on the association of depression with the physiological processes that might be associated with impaired mental and physical health has only recently been contextualized within the family environment. Participants in this multi-method case-control study were 180 mother-adolescent dyads (50% mothers with a history of depression treatment and current depressive symptoms). In order to examine the association between maternal depression and affective and autonomic reactivity amongst these mothers and their adolescent offspring we collected self-reported measures of positive and negative affect, as well as measures of cardiovascular and electrodermal autonomic activity, during mother-adolescent interaction tasks. Findings indicated that depressed mothers and their adolescent offspring exhibited greater self-reported negative affect reactivity during a problem-solving interaction and blunted (i.e., low) sympathetic activity as measured via skin conductance level across both interaction tasks. These effects remained significant after controlling for a range of potential covariates, including medication use, sex, age, adolescents own mental health symptoms, and behavior of the other interactant, along with correcting for multiple comparisons. Findings indicate that depressed mothers and their adolescent offspring both exhibit patterns of affect and physiology during interactions that are different from those of non-depressed mothers and their offspring, including increased negative affect reactivity during negative interactions and blunted sympathetic activity across both positive and negative interactions. These findings have potential implications for understanding the role of family processes in the intergenerational transmission of risk for depressive disorders.

Digital Mental Health for Young People: A Scoping Review of Ethical Promises and Challenges

Mental health disorders are complex disorders of the nervous system characterized by a behavioral or mental pattern that causes significant distress or impairment of personal functioning. Mental illness is of particular concern for younger people. The WHO estimates that around 20% of the world's children and adolescents have a mental health condition, a rate that is almost double compared to the general population. One approach toward mitigating the medical and socio-economic effects of mental health disorders is leveraging the power of digital health technology to deploy assistive, preventative, and therapeutic solutions for people in need. We define “digital mental health” as any application of digital health technology for mental health assessment, support, prevention, and treatment. However, there is only limited evidence that digital mental health tools can be successfully implemented in clinical settings. Authors have pointed to a lack of technical and medical standards for digital mental health apps, personalized neurotechnology, and assistive cognitive technology as a possible cause of suboptimal adoption and implementation in the clinical setting. Further, ethical concerns have been raised related to insufficient effectiveness, lack of adequate clinical validation, and user-centered design as well as data privacy vulnerabilities of current digital mental health products. The aim of this paper is to report on a scoping review we conducted to capture and synthesize the growing literature on the promises and ethical challenges of digital mental health for young people aged 0–25. This review seeks to survey the scope and focus of the relevant literature, identify major benefits and opportunities of ethical significance (e.g., reducing suffering and improving well-being), and provide a comprehensive mapping of the emerging ethical challenges. Our findings provide a comprehensive synthesis of the current literature and offer a detailed informative basis for any stakeholder involved in the development, deployment, and management of ethically-aligned digital mental health solutions for young people.

Utility of item 9 of the patient health questionnaire in the prospective identification of adolescents at risk of suicide attempt

INTRODUCTION

Previous studies report that item 9 of the Patient Health Questionnaire (PHQ9) is useful for stratifying risk of suicide attempt in adults. This study re-produced the utility of item 9 of PHQ9 in assessing risk of suicide attempt in adolescents.

MATERIALS AND METHODS

Individuals aged 13 to 17 years in 4 health systems with a diagnosis of depression and history of treatment were included. We estimated time to first observed fatal or non-fatal suicide attempt in the 2 years following completion of a PHQ9, stratified by response to item 9.

RESULTS

There were 51,807 PHQ9 questionnaires for 20,363 youth and 861 instances of suicide attempt. Cumulative probability of suicide attempt ranged from approximately 3.3% (95% CI, 3.0 to 3.5%) for those responding "not at all" on item 9 to 10.8% (95% CI, 9.2 to 12.4%) for those responding "nearly every day". These probabilities are more than 3 times higher than previously reported in adults.

CONCLUSION

PHQ item 9 is useful for stratifying risk of suicide attempt in the 2 years following completion of the questionnaire. Monitoring PHQ item 9 over time for patients in treatment for depression can be useful for population health management of adolescents with depression.

Predicting acute suicidal ideation on Instagram using ensemble machine learning models

INTRODUCTION

Online social networking data (SN) is a contextually and temporally rich data stream that has shown promise in the prediction of suicidal thought and behavior. Despite the clear advantages of this digital medium, predictive modeling of acute suicidal ideation (SI) currently remains underdeveloped. SN data, in conjunction with robust machine learning algorithms, may offer a promising way forward.

METHODS

We applied an ensemble machine learning model on a previously published dataset of adolescents on Instagram with a prior history of lifetime SI (N = 52) to predict SI within the past month. Using predictors that capture language use and activity within this SN, we evaluated the performance of our out-of-sample, cross-validated model against previous efforts and leveraged a model explainer to further probe relative predictor importance and subject-level phenomenology.

RESULTS

Linguistic and SN data predicted acute SI with an accuracy of 0.702 (sensitivity = 0.769, specificity = 0.654, AUC = 0.775). Model introspection showed a higher proportion of SN-derived predictors with substantial impact on prediction compared with linguistic predictors from structured interviews. Further analysis of subject-specific predictor importance uncovered potentially informative trends for future acute SI risk prediction.

CONCLUSION

Application of ensemble learning methodologies to SN data for the prediction of acute SI may mitigate the complexities and modeling challenges of SI that exist within these time scales. Future work is needed on larger, more heterogeneous populations to fine-tune digital biomarkers and more robustly test external validity.

Improving Suicide Prevention Through Evidence-Based Strategies: A Systematic Review

OBJECTIVE

The authors sought to identify scalable evidence-based suicide prevention strategies.

METHODS

A search of PubMed and Google Scholar identified 20,234 articles published between September 2005 and December 2019, of which 97 were randomized controlled trials with suicidal behavior or ideation as primary outcomes or epidemiological studies of limiting access to lethal means, using educational approaches, and the impact of antidepressant treatment.

RESULTS

Training primary care physicians in depression recognition and treatment prevents suicide. Educating youths on depression and suicidal behavior, as well as active outreach to psychiatric patients after discharge or a suicidal crisis, prevents suicidal behavior. Meta-analyses find that antidepressants prevent suicide attempts, but individual randomized controlled trials appear to be underpowered. Ketamine reduces suicidal ideation in hours but is untested for suicidal behavior prevention. Cognitive-behavioral therapy and dialectical behavior therapy prevent suicidal behavior. Active screening for suicidal ideation or behavior is not proven to be better than just screening for depression. Education of gatekeepers about youth suicidal behavior lacks effectiveness. No randomized trials have been reported for gatekeeper training for prevention of adult suicidal behavior. Algorithm-driven electronic health record screening, Internet-based screening, and smartphone passive monitoring to identify high-risk patients are understudied. Means restriction, including of firearms, prevents suicide but is sporadically employed in the United States, even though firearms are used in half of all U.S. suicides.

CONCLUSIONS

Training general practitioners warrants wider implementation and testing in other nonpsychiatrist physician settings. Active follow-up of patients after discharge or a suicide-related crisis should be routine, and restricting firearm access by at-risk individuals warrants wider use. Combination approaches in health care systems show promise in reducing suicide in several countries, but evaluating the benefit attributable to each component is essential. Further suicide rate reduction requires evaluating newer approaches, such as electronic health record-derived algorithms, Internet-based screening methods, ketamine's potential benefit for preventing attempts, and passive monitoring of acute suicide risk change.

Patient electronic communication data in clinical care: what is known and what is needed

The novel coronavirus (COVID-19) and physical distancing guidelines around the world have resulted in unprecedented changes to normal routine and increased smartphone use to maintain social relationships and support. Reports of depressive and anxiety symptom are on the rise, contributing to suffering among people-especially adolescents and young adults-with pre-existing mental health conditions. Psychiatric care has shifted primarily to telehealth limiting the important patient nonverbal communication that has been part of in-person clinical sessions. Supplementing clinical care with patient electronic communication (EC) data may provide valuable information and influence treatment decision making. Research in the impact of patient EC data on managing psychiatric symptoms is in its infancy. This review aims to identify how patient EC has been used in clinical care and its benefits in psychiatry and research. We discuss smartphone applications used to gather different types of EC data, how data have been integrated into clinical care, and implications for clinical care and research.

Evaluating the Impact of Different Symmetrical Models of Ambient Assisted Living Systems

In recent years, numerous attempts have been made to enhance the living standard for old-aged people. Ambient Assisted Living (AAL) is an evolving interdisciplinary field aimed at the exploitation of knowledge and communication technology in health and tele-monitoring systems to combat the impact of the growing aging population. AAL systems are designed for customized, responsive, and predictive requirements, requiring high performance of functionality to ensure interoperability, accessibility, security, and consistency. Standardization, continuity, and assistance of system development have become an urgent necessity to meet the increasing needs for sustainable systems. In this article, we examine and address the methods of the different AAL systems. In addition, we analyzed the acceptance criteria of the AAL framework intending to define and evaluate different AAL-based symmetrical models, leveraging performance characteristics under the integrated fuzzy environment. The main goal is to provide an understanding of the current situation of the AAL-oriented setups. Our vision is to investigate and evaluate the potential symmetrical models of AAL systems and frameworks for the implementation of effective new installations.

Saving Lives: Recognizing and Intervening with Youth at Risk for Suicide

Suicide is the second leading cause of death for youth in the United States. Fortunately, substantial advances have been achieved in identifying and intervening with youth at risk. In this review, we first focus on advances in proactive suicide risk screening and psychoeducation aimed at improving the recognition of suicide risk. These strategies have the potential to improve our ability to recognize and triage youth at risk who may otherwise be missed. We then review recent research on interventions for youth at risk. We consider a broad range of psychotherapeutic interventions, including crisis interventions in emergency care settings. Though empirical support remains limited for interventions targeting suicide risk in youth, effective and promising approaches continue to be identified. We highlight evidence-based screening and intervention approaches as well as challenges in these areas and recommendations for further investigation.

Comparison of causes for suicidal ideation and attempt: Korean Longitudinal Survey of Women and Families

The purpose of this study was to identify factors that influence suicidal ideation and attempts among Korean women, using longitudinal data. Data from wave 4 (n = 7227), wave 5 (n = 6892), and wave 6 (n = 6632) of the Korean Longitudinal Survey of Women and Families collected on 2012, 2014, and 2016 were subjected to Kaplan-Meier and Cox regression analysis. Number of cases for suicidal ideation was 4.7% of the total cases (n = 20,751) between wave 4 through 6; number of cases for suicidal attempts was 5.7% of the cases from suicide ideation (n = 979). Depressive feelings, bad or worst health, and increased stress had significant impacts on suicidal ideation (χ² = 1867.84, p < .001; χ² = 983.61, p < .001; χ² = 884.01, p < .001) and suicidal attempts (χ² = 5.36, p < .05; χ² = 11.19, p < .01; χ² = 7.46, p < .05; χ² = 6.21, p < .05) over time, respectively. From the Cox regression analysis, non-marital status (OR = 2.50, CI = 1.40-4.48) and having more than two children (OR = 2.55, CI = 1.18-5.51) compared to not having children were identified as predictors for suicidal attempt. Although the negative effect of number of children on suicidal attempts conflicts with previous evidence, socially determined mother roles and the significance of children should be considered in culturally sensitive terms when interpreting our findings.

The Role of New Technologies to Prevent Suicide in Adolescence: A Systematic Review of the Literature

Background and objectives: Suicide in adolescents represents a major public health concern. To date, a growing number of suicide preventive strategies based on the use of new technologies are emerging. We aimed to provide an overview of the present literature on the use of new technologies in adolescent suicide prevention. Materials and methods: An electronic search was run using the following keywords: Technology OR Technologies OR APP OR Application OR mobile application) AND (Adolescent OR youth OR puberty) AND (Suicid* OR Self-harm OR self-destruction). Inclusion criteria were: English language, published in a peer-reviewed journal, suicide prevention with the use of new technologies among adolescents. Results: Our search strategy yielded a total of 12 studies on the use of telemedicine, 7 on mobile applications, and 3 on language detection. We also found heterogeneity regarding the study design: 3 are randomized controlled trials (RCT), 13 are open-label single group trials, 2 are randomized studies, and 1 is a cross-sectional study. Telemedicine was the most adopted tool, especially web-based approaches. Mobile applications mostly focused on screening of depressive symptoms and suicidal ideation, and for clinical monitoring through the use of text messages. Although telepsychiatry and mobile applications can provide a fast and safe tool, supporting and preceding a face-to-face clinical assessment, only a few studies demonstrated efficacy in preventing suicide among adolescents through the use of these interventions. Some studies suggested algorithms able to recognize people at risk of suicide from the exploration of the language on social media posts. Conclusions: New technologies were found to be well accepted and tolerated supports for suicide prevention in adolescents. However, to date, few data support the use of such interventions in clinical practice and preventive strategies. Further studies are needed to test their efficacy in suicide prevention among adolescents and young adults.

Neural Correlates Associated With Suicide and Nonsuicidal Self-injury in Youth

There is no definitive neural marker of suicidal thoughts and behaviors (STBs) or nonsuicidal self-injury (NSSI), and relative to adults, research in youth is more limited. This comprehensive review focuses on magnetic resonance imaging studies reporting structural and functional neural correlates of STBs and NSSI in youth to 1) elucidate shared and independent neural alternations, 2) clarify how developmental processes may interact with neural alterations to confer risk, and 3) provide recommendations based on convergence across studies. Forty-seven articles were reviewed (STBs = 27; NSSI = 20), and notably, 63% of STB articles and 45% of NSSI articles were published in the previous 3 years. Structural magnetic resonance imaging research suggests reduced volume in the ventral prefrontal and orbitofrontal cortices among youth reporting STBs, and there is reduced anterior cingulate cortex volume related to STBs and NSSI. With regard to functional alterations, blunted striatal activation may characterize STB and NSSI youth, and there is reduced frontolimbic task-based connectivity in suicide ideators and attempters. Resting-state functional connectivity findings highlight reduced positive connectivity between the default mode network and salience network in attempters and show that self-injurers exhibit frontolimbic alterations. Together, suicidal and nonsuicidal behaviors are related to top-down and bottom-up neural alterations, which may compromise approach, avoidance, and regulatory systems. Future longitudinal research with larger and well-characterized samples, especially those integrating ambulatory stress assessments, will be well positioned to identify novel targets that may improve early identification and treatment for youth with STBs and NSSI.

Digital Phenotyping of Emotion Dysregulation Across Lifespan Transitions to Better Understand Psychopathology Risk

Ethical and consensual digital phenotyping through smartphone activity (i. e., passive behavior monitoring) permits measurement of temporal risk trajectories unlike ever before. This data collection modality may be particularly well-suited for capturing emotion dysregulation, a transdiagnostic risk factor for psychopathology, across lifespan transitions. Adolescence, emerging adulthood, and perinatal transitions are particularly sensitive developmental periods, often marked by increased distress. These participant groups are typically assessed with laboratory-based methods that can be costly and burdensome. Passive monitoring presents a relatively cost-effective and unobtrusive way to gather rich and objective information about emotion dysregulation and risk behaviors. We first discuss key theoretically-driven concepts pertaining to emotion dysregulation and passive monitoring. We then identify variables that can be measured passively and hold promise for better understanding emotion dysregulation. For example, two strong markers of emotion dysregulation are sleep disturbance and problematic use of Internet/social media (i.e., use that prompts negative emotions/outcomes). Variables related to mobility are also potentially useful markers, though these variables should be tailored to fit unique features of each developmental stage. Finally, we offer our perspective on candidate digital variables that may prove useful for each developmental transition. Smartphone-based passive monitoring is a rigorous method that can elucidate psychopathology risk across human development. Nonetheless, its use requires researchers to weigh unique ethical considerations, examine relevant theory, and consider developmentally-specific lifespan features that may affect implementation.

Predicting suicide attempt or suicide death following a visit to psychiatric specialty care: A machine learning study using Swedish national registry data

BACKGROUND

Suicide is a major public health concern globally. Accurately predicting suicidal behavior remains challenging. This study aimed to use machine learning approaches to examine the potential of the Swedish national registry data for prediction of suicidal behavior.

METHODS AND FINDINGS

The study sample consisted of 541,300 inpatient and outpatient visits by 126,205 Sweden-born patients (54% female and 46% male) aged 18 to 39 (mean age at the visit: 27.3) years to psychiatric specialty care in Sweden between January 1, 2011 and December 31, 2012. The most common psychiatric diagnoses at the visit were anxiety disorders (20.0%), major depressive disorder (16.9%), and substance use disorders (13.6%). A total of 425 candidate predictors covering demographic characteristics, socioeconomic status (SES), electronic medical records, criminality, as well as family history of disease and crime were extracted from the Swedish registry data. The sample was randomly split into an 80% training set containing 433,024 visits and a 20% test set containing 108,276 visits. Models were trained separately for suicide attempt/death within 90 and 30 days following a visit using multiple machine learning algorithms. Model discrimination and calibration were both evaluated. Among all eligible visits, 3.5% (18,682) were followed by a suicide attempt/death within 90 days and 1.7% (9,099) within 30 days. The final models were based on ensemble learning that combined predictions from elastic net penalized logistic regression, random forest, gradient boosting, and a neural network. The area under the receiver operating characteristic (ROC) curves (AUCs) on the test set were 0.88 (95% confidence interval [CI] = 0.87-0.89) and 0.89 (95% CI = 0.88-0.90) for the outcome within 90 days and 30 days, respectively, both being significantly better than chance (i.e., AUC = 0.50) (p < 0.01). Sensitivity, specificity, and predictive values were reported at different risk thresholds. A limitation of our study is that our models have not yet been externally validated, and thus, the generalizability of the models to other populations remains unknown.

CONCLUSIONS

By combining the ensemble method of multiple machine learning algorithms and high-quality data solely from the Swedish registers, we developed prognostic models to predict short-term suicide attempt/death with good discrimination and calibration. Whether novel predictors can improve predictive performance requires further investigation.

Exploring Suicidal Ideation Using an Innovative Mobile App-Strength Within Me: The Usability and Acceptability of Setting up a Trial Involving Mobile Technology and Mental Health Service Users

BACKGROUND

Suicide is a growing global public health problem that has resulted in an increase in the demand for psychological services to address mental health issues. It is expected that 1 in 6 people on a waiting list for mental health services will attempt suicide. Although suicidal ideation has been shown to be linked to a higher risk of death by suicide, not everybody openly discloses their suicidal thoughts or plans to friends and family or seeks professional help before suicide. Therefore, new methods are needed to track suicide risk in real time together with a better understanding of the ways in which people communicate or express their suicidality. Considering the dynamic nature and challenges in understanding suicide ideation and suicide risk, mobile apps could be better suited to prevent suicide as they have the ability to collect real-time data.

OBJECTIVE

This study aims to report the practicalities and acceptability of setting up and trialing digital technologies within an inpatient mental health setting in the United Kingdom and highlight their implications for future studies.

METHODS

Service users were recruited from 6 inpatient wards in the north west of England. Service users who were eligible to participate and provided consent were given an iPhone and Fitbit for 7 days and were asked to interact with a novel phone app, Strength Within Me (SWiM). Interaction with the app involved journaling (recording daily activities, how this made them feel, and rating their mood) and the option to create safety plans for emotions causing difficulties (identifying strategies that helped with these emotions). Participants also had the option to allow the study to access their personal Facebook account to monitor their social media use and activity. In addition, clinical data (ie, assessments conducted by trained researchers targeting suicidality, depression, and sleep) were also collected.

RESULTS

Overall, 43.0% (80/186 response rate) of eligible participants were recruited for the study. Of the total sample, 67 participants engaged in journaling, with the average number of entries per user being 8.2 (SD 8.7). Overall, only 24 participants created safety plans and the most common difficult emotion to be selected was feeling sad (n=21). This study reports on the engagement with the SWiM app, the technical difficulties the research team faced, the importance of building key relationships, and the implications of using Facebook as a source to detect suicidality.

CONCLUSIONS

To develop interventions that can be delivered in a timely manner, prediction of suicidality must be given priority. This paper has raised important issues and highlighted lessons learned from implementing a novel mobile app to detect the risk of suicidality for service users in an inpatient setting.

Adolescent suicide: what can pediatricians do?

PURPOSE OF REVIEW

Suicide is a major public health concern and the second leading cause of death for adolescents. Faced with an already-high prevalence and increasing rates over the past decade, pediatricians feel inadequately prepared to manage a suicidal patient. This article will review the changing rates of suicide, discuss recent literature on risk factors, identify methods to screen for suicidal thoughts and suggest an approach to counseling a suicidal patient. Finally, there will be a brief discussion on safety planning and public health measures to help reduce suicide rates.

RECENT FINDINGS

Rates of attempted suicide and death by suicide have been increasing for more than a decade. Risk assessment of potential suicidality remains very challenging, as the risk factors are multifactorial. However, some common risk factors persist including sexual minority identification and family or personal history of mental health issues. Although keeping these and other risk factors in mind, regular screening of adolescents for depression and self-harm is important. Finally, the best safety plans and treatment methods appear to be team-based.

SUMMARY

It remains the responsibility of pediatricians to stay aware of risk factors, regularly screen adolescents and prioritize collaborative safety planning for suicidal patients.

Technology Use for Adolescent Health and Wellness

As avid users of technology, adolescents are a key demographic to engage when designing and developing technology applications for health. There are multiple opportunities for improving adolescent health, from promoting preventive behaviors to providing guidance for adolescents with chronic illness in supporting treatment adherence and transition to adult health care systems. This article will provide a brief overview of current technologies and then highlight new technologies being used specifically for adolescent health, such as artificial intelligence, virtual and augmented reality, and machine learning. Because there is paucity of evidence in this field, we will make recommendations for future research.