BACKGROUND: The war in Syria has displaced over 6.8 million people, more than any other conflict since the Second World War. As a result, Syrian asylum seekers and refugees have experienced several life-changing events, resulting in high rates of anxiety, depression, posttraumatic stress disorder, and suicidal ideation (SI). To address the treatment gap and reduce the burden of help-seeking, a web-based intervention to reduce SI developed for general populations was culturally adapted for and with Syrian asylum seekers and refugees in the United Kingdom. The study revealed the importance of understanding their lived experience with migration and the acculturative process in providing treatment for SI. This study will now assess the feasibility and acceptability of the culturally adapted intervention for this population.
OBJECTIVE: The first phase of the study will include recruiting participants and delivering the web-based intervention (1) to assess the feasibility of meeting recruitment goals and recruitment rates and (2) to assess the feasibility of outcome measures. The second phase of the study will include one-to-one semistructured interviews (1) to assess the suitability of the culturally adapted intervention in terms of recruitment and adherence rates and barriers and facilitators to engagement and (2) to assess the acceptability of the intervention in terms of its cultural relevance and appropriateness.
METHODS: This is a protocol for a single-group, noncontrolled, mixed methods feasibility and acceptability study of a culturally adapted web-based intervention to reduce SI for Syrian asylum seekers and refugees in the United Kingdom. The study will assess the feasibility of recruitment goals, recruitment rates, adherence rates, and outcome measures using individual participant tracking forms, which will be analyzed quantitatively. The suitability and acceptability of the intervention will be assessed using one-to-one semistructured interviews with 12 participants who completed the intervention, which will be analyzed qualitatively.
RESULTS: Recruitment began in February 2024 and will run until 30 participants are recruited to the study or until the end of July 2024. Thus far, 19 participants have provided informed consent, 16 were eligible and enrolled, and 12 have completed a postintervention interview. No data have been analyzed. The study, including the write-up period, is expected to end in December 2024.
CONCLUSIONS: Despite experiencing several stressors related to forced displacement and high rates of mental health issues, access to treatment is still limited for Syrian asylum seekers and refugees in the United Kingdom. To address the treatment gap and reduce the burden of help-seeking, a web-based intervention to reduce SI was culturally adapted in collaboration with Syrian asylum seekers and refugees in the United Kingdom. This study will now assess the feasibility and acceptability of the intervention and culturally appropriate recruitment strategies.
BACKGROUND: ISRCTN ISRCTN11417025; https://www.isrctn.com/ISRCTN11417025.
UNASSIGNED: PRR1-10.2196/56957.

BACKGROUND: Self-injurious thoughts and behaviors (SITBs) are increasing dramatically among children and adolescents. Crisis support is intended to provide immediate mental health care, risk mitigation, and intervention for those experiencing SITBs and acute mental health distress. Digital mental health interventions (DMHIs) have emerged as accessible and effective alternatives to in-person care; however, most do not provide crisis support or ongoing care for children and adolescents with SITBs.
OBJECTIVE: To inform the development of digital crisis support and mental health care for children and adolescents presenting with SITBs, this study aims to (1) characterize children and adolescents with SITBs who participate in a digital crisis response service, (2) compare anxiety and depressive symptoms of children and adolescents presenting with SITBs versus those without SITBs throughout care, and (3) suggest future steps for the implementation of digital crisis support and mental health care for children and adolescents presenting with SITBs.
METHODS: This retrospective study was conducted using data from children and adolescents (aged 1-17 y; N=2161) involved in a pediatric collaborative care DMHI. SITB prevalence was assessed during each live session. For children and adolescents who exhibited SITBs during live sessions, a rapid crisis support team provided evidence-based crisis support services. Assessments were completed approximately once a month to measure anxiety and depressive symptom severity. Demographics, mental health symptoms, and change in the mental health symptoms of children and adolescents presenting with SITBs (group with SITBs) were compared to those of children and adolescents with no SITBs (group without SITBs).
RESULTS: Compared to the group without SITBs (1977/2161, 91.49%), the group with SITBs (184/2161, 8.51%) was mostly made up of adolescents (107/184, 58.2%) and female children and adolescents (118/184, 64.1%). At baseline, compared to the group without SITBs, the group with SITBs had more severe anxiety and depressive symptoms. From before to after mental health care with the DMHI, the 2 groups did not differ in the rate of children and adolescents with anxiety symptom improvement (group with SITBs: 54/70, 77% vs group without SITBs: 367/440, 83.4%; χ21=1.2; P=.32) as well as depressive symptom improvement (group with SITBs: 58/72, 81% vs group without SITBs: 255/313, 81.5%; χ21=0; P=.99). The 2 groups also did not differ in the amount of change in symptom severity during care with the DMHI for anxiety (t80.20=1.37; P=.28) and depressive (t83.75=-0.08; P=.99) symptoms.
CONCLUSIONS: This study demonstrates that participation in a collaborative care DMHI is associated with improved mental health outcomes in children and adolescents experiencing SITBs. These results provide preliminary insights for the use of pediatric DMHIs in crisis support and mental health care for children and adolescents presenting with SITBs, thereby addressing the public health issue of acute mental health crisis in children and adolescents.

BACKGROUND: Due to recent advances in artificial intelligence, large language models (LLMs) have emerged as a powerful tool for a variety of language-related tasks, including sentiment analysis, and summarization of provider-patient interactions. However, there is limited research on these models in the area of crisis prediction.
OBJECTIVE: This study aimed to evaluate the performance of LLMs, specifically OpenAI\'s generative pretrained transformer 4 (GPT-4), in predicting current and future mental health crisis episodes using patient-provided information at intake among users of a national telemental health platform.
METHODS: Deidentified patient-provided data were pulled from specific intake questions of the Brightside telehealth platform, including the chief complaint, for 140 patients who indicated suicidal ideation (SI), and another 120 patients who later indicated SI with a plan during the course of treatment. Similar data were pulled for 200 randomly selected patients, treated during the same time period, who never endorsed SI. In total, 6 senior Brightside clinicians (3 psychologists and 3 psychiatrists) were shown patients\' self-reported chief complaint and self-reported suicide attempt history but were blinded to the future course of treatment and other reported symptoms, including SI. They were asked a simple yes or no question regarding their prediction of endorsement of SI with plan, along with their confidence level about the prediction. GPT-4 was provided with similar information and asked to answer the same questions, enabling us to directly compare the performance of artificial intelligence and clinicians.
RESULTS: Overall, the clinicians\' average precision (0.7) was higher than that of GPT-4 (0.6) in identifying the SI with plan at intake (n=140) versus no SI (n=200) when using the chief complaint alone, while sensitivity was higher for the GPT-4 (0.62) than the clinicians\' average (0.53). The addition of suicide attempt history increased the clinicians\' average sensitivity (0.59) and precision (0.77) while increasing the GPT-4 sensitivity (0.59) but decreasing the GPT-4 precision (0.54). Performance decreased comparatively when predicting future SI with plan (n=120) versus no SI (n=200) with a chief complaint only for the clinicians (average sensitivity=0.4; average precision=0.59) and the GPT-4 (sensitivity=0.46; precision=0.48). The addition of suicide attempt history increased performance comparatively for the clinicians (average sensitivity=0.46; average precision=0.69) and the GPT-4 (sensitivity=0.74; precision=0.48).
CONCLUSIONS: GPT-4, with a simple prompt design, produced results on some metrics that approached those of a trained clinician. Additional work must be done before such a model can be piloted in a clinical setting. The model should undergo safety checks for bias, given evidence that LLMs can perpetuate the biases of the underlying data on which they are trained. We believe that LLMs hold promise for augmenting the identification of higher-risk patients at intake and potentially delivering more timely care to patients.

UNASSIGNED: There is growing concern around the use of sodium nitrite (SN) as an emerging means of suicide, particularly among younger people. Given the limited information on the topic from traditional public health surveillance sources, we studied posts made to an online suicide discussion forum, \"Sanctioned Suicide,\" which is a primary source of information on the use and procurement of SN.
UNASSIGNED: This study aims to determine the trends in SN purchase and use, as obtained via data mining from subscriber posts on the forum. We also aim to determine the substances and topics commonly co-occurring with SN, as well as the geographical distribution of users and sources of SN.
UNASSIGNED: We collected all publicly available from the site\'s inception in March 2018 to October 2022. Using data-driven methods, including natural language processing and machine learning, we analyzed the trends in SN mentions over time, including the locations of SN consumers and the sources from which SN is procured. We developed a transformer-based source and location classifier to determine the geographical distribution of the sources of SN.
UNASSIGNED: Posts pertaining to SN show a rise in popularity, and there were statistically significant correlations between real-life use of SN and suicidal intent when compared to data from the Centers for Disease Control and Prevention (CDC) Wide-Ranging Online Data for Epidemiologic Research (⍴=0.727; P<.001) and the National Poison Data System (⍴=0.866; P=.001). We observed frequent co-mentions of antiemetics, benzodiazepines, and acid regulators with SN. Our proposed machine learning-based source and location classifier can detect potential sources of SN with an accuracy of 72.92% and showed consumption in the United States and elsewhere.
UNASSIGNED: Vital information about SN and other emerging mechanisms of suicide can be obtained from online forums.

Suicide remains a major public health problem, with nearly 1 million deaths per year. The number tends to increase over time and factors leading to suicide suicidal behaviors are complex. However, there is a paucity of evidence on suicidal behaviors and the associated factors among people living with HIV (PLWH) in Indonesia. Therefore, this study aimed to estimate the prevalence and associated factors of suicidal behavior between indigenous and non-indigenous living with HIV who were on Dolutegravir and Efavirenz therapies. The cross-sectional data were collected using questionnaires. Participants completed the Suicidal Behaviors Questionnaire-Revised (SBQ-R), Depression Anxiety Stress Scale-42 (DASS-42), HIV Stigma-Sowell Scale, and demographic information questions. The outcome was low and high self-reported suicidal behaviors, while logistic regression analyses were used to estimate adjusted odds ratios (aOR) for associated factors of high suicidal behaviors. A total of 200 PLWH were enrolled and 8.5% of the participants had high levels of suicidal behaviors. The majority of participants were Efavirenz users (84.0%), and Papuans as Indigenous (75.5%). More than half had a high school education (60.5%), were female (58%), married (54%), and unpaid (59%). The multiple logistic regression model showed that indigenous (aOR = 0.122; 95% CI = 0.029-0.514), and people who had children (aOR = 0.221; 95% CI = 0.051-0.957) were more likely to have low suicidal behaviors. Participants who were aged 18-27 years (aOR = 5.894; 95% CI = 1.336-30.579), had high self-blame (aOR = 1.342; 95% CI) = 1.004-1.792), and detectable HIV viral load (aOR = 6.177; 95%CI = 1.118-34.119) had high suicidal behavior. This study identified the risk of suicidality among PLWHs is high and routine suicide assessment is prioritized. The findings are also useful for intervention design and the development of clinical practice guidelines to manage the well-being of PLWH such as using digital intervention to cope with hindrances.

BACKGROUND: Given that signage, messaging, and advertisements (ads) are the gateway to many interventions in suicide prevention, it is important that we understand what type of messaging works best for whom.
OBJECTIVE: We investigated whether explicitly mentioning suicide increases engagement using internet ads by investigating engagement with campaigns with different categories of keywords searched, which may reflect different cognitive states.
METHODS: We ran a 2-arm study Australia-wide, with or without ads featuring explicit suicide wording. We analyzed whether there were differences in engagement for campaigns with explicit and nonexplicit ads for low-risk (distressed but not explicitly suicidal), high-risk (explicitly suicidal), and help-seeking for suicide keywords.
RESULTS: Our analyses revealed that having explicit wording has opposite effects, depending on the search terms used: explicit wording reduced the engagement rate for individuals searching for low-risk keywords but increased engagement for those using high-risk keywords.
CONCLUSIONS: The findings suggest that individuals who are aware of their suicidality respond better to campaigns that explicitly use the word \"suicide.\" We found that individuals who search for low-risk keywords also respond to explicit ads, suggesting that some individuals who are experiencing suicidality search for low-risk keywords.

BACKGROUND: Prior suicide attempts are a relatively strong risk factor for future suicide attempts. There is growing interest in using longitudinal electronic health record (EHR) data to derive statistical risk prediction models for future suicide attempts and other suicidal behavior outcomes. However, model performance may be inflated by a largely unrecognized form of \"data leakage\" during model training: diagnostic codes for suicide attempt outcomes may refer to prior attempts that are also included in the model as predictors.
OBJECTIVE: We aimed to develop an automated rule for determining when documented suicide attempt diagnostic codes identify distinct suicide attempt events.
METHODS: From a large health care system\'s EHR, we randomly sampled suicide attempt codes for 300 patients with at least one pair of suicide attempt codes documented at least one but no more than 90 days apart. Supervised chart reviewers assigned the clinical settings (ie, emergency department [ED] versus non-ED), methods of suicide attempt, and intercode interval (number of days). The probability (or positive predictive value) that the second suicide attempt code in a given pair of codes referred to a distinct suicide attempt event from its preceding suicide attempt code was calculated by clinical setting, method, and intercode interval.
RESULTS: Of 1015 code pairs reviewed, 835 (82.3%) were nonindependent (ie, the 2 codes referred to the same suicide attempt event). When the second code in a pair was documented in a clinical setting other than the ED, it represented a distinct suicide attempt 3.3% of the time. The more time elapsed between codes, the more likely the second code in a pair referred to a distinct suicide attempt event from its preceding code. Code pairs in which the second suicide attempt code was assigned in an ED at least 5 days after its preceding suicide attempt code had a positive predictive value of 0.90.
CONCLUSIONS: EHR-based suicide risk prediction models that include International Classification of Diseases codes for prior suicide attempts as a predictor may be highly susceptible to bias due to data leakage in model training. We derived a simple rule to distinguish codes that reflect new, independent suicide attempts: suicide attempt codes documented in an ED setting at least 5 days after a preceding suicide attempt code can be confidently treated as new events in EHR-based suicide risk prediction models. This rule has the potential to minimize upward bias in model performance when prior suicide attempts are included as predictors in EHR-based suicide risk prediction models.

BACKGROUND: Emergency departments (EDs) manage many patients with suicide risk, but effective interventions for suicidality are challenging to implement in this setting. ReachCare is a technology-facilitated version of an evidence-based intervention for suicidal ED patients. Here, we present findings on the acceptability and quality of ReachCare in the ED, as well as a comparison of these measures across 3 potential delivery modalities.
OBJECTIVE: Our aim was to test the feasibility of the ReachCare intervention in its entirety through conducting a pilot study with patients presenting with suicidality to the ED. We tested three different ways of receiving the ED-based components of ReachCare: (1) self-administered on the tablet app using a chatbot interface, (2) administered by an in-person clinician, or (3) administered by a telehealth clinician.
METHODS: In total, 47 ED patients who screened positive for suicide risk were randomly allocated to receive one of three delivery modalities of ReachCare in the ED: (1) self-administered on the patient-facing tablet app with a chatbot interface, (2) delivered by an in-person clinician, or (3) delivered by a telehealth clinician, with the latter two using a clinician-facing web app. We measured demographic and clinical characteristics, acceptability and appropriateness of the intervention, and quality and completeness of the resulting safety plans.
RESULTS: Patients assigned high ratings for the acceptability (median 4.00/5, IQR 4.00-4.50) and appropriateness (median 4.00/5, IQR 4.00-4.25) of ReachCare\'s ED components, and there were no substantial differences across the 3 delivery modalities [H(acceptability)=3.90, P=.14; H(appropriateness)=1.05, P=.59]. The self-administered modality took significantly less time than the 2 clinician modalities (H=27.91, P<.001), and the usability of the self-administered version was in the \"very high\" range (median 93.75/100, IQR 80.00-97.50). The safety plans created across all 3 modalities were high-quality (H=0.60, P=.74).
CONCLUSIONS: Patients rated ReachCare in the ED as highly acceptable and appropriate regardless of modality. Self-administration may be a feasible way to ensure patients with suicide risk receive an intervention in resource constrained EDs. Limitations include small sample size and demographic differences between those enrolled versus not enrolled. Further research will examine the clinical outcomes of patients receiving both the in-ED and post-ED components of ReachCare.
BACKGROUND: ClinicalTrials.gov NCT04720911; https://clinicaltrials.gov/ct2/show/NCT04720911.

BACKGROUND: Digital formats have the potential to enhance accessibility to care for individuals with suicidal ideation. However, digital self-help interventions have faced limitations, including small effect sizes in reducing suicidal ideation, low adherence, and safety concerns.
OBJECTIVE: Therefore, we aimed to develop a remote blended cognitive behavioral therapy intervention that specifically targets suicidal ideation by blending video therapy with web-based self-help modules. The objective of this paper is to describe the collaborative development process and the resulting intervention and treatment rationale.
METHODS: First, we compiled intervention components from established treatment manuals designed for people with suicidal ideation or behavior, resulting in the development of 11 drafts of web-based modules. Second, we conducted a qualitative study, involving 5 licensed psychotherapists and 3 lay counselors specialized in individuals with suicidal ideation who reviewed these module drafts. Data were collected using the think-aloud method and semistructured interviews, and a qualitative content analysis was performed. The 4 a priori main categories of interest were blended care for individuals with suicidal ideation, contents of web-based modules, usability of modules, and layout. Subcategories emerged inductively from the interview transcripts. Finally, informed by previous treatment manuals and qualitative findings, we developed the remote blended treatment program.
RESULTS: The participants suggested that therapists should thoroughly prepare the web-based therapy with patients to tailor the therapy to each individual\'s needs. Participants emphasized that the web-based modules should explain concepts in a simple manner, convey empathy and validation, and include reminders for the safety plan. In addition, participants highlighted the need for a simple navigation and layout. Taking these recommendations into account, we developed a fully remote blended cognitive behavioral therapy intervention comprising 12 video therapy sessions and up to 31 web-based modules. The treatment involves collaboratively developing a personalized treatment plan to address individual suicidal drivers.
CONCLUSIONS: This remote treatment takes advantage of the high accessibility of digital formats while incorporating full sessions with a therapist. In a subsequent pilot trial, we will seek input from individuals with lived experience and therapists to test the feasibility of the treatment.

BACKGROUND: ChatGPT, a linguistic artificial intelligence (AI) model engineered by OpenAI, offers prospective contributions to mental health professionals. Although having significant theoretical implications, ChatGPT\'s practical capabilities, particularly regarding suicide prevention, have not yet been substantiated.
OBJECTIVE: The study\'s aim was to evaluate ChatGPT\'s ability to assess suicide risk, taking into consideration 2 discernable factors-perceived burdensomeness and thwarted belongingness-over a 2-month period. In addition, we evaluated whether ChatGPT-4 more accurately evaluated suicide risk than did ChatGPT-3.5.
METHODS: ChatGPT was tasked with assessing a vignette that depicted a hypothetical patient exhibiting differing degrees of perceived burdensomeness and thwarted belongingness. The assessments generated by ChatGPT were subsequently contrasted with standard evaluations rendered by mental health professionals. Using both ChatGPT-3.5 and ChatGPT-4 (May 24, 2023), we executed 3 evaluative procedures in June and July 2023. Our intent was to scrutinize ChatGPT-4\'s proficiency in assessing various facets of suicide risk in relation to the evaluative abilities of both mental health professionals and an earlier version of ChatGPT-3.5 (March 14 version).
RESULTS: During the period of June and July 2023, we found that the likelihood of suicide attempts as evaluated by ChatGPT-4 was similar to the norms of mental health professionals (n=379) under all conditions (average Z score of 0.01). Nonetheless, a pronounced discrepancy was observed regarding the assessments performed by ChatGPT-3.5 (May version), which markedly underestimated the potential for suicide attempts, in comparison to the assessments carried out by the mental health professionals (average Z score of -0.83). The empirical evidence suggests that ChatGPT-4\'s evaluation of the incidence of suicidal ideation and psychache was higher than that of the mental health professionals (average Z score of 0.47 and 1.00, respectively). Conversely, the level of resilience as assessed by both ChatGPT-4 and ChatGPT-3.5 (both versions) was observed to be lower in comparison to the assessments offered by mental health professionals (average Z score of -0.89 and -0.90, respectively).
CONCLUSIONS: The findings suggest that ChatGPT-4 estimates the likelihood of suicide attempts in a manner akin to evaluations provided by professionals. In terms of recognizing suicidal ideation, ChatGPT-4 appears to be more precise. However, regarding psychache, there was an observed overestimation by ChatGPT-4, indicating a need for further research. These results have implications regarding ChatGPT-4\'s potential to support gatekeepers, patients, and even mental health professionals\' decision-making. Despite the clinical potential, intensive follow-up studies are necessary to establish the use of ChatGPT-4\'s capabilities in clinical practice. The finding that ChatGPT-3.5 frequently underestimates suicide risk, especially in severe cases, is particularly troubling. It indicates that ChatGPT may downplay one\'s actual suicide risk level.