Dataset Information

National Suicide Prevention Lifeline crisis chat interventions: Evaluation of chatters' perceptions of effectiveness.

ABSTRACT:

Objective

As part of the National Suicide Prevention Lifeline's crisis response system, the Lifeline Crisis Chat Network (LCC) answers chats from hundreds of thousands of at-risk individuals yearly. The study's objective was to assess the effectiveness of these online crisis interventions.

Method

Data from 39,911 pre-chat surveys and 13,130 linked pre- and post-chat surveys completed by LCC chatters from October 2017-June 2018 were analyzed. The relationship of several effectiveness measures with chatter demographics, pre-chat distress, suicidal ideation, and chatters' perceptions of engagement with their counselors was examined using a series of logistic regression analyses.

Results

Chatters were significantly and substantially less distressed at the end of the chat intervention than at the beginning. By the end of the chat, two-thirds of suicidal chatters reported that the chat had been helpful, while just under half reported being less suicidal.

Conclusions

Our study offers empirical evidence for the Lifeline's online crisis chat services' effectiveness, but also highlights areas for improvement. This is of critical import in light of the recent designation of 988 as the nationwide number for the Lifeline beginning in 2022, which will increase the Lifeline's prominence in providing suicide prevention and mental health crisis interventions in the United States.

SUBMITTER: Gould MS

PROVIDER: S-EPMC9292033 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundThe working environment of a suicide prevention helpline requires high emotional and cognitive awareness from chat counselors. A shared opinion among counselors is that as a chat conversation becomes more difficult, it takes more effort and a longer amount of time to compose a response, which, in turn, can lead to writer's block.ObjectiveThis study evaluates and then designs supportive technology to determine if a support system that provides inspiration can help counselors resolve writer's block when they encounter difficult situations in chats with help-seekers.MethodsA content-based recommender system with sentence embedding was used to search a chat corpus for similar chat situations. The system showed a counselor the most similar parts of former chat conversations so that the counselor would be able to use approaches previously taken by their colleagues as inspiration. In a within-subject experiment, counselors' chat replies when confronted with a difficult situation were analyzed to determine if experts could see a noticeable difference in chat replies that were obtained in 3 conditions: (1) with the help of the support system, (2) with written advice from a senior counselor, or (3) when receiving no help. In addition, the system's utility and usability were measured, and the validity of the algorithm was examined.ResultsA total of 24 counselors used a prototype of the support system; the results showed that, by reading chat replies, experts were able to significantly predict if counselors had received help from the support system or from a senior counselor (P=.004). Counselors scored the information they received from a senior counselor (M=1.46, SD 1.91) as significantly more helpful than the information received from the support system or when no help was given at all (M=-0.21, SD 2.26). Finally, compared with randomly selected former chat conversations, counselors rated the ones identified by the content-based recommendation system as significantly more similar to their current chats (?=.30, P<.001).ConclusionsSupport given to counselors influenced how they responded in difficult conversations. However, the higher utility scores given for the advice from senior counselors seem to indicate that specific actionable instructions are preferred. We expect that these findings will be beneficial for developing a system that can use similar chat situations to generate advice in a descriptive style, hence helping counselors through writer's block.

Project description:BackgroundWith the rise of computer science and artificial intelligence, analyzing large data sets promises enormous potential in gaining insights for developing and improving evidence-based health interventions. One such intervention is the counseling strategy motivational interviewing (MI), which has been found effective in improving a wide range of health-related behaviors. Despite the simplicity of its principles, MI can be a challenging skill to learn and requires expertise to apply effectively.ObjectiveThis study aims to investigate the performance of artificial intelligence models in classifying MI behavior and explore the feasibility of using these models in online helplines for mental health as an automated support tool for counselors in clinical practice.MethodsWe used a coded data set of 253 MI counseling chat sessions from the 113 Suicide Prevention helpline. With 23,982 messages coded with the MI Sequential Code for Observing Process Exchanges codebook, we trained and evaluated 4 machine learning models and 1 deep learning model to classify client- and counselor MI behavior based on language use.ResultsThe deep learning model BERTje outperformed all machine learning models, accurately predicting counselor behavior (accuracy=0.72, area under the curve [AUC]=0.95, Cohen κ=0.69). It differentiated MI congruent and incongruent counselor behavior (AUC=0.92, κ=0.65) and evocative and nonevocative language (AUC=0.92, κ=0.66). For client behavior, the model achieved an accuracy of 0.70 (AUC=0.89, κ=0.55). The model's interpretable predictions discerned client change talk and sustain talk, counselor affirmations, and reflection types, facilitating valuable counselor feedback.ConclusionsThe results of this study demonstrate that artificial intelligence techniques can accurately classify MI behavior, indicating their potential as a valuable tool for enhancing MI proficiency in online helplines for mental health. Provided that the data set size is sufficiently large with enough training samples for each behavioral code, these methods can be trained and applied to other domains and languages, offering a scalable and cost-effective way to evaluate MI adherence, accelerate behavioral coding, and provide therapists with personalized, quick, and objective feedback.

Project description:BackgroundDigital interventions are proposed as one way by which effective treatments for self-harm and suicidal ideation may be improved and their scalability enhanced. Mobile devices offer a potentially powerful medium to deliver evidence-based interventions with greater specificity to the individual when the intervention is needed. The recent proliferation of publicly available mobile apps designed for suicide prevention underlines the need for robust evidence to promote safe practice.ObjectiveThis review aimed to examine the effectiveness of currently available mobile health (mHealth) technology tools in reducing suicide-specific outcomes.MethodsThe following databases were searched: Cochrane Central Register of Controlled Trials (The Cochrane Library), MEDLINE, EMBASE, PsycINFO, and relevant sources of gray literature. All published and unpublished randomized controlled trials (RCTs), pseudo-RCTs, and pre-post observational studies that evaluated the effectiveness of mHealth technology in suicide prevention delivered via mobile computing and communication technology were included. Studies were included if they measured at least one suicide outcome variable (ie, suicidal ideation, suicidal intent, nonsuicidal self-injurious behavior, and suicidal behavior). A total of 2 review authors independently extracted data and assessed study suitability, in accordance with the Cochrane Collaboration Risk of Bias Tool, on July 31, 2018. Owing to the heterogeneity of outcomes found across studies, results were not amenable for pooled synthesis, and a meta-analysis was not performed. A narrative synthesis of the available research is presented here.ResultsA total of 7 studies met criteria for inclusion . Four published articles that reported on the effectiveness of the following mobile phone apps were included: iBobbly, Virtual Hope Box, BlueIce, and Therapeutic Evaluative Conditioning. Results demonstrated some positive impacts for individuals at elevated risk of suicide or self-harm, including reductions in depression, psychological distress, and self-harm and increases in coping self-efficacy. None of the apps evaluated demonstrated the ability to significantly decrease suicidal ideation compared with a control condition. In addition, 3 unpublished and recently completed trials also met criteria for inclusion in the review.ConclusionsFurther research is needed to evaluate the efficacy of stand-alone mHealth technology-based interventions in suicide prevention. The small number of studies reported in this review tentatively indicate that such tools may have a positive impact on suicide-specific outcomes. Future mHealth intervention evaluations would benefit from addressing the following 3 main methodological limitations : (1) heterogeneity of outcomes: a lack of standardized measurement of suicide outcomes across studies; (2) ecological validity: the tendency to exclude potential participants because of the elevated suicide risk may reduce generalizability within clinical settings; and (3) app regulation and definition: the lack of a standardized classification system for mHealth intervention type points to the need for better definition of the scope of such technologies to promote safe practice.Trial registrationPROSPERO CRD42017072899; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=72899.International registered report identifier (irrid)RR2-10.2196/resprot.8635.

Project description:Suicidal behaviour and deliberate self-harm are common among adults. Research indicates that maintaining contact either via letter or postcard with at-risk adults following discharge from care services can reduce reattempt risk. Feasibility trials demonstrated that intervention through text message was also effective in preventing suicide repetition amongst suicide attempters. The aim of the current study is to investigate the effect of text message intervention versus traditional treatment on reducing the risk of suicide attempt repetition among adults after self-harm.The study will be a 2-year multicentric randomized controlled trial conducted by the Brest University Hospital, France. Participants will be adults discharged after self-harm, from emergency services or after a short hospitalization. Participants will be recruited over a 12-month period. The intervention is comprised of an SMS that will be sent at h48, D7, D15 and monthly. The text message enquires about the patients' well-being and includes information regarding individual sources of help and evidence-based self help strategies. Participants will be assessed at the baseline, month 6 and 13. As primary endpoint, we will assess the number of patients who reattempt suicide in each group at 6 months. As secondary endpoints, we will assess the number of patients who reattempt suicide at 13 month, the number of suicide attempts in the intervention and control groups at 6 and 13 month, the number of death by suicide in the intervention and control groups at month 6 and 13. In both groups, suicidal ideations, will be assessed at the baseline, month 6 and 13. Medical costs and satisfaction will be assessed at month 13.This paper describes the design and deployment of a trial SIAM; an easily reproducible intervention that aims to reduce suicide risk in adults after self-harm. It utilizes several characteristics of interventions that have shown a significant reduction in the number of suicide reattempts. We propose to assess its efficacy in reducing suicide reattempt in the suicide attempter (SA) population.The study was registered on Clinical Trials Registry (clinicaltrials.gov): NCT02106949, registered on 06 June 2014.