“I Can’t Crack the Code”: What Suicide Notes Teach Us about Experiences with Mental Illness and Mental Health Care

Furqan, Zainab; Sinyor, Mark; Schaffer, Ayal; Kurdyak, Paul; Zaheer, Juveria

doi:10.1177/0706743718787795

Cited by 8 publications

(9 citation statements)

References 40 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, the findings cannot be generalised to a larger population or to other suicide methods. However, the sample size was comparable to other indepth studies of suicide notes (Cheung, Merry, & Sundram, 2015;Furqan, Sinyor, Schaffer, Kurdyak, & Zaheer, 2019).…”

Section: Limitations and Future Directionssupporting

confidence: 61%

Why Choose the Railway?

Duddin

Raynes

2022

Crisis

View full text Add to dashboard Cite

Abstract. Background: The impact of railway suicide in the United Kingdom is extensive, yet reasons for why people choose this method are not clearly understood and research into the examination of suicide notes in this area is limited. Aims: Our study aimed to utilize the unique access to suicide notes written by those who died by suicide on the railway so as to gain a greater understanding of why people chose this method. Method: Descriptive and thematic analysis was conducted on 75 suicide notes for those who had died by suicide on the UK railway between 2010 and 2016. Results: Demographic findings from the sample were largely consistent with railway UK data trends. Five main themes were identified as being significant: “certain and instant,” “impersonal and non-human,” “ability to be planned,” “a good death,” and “bereavement suicide.” Limitations: Findings are based on suicide note authors who died by suicide on the railway in the UK, as such generalizability may be limited. Conclusion: Findings suggest that people select the railway for their suicide for the following motives: perception of being instant and certain and viewed as a good death, ability to be planned, belief it causes less of a burden on loved ones (via the perception of the railway as impersonal), and a prior experience of it being fatal (via bereavement suicide). Key implications in relation to prevention strategies and future research are discussed.

show abstract

Section: Limitations and Future Directionssupporting

confidence: 61%

Why Choose the Railway?

Duddin

Raynes

2022

Crisis

View full text Add to dashboard Cite

show abstract

“…The study also found that high-income countries are significantly more likely to have child and adolescent mental health strategies, dedicated mental health authority and suicide prevention programs, relative to LMIC. More importantly, given the robust link between mental health problems and tendency for suicide particularly in the high-income countries [ 9 , 11 ], it is plausible to reason that programs and initiatives designed to promote and restore mental health functioning will contribute to a reduction in suicide rate. In contrast, however, the study found that macro-level mental health indicators examined in this study (e.g.…”

Section: Discussionmentioning

confidence: 99%

Macro-level mental health system indicators and cross-national suicide rates

Andoh–Arthur

Adjorlolo

2021

Global Health Action

View full text Add to dashboard Cite

Background The relationship between macro-level mental health system indicators and population suicide rates is an area of contention in the literature, necessitating an analysis of current cross-national data to document any new trend in the relationship. Objective This study investigated whether mental health system indicators are associated with national suicide rates. Method Using an ecological study design and multivariate non-parametric robust regression models, data on suicide rates and mental health system indicators of 191 countries retrieved from WHOs 2017 Mental Health Atlas were compared. Results Findings revealed that the average suicide mortality rate was significantly higher in high- income countries, relative to low-income countries. High-income countries are significantly more likely to have high number of mental health professionals, mental health policies and legislation, independent mental health authority and suicide prevention programs. These mental health system indicators demonstrated significant and positive association with suicide, suggesting that countries scoring high on these factors have higher odds of being categorized as high suicide risk countries. Conclusion The findings have several implications for policy and practice, including the need to make existing mental health systems very responsive to suicide prevention.

show abstract

“…We used ten composite quotes to share example predictions of our system on text that could be predictive/indicative of self-harming and/or suicidality. These composite quotes were created by Furqan et al [22] , and were derived from qualitative research that synthesized primary themes noted in a selection of suicide notes that made explicit mentions of mental illness and/or mental healthcare. To assess the role of individual words (or tokens) in the classification of the quote, we iteratively perturbed each token and replaced it with an unknown token outside of the model's vocabulary and re-ran the prediction.…”

Section: Composite Quotesmentioning

confidence: 99%

Transfer Learning for Risk Classification of Social Media Posts: Model Evaluation Study

et al. 2020

View full text Add to dashboard Cite

BackgroundMental illness affects a significant portion of the worldwide population. Online mental health forums can provide a supportive environment for those afflicted and also generate a large amount of data which can be mined to predict mental health states using machine learning methods. ObjectiveWe benchmark multiple methods of text feature representation for social media posts and compare their downstream use with automated machine learning (AutoML) tools to triage content for moderator attention. MethodsWe used 1588 labeled posts from the CLPsych 2017 shared task collected from the Reachout.com forum (Milne et al., 2019). Posts were represented using lexicon based tools including VADER, Empath, LIWC and also used pre-trained artificial neural network models including DeepMoji, Universal Sentence Encoder, and GPT-1. We used TPOT and auto-sklearn as AutoML tools to generate classifiers to triage the posts. ResultsThe top-performing system used features derived from the GPT-1 model, which was finetuned on over 150,000 unlabeled posts from Reachout.com . Our top system had a macro averaged F1 score of 0.572, providing a new state-of-the-art result on the CLPsych 2017 task. This was achieved without additional information from meta-data or preceding posts. Error analyses revealed that this top system often misses expressions of hopelessness. We additionally present visualizations that aid understanding of the learned classifiers. ConclusionsWe show that transfer learning is an effective strategy for predicting risk with relatively little labeled data. We note that finetuning of pretrained language models provides further gains when large amounts of unlabeled text is available.

show abstract

“I Can’t Crack the Code”: What Suicide Notes Teach Us about Experiences with Mental Illness and Mental Health Care

Abstract: This study highlights unique perspectives by suicide decedents, whose voices and experiences may not have been heard otherwise, addressing a critical deficit in existing literature. These insights can potentially enrich clinical care or strengthen existing suicide prevention programs.

Cited by 8 publications

References 40 publications

Why Choose the Railway?

Why Choose the Railway?

Macro-level mental health system indicators and cross-national suicide rates

Transfer Learning for Risk Classification of Social Media Posts: Model Evaluation Study

Contact Info

Product

Resources

About