Using categorical data analyses in suicide research: Considering clinical utility and practicality

Mitchell, Sean M.; Cero, Ian; Littlefield, Andrew K.; Brown, Sarah

doi:10.1111/sltb.12670

Cited by 4 publications

(2 citation statements)

References 24 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, by targeting vulnerable populations only, ML could uncover predictors of suicidal behaviors specific to distinct disorders and help in better stratifying patients according to the actual risk. This would translate into useful information that can be more easily applied in clinical and forensic settings [ 25 ].…”

Section: Introductionmentioning

confidence: 99%

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Pigoni,

Delvecchio,

Turtulici

et al. 2024

Transl Psychiatry

View full text Add to dashboard Cite

Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, as many large-sample studies mixed psychiatric and non-psychiatric populations, a formal psychiatric diagnosis emerged as a strong predictor of suicidal risk, overshadowing more subtle risk factors specific to distinct populations. To overcome this limitation, we conducted a systematic review of ML studies evaluating suicidal behaviors exclusively in psychiatric clinical populations. A systematic literature search was performed from inception through November 17, 2022 on PubMed, EMBASE, and Scopus following the PRISMA guidelines. Original research using ML techniques to assess the risk of suicide or predict suicide attempts in the psychiatric population were included. An assessment for bias risk was performed using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines. About 1032 studies were retrieved, and 81 satisfied the inclusion criteria and were included for qualitative synthesis. Clinical and demographic features were the most frequently employed and random forest, support vector machine, and convolutional neural network performed better in terms of accuracy than other algorithms when directly compared. Despite heterogeneity in procedures, most studies reported an accuracy of 70% or greater based on features such as previous attempts, severity of the disorder, and pharmacological treatments. Although the evidence reported is promising, ML algorithms for suicidal prediction still present limitations, including the lack of neurobiological and imaging data and the lack of external validation samples. Overcoming these issues may lead to the development of models to adopt in clinical practice. Further research is warranted to boost a field that holds the potential to critically impact suicide mortality.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Pigoni,

Delvecchio,

Turtulici

et al. 2024

Transl Psychiatry

View full text Add to dashboard Cite

show abstract

“…base-rate of one in 100 is still low and is likely to lead to high rates of false positives (Mitchell et al, 2021).…”

Section: Statistical Challengesmentioning

confidence: 99%

Part 1: Supporting the Reduction of Suicide in the General Population of Wales via the use of Structured Professional Judgement; Part 2: Identifying the Factors Moderating Suicidal Thoughts and Suicide Attempts During the COVID-19 Pandemic

Knowles¹

View full text Add to dashboard Cite

Early identification of individuals at risk of suicide represents a crucial component of effective suicide prevention. However, many of the current suicide risk assessment procedures are limited in their ability to identify and prevent future suicide attempts. This thesis aimed to investigate whether the structured professional judgement approach was an effective method of suicide risk assessment within an accident and emergency department. Chapter 1 outlined the major challenges facing the field of suicide risk assessment and introduced the structured professional judgement approach to risk assessment. Chapter 2 reviewed the various methods used to assess the risk of suicide within accident and emergency services, evaluated the efficacy of the structured professional judgement approach and outlined the new structured professional judgement scheme, the Risk of Suicide Protocol, that was investigated in this thesis. Chapter 3 compared the Risk of Suicide Protocol and assessment as usual in their ability to identify future suicide attempts in 107 participants referred for a suicide risk assessment with the accident and emergencybased Psychiatric Liaison Team. Chapter 3 also evaluated the inter-rater reliability of the Risk of Suicide Protocol, with two independent assessors completing assessments on the same 12 patients. Chapter 7 reviewed the research relating to the RoSP and discussed the wider meaning and clinical implications of the findings. The findings demonstrated that risk judgements made using the Risk of Suicide Protocol were significantly better at identifying future suicide attempts compared to assessment as usual. Additionally, the risk judgements made using the Risk of Suicide Protocol demonstrated excellent inter-rater reliability. These results indicate that the Risk of Suicide Protocol is a valid and reliable assessment for the structured clinical evaluation of suicide risk within an accident and emergency department. Overall, this thesis demonstrates that the Risk of Suicide Protocol represents a valuable method for the evaluation of suicide risk and may offer an important solution to some of the challenges facing the field of suicide risk assessment.

show abstract

Prediction and Analysis of Saturated Electricity Consumption Based on Logistic - BP Neural Network

Cui¹,

Jia²,

Xue³

et al. 2021

2021 International Conference on Applications and Techniques in Cyber Intelligence

View full text Add to dashboard Cite

Using categorical data analyses in suicide research: Considering clinical utility and practicality

Cited by 4 publications

References 24 publications

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Part 1: Supporting the Reduction of Suicide in the General Population of Wales via the use of Structured Professional Judgement; Part 2: Identifying the Factors Moderating Suicidal Thoughts and Suicide Attempts During the COVID-19 Pandemic

Prediction and Analysis of Saturated Electricity Consumption Based on Logistic - BP Neural Network

Contact Info

Product

Resources

About