PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
Developing a Tool to Assess the Impact of Simulated Intervention Strategies on Suicide and Suicidal Behaviours in Canada: A Dynamic Modelling & Machine Learning Approach
Version 1
: Received: 10 May 2024 / Approved: 11 May 2024 / Online: 13 May 2024 (12:14:48 CEST)
How to cite:
Zahan, R.; Mikuliak, J.; Osgood, N. D. Developing a Tool to Assess the Impact of Simulated Intervention Strategies on Suicide and Suicidal Behaviours in Canada: A Dynamic Modelling & Machine Learning Approach. Preprints2024, 2024050813. https://doi.org/10.20944/preprints202405.0813.v1
Zahan, R.; Mikuliak, J.; Osgood, N. D. Developing a Tool to Assess the Impact of Simulated Intervention Strategies on Suicide and Suicidal Behaviours in Canada: A Dynamic Modelling & Machine Learning Approach. Preprints 2024, 2024050813. https://doi.org/10.20944/preprints202405.0813.v1
Zahan, R.; Mikuliak, J.; Osgood, N. D. Developing a Tool to Assess the Impact of Simulated Intervention Strategies on Suicide and Suicidal Behaviours in Canada: A Dynamic Modelling & Machine Learning Approach. Preprints2024, 2024050813. https://doi.org/10.20944/preprints202405.0813.v1
APA Style
Zahan, R., Mikuliak, J., & Osgood, N. D. (2024). Developing a Tool to Assess the Impact of Simulated Intervention Strategies on Suicide and Suicidal Behaviours in Canada: A Dynamic Modelling & Machine Learning Approach. Preprints. https://doi.org/10.20944/preprints202405.0813.v1
Chicago/Turabian Style
Zahan, R., Jalen Mikuliak and Nathaniel D. Osgood. 2024 "Developing a Tool to Assess the Impact of Simulated Intervention Strategies on Suicide and Suicidal Behaviours in Canada: A Dynamic Modelling & Machine Learning Approach" Preprints. https://doi.org/10.20944/preprints202405.0813.v1
Abstract
Suicide dynamics form a complex system deeply influenced by interrelated factors, necessitating advanced methodologies for comprehensive analysis. This study pioneers the application of Particle Markov Chain Monte Carlo (PMCMC) methods in suicide research, recognized for their enhanced sampling efficiency over traditional techniques in complex, high-dimensional models. PMCMC is particularly adept at handling non-Gaussian distributions and navigating parameter spaces efficiently, preventing the entrapment in local optima. Utilizing PMCMC, our research simulated a broad spectrum of potential outcomes, clarifying the probable scenarios and their likelihoods, thus enriching the predictive accuracy and understanding of suicide dynamics. These methods facilitated the exploration of dynamic interactions among key risk factors such as mental health issues, trauma, substance use, social isolation, and access to harmful means, whose complex interplays challenge predictive modeling. The study extends previous applications of PMCMC in complex systems like H1N1, opioid crises, and COVID-19 to the domain of suicide, suggesting its potential in enhancing decision-making and intervention strategies. However, limitations due to the model's simplified assumptions and the specificity of the data to certain populations underscore the necessity for broader application to validate findings across varied demographics. In summary, while PMCMC offers robust capabilities for the dynamic modeling of suicide, it requires careful parameter selection and consideration of computational demands. Future research should continue to leverage this approach in more complex settings, enhancing our ability to predict and mitigate suicide risks effectively.
Keywords
complex system; data science; machine learning; particle markov chain monte carlo; suicide; system dynamics; systems science; time series data; dynamic modeling; mental health research
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
