No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

My objective was to predict outcomes following police interactions with PMIs, and compare the predictive accuracy of logistic regression models and Random Forests learning algorithms. Additionally I evaluated if predictive accuracy of Random Forests changed when applied to merged versus region-specific data. I conducted a retrospective cohort study of reports completed by police in 13 communities between 2015 and 2018. 13,058 reports were analyzed. Random Forests learning algorithms were compared against logistic regression models for predictive accuracy in a merged dataset (13 communities) and 3 regional datasets. Outcomes for prediction were high risk of harm to self, risk of harm to others, and risk of failure to care for self within 24 and 72 hours following police contact. Random Forests learning algorithms were trained on merged and regional datasets, and compared against merged and regional holdout datasets. Performance was compared by area under the curve. For Random Forests learning algorithms, confusion matrix statistics were calculated for each outcome and predictive utility was examined by calculating conditional probabilities. Prediction accuracy was modest across all methods. Random Forests achieved better predictive accuracy than logistic regression. Random Forests accuracy varied between merged and regional holdout data. Sensitivity of Random Forests learning algorithms were moderate (74% average, 6 outcomes, merged holdout set). Specificity was low (53% average, 6 outcomes, merged holdout set). Conditional probabilities were modestly improved by the use of the Random Forests learning algorithm. The rareness of the target outcomes created a situation where even predictions with moderate likelihood ratios had only modest predictive value. Though the Random Forests learning algorithms did outperform the logistic regression learning algorithms, the clinical significance of those benefits were limited when conditional probabilities were calculated. These findings are limited to the outcomes considered, and may not apply to more common outcomes. / Thesis / Master of Health Sciences (MSc) / The study goal was to predict outcomes following police interactions with persons with mental illness (PMIs). Additionally we compare the predictive validity of logistic regression and Random Forests learning algorithms. Classification approaches were applied to outcomes following police interactions with PMIs, including: high risk of harm to self, high risk of harm to others, and high risk of failure to care for self within 24 hours and 72 hours of initial police contact. The study also sought to determine if the predictive accuracy of Random Forests was sensitive to the police service community. Variation in predictive accuracy was assessed between a merged data set (13 communities) and 3 community-specific data. The study found that the predictive accuracy of the classification approaches on outcomes was modest. Random Forests exhibited greater predictive validity than logistic regression. The performance of the Random Forests suggested that performance was not sensitive to police service context.

Effectively addressing mental health and substance use problems are important challenges faced globally. People experiencing such problems encounter many societal barriers that can affect their ability to participate as full members of society and have life expectancies much shorter than the general population. Policies to address mental health and substance use problems require the mobilization of multiple sectors, such as health, education, and justice. While there is strong evidence for programs and services that work, and there are policy directions aimed at achieving better service experiences and improved health and social outcomes, there is a lack of knowledge about how to get these policies and programs embedded effectively into daily practice – a process called implementation. The objective of this dissertation is to advance the understanding of implementation strategies for addressing such complex challenges through five original scientific contributions. The first is a critical interpretive synthesis of existing literature to generate a theoretical framework of the implementation process from the perspective of a policy goal by integrating findings from the public policy, implementation science and knowledge translation fields. Next is a two-part comparative case study exploring how policy implementation was structured and the strategies used in large, well-developed mental health systems. Last is a two-part in-depth examination of mental health policy implementation efforts in Ontario, Canada, beginning with an analysis of the development and implementation of the province’s mental health strategy, followed by an examination of the role that citizens and other stakeholder groups played in its implementation. Together these studies contribute theoretical, substantive and methodological insights toward understanding the effective implementation of policy directions for complex social challenges. Better implementation means more citizens can benefit from effective policies and programs that are needed across populations. / Thesis / Doctor of Philosophy (PhD) / People with mental health and substance use problems face many barriers that can affect their ability to participate in society. In order to make a positive impact on mental health, changes need to be made in a number of different areas such as health, education and justice. There is now research evidence about programs and policies that are effective, but there is a lack of understanding of how to get those changes into policy and practice so that people can benefit from them – a process called implementation. This thesis answers questions about implementation in mental health systems to help fill this gap. It contributes: 1) a new theory of implementation from the perspective of a policy goal; 2) insights about the infrastructure needed to support large-scale implementation; and 3) an understanding of how citizens and other stakeholders contribute to implementation by examining Ontario’s mental health and addictions strategy.

No description available.