# Risk factors and predictive performance for first healthcare encounter indicating homelessness using administrative data among Calgary residents diagnosed with addiction or mental health conditions

## TL;DR

This study uses healthcare data to identify risk factors for homelessness among people with addiction or mental health issues in Calgary, finding that mental health emergencies and substance misuse are strong predictors.

## Contribution

The study introduces a machine learning approach to predict homelessness risk among AMH patients using administrative data, showing modest improvements over traditional logistic regression.

## Key findings

- Mental health emergency visits, substance misuse, and substance use disorders were the strongest predictors of first healthcare encounters indicating homelessness.
- Machine learning models like XGBoost slightly outperformed logistic regression in predicting homelessness risk.
- Approximately 0.82% of individuals diagnosed with AMH experienced homelessness-related healthcare encounters during the study period.

## Abstract

Individuals diagnosed with addiction or mental health (AMH) conditions are more likely to experience potentially adverse outcomes of homelessness. Despite their link to later outcomes, research on initial episodes of AMH outcomes is limited. This study aims to use administrative data to identify the factors associated with the first healthcare encounters with indicators of homelessness (FHE-H) for individuals diagnosed with AMH. We assessed logistic regression and compared its performance with machine learning models, including random forests and extreme gradient boosting (XGBoost). We conducted a retrospective cohort study linking several administrative datasets for 232,253 individuals with Alberta health insurance in Calgary, Canada, who were aged between 18 and 65 and diagnosed with AMH between April 1, 2013, and March 31, 2018. We assessed outcomes in two years following cohort entry. Individuals with episodes of FHE-H (2,606 individuals) before the index date were excluded. Multivariable logistic regression models were used to identify factors associated with outcomes by estimating adjusted odds ratios (AORs) with 95% confidence intervals. Among 229,647 individuals diagnosed with AMH, 1,886 (0.82%) experienced FHE-H during the follow-up period. Mental health emergency visits (AORs=5.28 [95% CI: 4.41, 6.33]), substance misuse (AORs=3.87 [95% CI: 3.28, 4.56], substance use disorders (AORs=2.03 [95% CI: 1.64, 2.50]), and male sex (AORs=1.28 [95% CI: 1.14, 1.44]) were associated with FHE-H. XGBoost performance improved over logistic regression, with increases in area under the curve (AUC) by 1% and precision by 2%. Overall, several AMH features were associated with FHE-H, and machine learning models outperformed logistic regression, although to a small degree.

Individuals diagnosed with addiction or mental health (AMH) conditions face a higher risk of experiencing homelessness, yet little is known about the early indicators that precede this outcome. In this study, we analyzed administrative healthcare data from over 230,000 adults in Calgary, Canada, to identify factors linked to a first healthcare encounter indicating homelessness. Using both statistical and machine learning models, we found that emergency mental health visits, substance misuse, and substance use disorders were the strongest predictors of future homelessness risk. Although machine learning only modestly improved prediction accuracy, it provided deeper insight into how multiple factors interact to shape vulnerability. By identifying individuals at high risk earlier, our findings highlight opportunities for preventive interventions and improved care coordination. This research demonstrates how large-scale administrative healthcare data can be used to better understand the factors associated with experiencing homelessness among people diagnosed with AMH conditions.