Tree-Based Machine Learning to Identify Predictors of Psoriasis Incidence at the Neighborhood Level: A Populational Study from Quebec, Canada

Background

Psoriasis is a major global health burden affecting ~ 60 million people worldwide. Existing studies on psoriasis focused on individual-level health behaviors (e.g. diet, alcohol consumption, smoking, exercise) and characteristics as drivers of psoriasis risk. However, it is increasingly recognized that health behavior arises in the context of larger social, cultural, economic and environmental determinants of health. We aimed to identify the top risk factors that significantly impact the incidence of psoriasis at the neighborhood level using populational data from the province of Quebec (Canada) and advanced tree-based machine learning (ML) techniques.

Methods

Adult psoriasis patients were identified using International Classification of Disease (ICD)-9/10 codes from Quebec (Canada) populational databases for years 1997–2015. Data on environmental and socioeconomic factors 1 year prior to psoriasis onset were obtained from the Canadian Urban Environment Health Consortium (CANUE) and Statistics Canada (StatCan) and were input as predictors into the gradient boosting ML. Model performance was evaluated using the area under the curve (AUC). Parsimonious models and partial dependence plots were determined to assess directionality of the relationship.

Results

The incidence of psoriasis varied geographically from 1.6 to 325.6/100,000 person-years in Quebec. The parsimonious model (top 9 predictors) had an AUC of 0.77 to predict high psoriasis incidence. Amongst top predictors, ultraviolet (UV) radiation, maximum daily temperature, proportion of females, soil moisture, urbanization, and distance to expressways had a negative association with psoriasis incidence. Nighttime light brightness had a positive association, whereas social and material deprivation indices suggested a higher psoriasis incidence in the middle socioeconomic class neighborhoods.

Conclusion

This is the first study to highlight highly variable psoriasis incidence rates on a jurisdictional level and suggests that living environment, notably climate, vegetation, urbanization and neighborhood socioeconomic characteristics may have an association with psoriasis incidence.