摘要：Background: The number of unmatched Canadian Medical Graduates (CMGs) has risen dramatically over the last decade. To identify long-term solutions to this problem, an understanding of the factors contributing to these rising unmatched rates is critical. Methods: Using match and electives data from 2009-2019, we employed machine learning algorithms to identify three clusters of disciplines with distinct trends in match and electives behaviours. We assessed the relationships between unmatched rates, competitiveness, rates of parallel planning, and program selection practices at a discipline level. Results: Across Canada, growth in CMGs has outpaced growth in residency seats, narrowing the seat-to-applicant ratio. Yet not all disciplines have been affected equally - a subset of surgical disciplines experienced a consistent decline in residency seats over time. Applicants to these disciplines are also at disproportionate risk of becoming unmatched, and this is associated with lower rates of parallel planning as quantified through clinical electives and match applications. This, in turn, is associated with the program selection practices of these disciplines. Conclusion: Long term solutions to the unmatched CMG crisis require more nuance than indiscriminately increasing residency seats and should consider cluster specific match ratios as well as regulations around clinical electives and program selection practices.
