An-Wen Chan1, Kinwah Fung2, Jennifer M Tran3, Jessica Kitchen4, Peter C Austin5, Martin A Weinstock6, Paula A Rochon2. 1. Women's College Research Institute, Women's College Hospital, Toronto, Ontario, Canada2Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada3Division of Dermatology, Department of Medicine, University of Toronto, Ontario, Canada. 2. Women's College Research Institute, Women's College Hospital, Toronto, Ontario, Canada2Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada. 3. Division of Dermatology, Department of Medicine, University of Toronto, Ontario, Canada. 4. Women's College Research Institute, Women's College Hospital, Toronto, Ontario, Canada. 5. Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada. 6. Department of Dermatology, Brown University, Providence, Rhode Island5Department of Epidemiology, Brown University, Providence, Rhode Island.
Abstract
Importance: Keratinocyte carcinoma (nonmelanoma skin cancer) accounts for substantial burden in terms of high incidence and health care costs but is excluded by most cancer registries in North America. Administrative health insurance claims databases offer an opportunity to identify these cancers using diagnosis and procedural codes submitted for reimbursement purposes. Objective: To apply recursive partitioning to derive and validate a claims-based algorithm for identifying keratinocyte carcinoma with high sensitivity and specificity. Design, Setting, and Participants: Retrospective study using population-based administrative databases linked to 602 371 pathology episodes from a community laboratory for adults residing in Ontario, Canada, from January 1, 1992, to December 31, 2009. The final analysis was completed in January 2016. We used recursive partitioning (classification trees) to derive an algorithm based on health insurance claims. The performance of the derived algorithm was compared with 5 prespecified algorithms and validated using an independent academic hospital clinic data set of 2082 patients seen in May and June 2011. Main Outcomes and Measures: Sensitivity, specificity, positive predictive value, and negative predictive value using the histopathological diagnosis as the criterion standard. We aimed to achieve maximal specificity, while maintaining greater than 80% sensitivity. Results: Among 602 371 pathology episodes, 131 562 (21.8%) had a diagnosis of keratinocyte carcinoma. Our final derived algorithm outperformed the 5 simple prespecified algorithms and performed well in both community and hospital data sets in terms of sensitivity (82.6% and 84.9%, respectively), specificity (93.0% and 99.0%, respectively), positive predictive value (76.7% and 69.2%, respectively), and negative predictive value (95.0% and 99.6%, respectively). Algorithm performance did not vary substantially during the 18-year period. Conclusions and Relevance: This algorithm offers a reliable mechanism for ascertaining keratinocyte carcinoma for epidemiological research in the absence of cancer registry data. Our findings also demonstrate the value of recursive partitioning in deriving valid claims-based algorithms.
Importance: Keratinocyte carcinoma (nonmelanoma skin cancer) accounts for substantial burden in terms of high incidence and health care costs but is excluded by most cancer registries in North America. Administrative health insurance claims databases offer an opportunity to identify these cancers using diagnosis and procedural codes submitted for reimbursement purposes. Objective: To apply recursive partitioning to derive and validate a claims-based algorithm for identifying keratinocyte carcinoma with high sensitivity and specificity. Design, Setting, and Participants: Retrospective study using population-based administrative databases linked to 602 371 pathology episodes from a community laboratory for adults residing in Ontario, Canada, from January 1, 1992, to December 31, 2009. The final analysis was completed in January 2016. We used recursive partitioning (classification trees) to derive an algorithm based on health insurance claims. The performance of the derived algorithm was compared with 5 prespecified algorithms and validated using an independent academic hospital clinic data set of 2082 patients seen in May and June 2011. Main Outcomes and Measures: Sensitivity, specificity, positive predictive value, and negative predictive value using the histopathological diagnosis as the criterion standard. We aimed to achieve maximal specificity, while maintaining greater than 80% sensitivity. Results: Among 602 371 pathology episodes, 131 562 (21.8%) had a diagnosis of keratinocyte carcinoma. Our final derived algorithm outperformed the 5 simple prespecified algorithms and performed well in both community and hospital data sets in terms of sensitivity (82.6% and 84.9%, respectively), specificity (93.0% and 99.0%, respectively), positive predictive value (76.7% and 69.2%, respectively), and negative predictive value (95.0% and 99.6%, respectively). Algorithm performance did not vary substantially during the 18-year period. Conclusions and Relevance: This algorithm offers a reliable mechanism for ascertaining keratinocyte carcinoma for epidemiological research in the absence of cancer registry data. Our findings also demonstrate the value of recursive partitioning in deriving valid claims-based algorithms.