Analytical validation of Exandra: a clinical decision support system for promoting guideline-directed therapy of type-2 diabetes in primary care - a collaborative study with experts from Diabetes Canada.
Klaudia Grechuta, Pedram Shokouh, Valentina Bayer, Henrich Kraemer, Jeremy Gilbert, Susie Jin, Ahmad Alhussein
{"title":"Analytical validation of Exandra: a clinical decision support system for promoting guideline-directed therapy of type-2 diabetes in primary care - a collaborative study with experts from Diabetes Canada.","authors":"Klaudia Grechuta, Pedram Shokouh, Valentina Bayer, Henrich Kraemer, Jeremy Gilbert, Susie Jin, Ahmad Alhussein","doi":"10.1186/s12911-025-02881-4","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Individuals with type 2 diabetes (T2D) have a high prevalence of cardiovascular and renal comorbidities. Despite clinical practice guidelines recommending the use of cardiorenal protective medications, many people with T2D are not prescribed these medications. A clinical decision support system called Exandra was developed to provide treatment recommendations for individuals with T2D based on current clinical practice guidelines from Diabetes Canada. The current study aimed to medically validate Exandra via review by external medical experts in T2D.</p><p><strong>Methods: </strong>Validation of Exandra took place in two phases. Test cases using simulated clinical scenarios and recommendations were generated by Exandra. In Phase 1 of the validation, reviewers evaluated whether they agreed with Exandra's recommendations with a \"yes,\" \"no,\" or \"not sure\" response. In Phase 2, reviewers were interviewed about their \"no\" and \"not sure\" responses to determine possible reasons and potential fixes to the Exandra system. The primary outcome was the precision rate of Exandra following the interviews and final adjudication of the cases. The target precision rate was 90%.</p><p><strong>Results: </strong>Exandra displayed an overall precision rate of 95.5%. A large proportion of cases that were initially labeled \"no\" or \"not sure\" by reviewers were changed to \"yes\" following the interview phase. This was largely due to the validation using a simplified user interface compared with the complexity of the actual Exandra system, and reviewers needing clarification of how the outputs would be displayed on the Exandra platform.</p><p><strong>Conclusion: </strong>Exandra displayed a high level of accuracy and precision in providing guideline-directed recommendations for managing T2D and its common comorbidities. The results of this study indicate that Exandra is a promising tool for improving the management of T2D and its comorbidities.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"74"},"PeriodicalIF":3.3000,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Medical Informatics and Decision Making","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12911-025-02881-4","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICAL INFORMATICS","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Individuals with type 2 diabetes (T2D) have a high prevalence of cardiovascular and renal comorbidities. Despite clinical practice guidelines recommending the use of cardiorenal protective medications, many people with T2D are not prescribed these medications. A clinical decision support system called Exandra was developed to provide treatment recommendations for individuals with T2D based on current clinical practice guidelines from Diabetes Canada. The current study aimed to medically validate Exandra via review by external medical experts in T2D.
Methods: Validation of Exandra took place in two phases. Test cases using simulated clinical scenarios and recommendations were generated by Exandra. In Phase 1 of the validation, reviewers evaluated whether they agreed with Exandra's recommendations with a "yes," "no," or "not sure" response. In Phase 2, reviewers were interviewed about their "no" and "not sure" responses to determine possible reasons and potential fixes to the Exandra system. The primary outcome was the precision rate of Exandra following the interviews and final adjudication of the cases. The target precision rate was 90%.
Results: Exandra displayed an overall precision rate of 95.5%. A large proportion of cases that were initially labeled "no" or "not sure" by reviewers were changed to "yes" following the interview phase. This was largely due to the validation using a simplified user interface compared with the complexity of the actual Exandra system, and reviewers needing clarification of how the outputs would be displayed on the Exandra platform.
Conclusion: Exandra displayed a high level of accuracy and precision in providing guideline-directed recommendations for managing T2D and its common comorbidities. The results of this study indicate that Exandra is a promising tool for improving the management of T2D and its comorbidities.
期刊介绍:
BMC Medical Informatics and Decision Making is an open access journal publishing original peer-reviewed research articles in relation to the design, development, implementation, use, and evaluation of health information technologies and decision-making for human health.