Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study
Background:. Chronic wounds affect approximately 2.5% of the US population and can cause severe complications if not identified and treated promptly. Artificial intelligence tools such as Microsoft’s Copilot have the potential to expedite diagnosis, but their clinical diagnostic accuracy remains und...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer
2025-06-01
|
| Series: | Plastic and Reconstructive Surgery, Global Open |
| Online Access: | http://journals.lww.com/prsgo/fulltext/10.1097/GOX.0000000000006871 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850111435596627968 |
|---|---|
| author | Kirollos Tadrousse, BS Catherine A. Cash, BS Madhulika R. Kastury, BS Noelle Thompson, BS Richard Simman, MD, FACS, FACCWS |
| author_facet | Kirollos Tadrousse, BS Catherine A. Cash, BS Madhulika R. Kastury, BS Noelle Thompson, BS Richard Simman, MD, FACS, FACCWS |
| author_sort | Kirollos Tadrousse, BS |
| collection | DOAJ |
| description | Background:. Chronic wounds affect approximately 2.5% of the US population and can cause severe complications if not identified and treated promptly. Artificial intelligence tools such as Microsoft’s Copilot have the potential to expedite diagnosis, but their clinical diagnostic accuracy remains underexplored.
Methods:. Ten chronic wound cases were selected from the publicly available database of the Silesian University of Technology. Images and demographic data were entered into Copilot, which generated the top 3 differential diagnoses for each case. Diagnostic accuracy was evaluated using a predefined scoring system. Statistical analysis included descriptive statistics, the Wilcoxon signed-rank test, bootstrapping, the Fisher–Pitman permutation test, Cohen kappa, and Fisher exact test.
Results:. Copilot correctly identified the primary diagnosis in 30% of cases and included the correct diagnosis within its top 3 differentials in 70% of cases. The mean diagnostic score was 1.7 (median: 2, SD: 1.25, variance: 1.57). The Wilcoxon test indicated no significant deviation from the median reference value (P = 0.6364), whereas bootstrapping yielded a 95% confidence interval of 1–4. The permutation test demonstrated a significant difference from the null hypothesis (P = 0.017), and the Cohen kappa revealed perfect agreement (kappa = 1, P = 0.00157). The Fisher exact test showed no significant association between primary and top 3 diagnostic accuracy (P = 0.20).
Conclusions:. Microsoft Copilot demonstrated limited diagnostic accuracy in chronic wound assessment, underscoring the need for cautious integration into clinical workflows. Broader datasets and more rigorous validation are crucial for enhancing artificial intelligence–supported diagnostics in wound care. |
| format | Article |
| id | doaj-art-6501666aa9b0480fb48dfce830a602d0 |
| institution | OA Journals |
| issn | 2169-7574 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Wolters Kluwer |
| record_format | Article |
| series | Plastic and Reconstructive Surgery, Global Open |
| spelling | doaj-art-6501666aa9b0480fb48dfce830a602d02025-08-20T02:37:37ZengWolters KluwerPlastic and Reconstructive Surgery, Global Open2169-75742025-06-01136e687110.1097/GOX.0000000000006871202506000-00046Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative StudyKirollos Tadrousse, BS0Catherine A. Cash, BS1Madhulika R. Kastury, BS2Noelle Thompson, BS3Richard Simman, MD, FACS, FACCWS4From the * College of Medicine and Life Sciences, University of Toledo, Toledo, OHFrom the * College of Medicine and Life Sciences, University of Toledo, Toledo, OHFrom the * College of Medicine and Life Sciences, University of Toledo, Toledo, OHFrom the * College of Medicine and Life Sciences, University of Toledo, Toledo, OH† Department of Surgery, College of Medicine and Life Sciences, University of Toledo, Toledo, OHBackground:. Chronic wounds affect approximately 2.5% of the US population and can cause severe complications if not identified and treated promptly. Artificial intelligence tools such as Microsoft’s Copilot have the potential to expedite diagnosis, but their clinical diagnostic accuracy remains underexplored. Methods:. Ten chronic wound cases were selected from the publicly available database of the Silesian University of Technology. Images and demographic data were entered into Copilot, which generated the top 3 differential diagnoses for each case. Diagnostic accuracy was evaluated using a predefined scoring system. Statistical analysis included descriptive statistics, the Wilcoxon signed-rank test, bootstrapping, the Fisher–Pitman permutation test, Cohen kappa, and Fisher exact test. Results:. Copilot correctly identified the primary diagnosis in 30% of cases and included the correct diagnosis within its top 3 differentials in 70% of cases. The mean diagnostic score was 1.7 (median: 2, SD: 1.25, variance: 1.57). The Wilcoxon test indicated no significant deviation from the median reference value (P = 0.6364), whereas bootstrapping yielded a 95% confidence interval of 1–4. The permutation test demonstrated a significant difference from the null hypothesis (P = 0.017), and the Cohen kappa revealed perfect agreement (kappa = 1, P = 0.00157). The Fisher exact test showed no significant association between primary and top 3 diagnostic accuracy (P = 0.20). Conclusions:. Microsoft Copilot demonstrated limited diagnostic accuracy in chronic wound assessment, underscoring the need for cautious integration into clinical workflows. Broader datasets and more rigorous validation are crucial for enhancing artificial intelligence–supported diagnostics in wound care.http://journals.lww.com/prsgo/fulltext/10.1097/GOX.0000000000006871 |
| spellingShingle | Kirollos Tadrousse, BS Catherine A. Cash, BS Madhulika R. Kastury, BS Noelle Thompson, BS Richard Simman, MD, FACS, FACCWS Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study Plastic and Reconstructive Surgery, Global Open |
| title | Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study |
| title_full | Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study |
| title_fullStr | Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study |
| title_full_unstemmed | Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study |
| title_short | Diagnostic Accuracy of Microsoft’s Copilot Artificial Intelligence in Chronic Wound Assessment: A Comparative Study |
| title_sort | diagnostic accuracy of microsoft s copilot artificial intelligence in chronic wound assessment a comparative study |
| url | http://journals.lww.com/prsgo/fulltext/10.1097/GOX.0000000000006871 |
| work_keys_str_mv | AT kirollostadroussebs diagnosticaccuracyofmicrosoftscopilotartificialintelligenceinchronicwoundassessmentacomparativestudy AT catherineacashbs diagnosticaccuracyofmicrosoftscopilotartificialintelligenceinchronicwoundassessmentacomparativestudy AT madhulikarkasturybs diagnosticaccuracyofmicrosoftscopilotartificialintelligenceinchronicwoundassessmentacomparativestudy AT noellethompsonbs diagnosticaccuracyofmicrosoftscopilotartificialintelligenceinchronicwoundassessmentacomparativestudy AT richardsimmanmdfacsfaccws diagnosticaccuracyofmicrosoftscopilotartificialintelligenceinchronicwoundassessmentacomparativestudy |