ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board?
Objective To evaluate ChatGPT‘s performance in brain glioma adjuvant therapy decision-making.Methods We randomly selected 10 patients with brain gliomas discussed at our institution’s central nervous system tumour board (CNS TB). Patients’ clinical status, surgical outcome, textual imaging informati...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2023-06-01
|
| Series: | BMJ Health & Care Informatics |
| Online Access: | https://informatics.bmj.com/content/30/1/e100775.full |
| _version_ | 1827153061763612672 |
|---|---|
| author | Karl Schaller Philippe Bijlenga Aria Nouri Kristof Egervari Shahan Momjian Julien Haemmerli Lukas Sveikata Adrien May Christian Freyschlag Johannes A Lobrinus Denis Migliorini Nicolae Sanda Sebastien Tran Jacky Yeung |
| author_facet | Karl Schaller Philippe Bijlenga Aria Nouri Kristof Egervari Shahan Momjian Julien Haemmerli Lukas Sveikata Adrien May Christian Freyschlag Johannes A Lobrinus Denis Migliorini Nicolae Sanda Sebastien Tran Jacky Yeung |
| author_sort | Karl Schaller |
| collection | DOAJ |
| description | Objective To evaluate ChatGPT‘s performance in brain glioma adjuvant therapy decision-making.Methods We randomly selected 10 patients with brain gliomas discussed at our institution’s central nervous system tumour board (CNS TB). Patients’ clinical status, surgical outcome, textual imaging information and immuno-pathology results were provided to ChatGPT V.3.5 and seven CNS tumour experts. The chatbot was asked to give the adjuvant treatment choice, and the regimen while considering the patient’s functional status. The experts rated the artificial intelligence-based recommendations from 0 (complete disagreement) to 10 (complete agreement). An intraclass correlation coefficient agreement (ICC) was used to measure the inter-rater agreement.Results Eight patients (80%) met the criteria for glioblastoma and two (20%) were low-grade gliomas. The experts rated the quality of ChatGPT recommendations as poor for diagnosis (median 3, IQR 1–7.8, ICC 0.9, 95% CI 0.7 to 1.0), good for treatment recommendation (7, IQR 6–8, ICC 0.8, 95% CI 0.4 to 0.9), good for therapy regimen (7, IQR 4–8, ICC 0.8, 95% CI 0.5 to 0.9), moderate for functional status consideration (6, IQR 1–7, ICC 0.7, 95% CI 0.3 to 0.9) and moderate for overall agreement with the recommendations (5, IQR 3–7, ICC 0.7, 95% CI 0.3 to 0.9). No differences were observed between the glioblastomas and low-grade glioma ratings.Conclusions ChatGPT performed poorly in classifying glioma types but was good for adjuvant treatment recommendations as evaluated by CNS TB experts. Even though the ChatGPT lacks the precision to replace expert opinion, it may serve as a promising supplemental tool within a human-in-the-loop approach. |
| first_indexed | 2024-03-08T16:37:53Z |
| format | Article |
| id | doaj.art-1242d5649eb64f529d71806a749af804 |
| institution | Directory Open Access Journal |
| issn | 2632-1009 |
| language | English |
| last_indexed | 2025-03-20T22:15:47Z |
| publishDate | 2023-06-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Health & Care Informatics |
| spelling | doaj.art-1242d5649eb64f529d71806a749af8042024-08-09T01:15:10ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092023-06-0130110.1136/bmjhci-2023-100775ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board?Karl Schaller0Philippe Bijlenga1Aria Nouri2Kristof Egervari3Shahan Momjian4Julien Haemmerli5Lukas Sveikata6Adrien May7Christian Freyschlag8Johannes A Lobrinus9Denis Migliorini10Nicolae Sanda11Sebastien Tran12Jacky Yeung13Department of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, SwitzerlandDivision of Neurosurgery, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Pathology and Immunology, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Clinical Neurosciences, Division of Neurology, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Neurosurgery, Medical University of Innsbruck, Innsbruck, AustriaDepartment of Pathology and Immunology, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Oncology, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Clinical Neurosciences, Division of Neurology, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Radiation Oncology, Geneva University Hospitals, Geneva, SwitzerlandDepartment of Neurosurgery, Yale University School of Medicine, New Haven, Connecticut, USAObjective To evaluate ChatGPT‘s performance in brain glioma adjuvant therapy decision-making.Methods We randomly selected 10 patients with brain gliomas discussed at our institution’s central nervous system tumour board (CNS TB). Patients’ clinical status, surgical outcome, textual imaging information and immuno-pathology results were provided to ChatGPT V.3.5 and seven CNS tumour experts. The chatbot was asked to give the adjuvant treatment choice, and the regimen while considering the patient’s functional status. The experts rated the artificial intelligence-based recommendations from 0 (complete disagreement) to 10 (complete agreement). An intraclass correlation coefficient agreement (ICC) was used to measure the inter-rater agreement.Results Eight patients (80%) met the criteria for glioblastoma and two (20%) were low-grade gliomas. The experts rated the quality of ChatGPT recommendations as poor for diagnosis (median 3, IQR 1–7.8, ICC 0.9, 95% CI 0.7 to 1.0), good for treatment recommendation (7, IQR 6–8, ICC 0.8, 95% CI 0.4 to 0.9), good for therapy regimen (7, IQR 4–8, ICC 0.8, 95% CI 0.5 to 0.9), moderate for functional status consideration (6, IQR 1–7, ICC 0.7, 95% CI 0.3 to 0.9) and moderate for overall agreement with the recommendations (5, IQR 3–7, ICC 0.7, 95% CI 0.3 to 0.9). No differences were observed between the glioblastomas and low-grade glioma ratings.Conclusions ChatGPT performed poorly in classifying glioma types but was good for adjuvant treatment recommendations as evaluated by CNS TB experts. Even though the ChatGPT lacks the precision to replace expert opinion, it may serve as a promising supplemental tool within a human-in-the-loop approach.https://informatics.bmj.com/content/30/1/e100775.full |
| spellingShingle | Karl Schaller Philippe Bijlenga Aria Nouri Kristof Egervari Shahan Momjian Julien Haemmerli Lukas Sveikata Adrien May Christian Freyschlag Johannes A Lobrinus Denis Migliorini Nicolae Sanda Sebastien Tran Jacky Yeung ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board? BMJ Health & Care Informatics |
| title | ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board? |
| title_full | ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board? |
| title_fullStr | ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board? |
| title_full_unstemmed | ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board? |
| title_short | ChatGPT in glioma adjuvant therapy decision making: ready to assume the role of a doctor in the tumour board? |
| title_sort | chatgpt in glioma adjuvant therapy decision making ready to assume the role of a doctor in the tumour board |
| url | https://informatics.bmj.com/content/30/1/e100775.full |
| work_keys_str_mv | AT karlschaller chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT philippebijlenga chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT arianouri chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT kristofegervari chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT shahanmomjian chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT julienhaemmerli chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT lukassveikata chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT adrienmay chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT christianfreyschlag chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT johannesalobrinus chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT denismigliorini chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT nicolaesanda chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT sebastientran chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard AT jackyyeung chatgptingliomaadjuvanttherapydecisionmakingreadytoassumetheroleofadoctorinthetumourboard |