ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images
Introduction: ChatGPT has the ability to generate human-like text, analyze and understand medical images using natural Language processing (NLP) algorithms. It can generate real-time diagnosis and recognize patterns and learn from previous cases to improve accuracy by combining patient history, symp...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Pensoft Publishers
2024-12-01
|
| Series: | Folia Medica |
| Online Access: | https://foliamedica.bg/article/135584/download/pdf/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556484378329088 |
|---|---|
| author | Shila Kahalian Marieh Rajabzadeh Melisa Öçbe Mahmut Sabri Medisoglu |
| author_facet | Shila Kahalian Marieh Rajabzadeh Melisa Öçbe Mahmut Sabri Medisoglu |
| author_sort | Shila Kahalian |
| collection | DOAJ |
| description | Introduction: ChatGPT has the ability to generate human-like text, analyze and understand medical images using natural Language processing (NLP) algorithms. It can generate real-time diagnosis and recognize patterns and learn from previous cases to improve accuracy by combining patient history, symptoms, and image characteristics. It has been used recently for learning about maxillofacial diseases, writing and translating radiology reports, and identifying anatomical landmarks, among other things. Materials and methods: In this study, 52 radiographic images were queried on the OpenAI application ChatGPT-4.0. The responses were evaluated with and without using clues for specific radiographs to see if adding clues during prompting improved diagnostic accuracy. Results: The true prediagnosis rate without any clue was 30.7%. By adding one clue this rate significantly increased to 56.9%. There was not a significant difference in accurate diagnosis of anatomical landmarks, cysts, and tumors (p>0.05). However, including internal structure information improved the diagnostic accuracy (p<0.05) Conclusion: GPT-4.0 showed a tendency to misdiagnose closely located anatomical structures and by adding additional clues its performance showed improvement, while its ability to recognize diverse differential diagnoses remains limited. |
| format | Article |
| id | doaj-art-33987c8693af4c94aebf366181e47908 |
| institution | Kabale University |
| issn | 1314-2143 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Pensoft Publishers |
| record_format | Article |
| series | Folia Medica |
| spelling | doaj-art-33987c8693af4c94aebf366181e479082025-01-07T08:30:10ZengPensoft PublishersFolia Medica1314-21432024-12-0166686386810.3897/folmed.66.e135584135584ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic imagesShila Kahalian0Marieh Rajabzadeh1Melisa Öçbe2Mahmut Sabri Medisoglu3Kocaeli Health and Technology UniversityKocaeli Health and Technology UniversityKocaeli Health and Technology UniversityKocaeli Health and Technology UniversityIntroduction: ChatGPT has the ability to generate human-like text, analyze and understand medical images using natural Language processing (NLP) algorithms. It can generate real-time diagnosis and recognize patterns and learn from previous cases to improve accuracy by combining patient history, symptoms, and image characteristics. It has been used recently for learning about maxillofacial diseases, writing and translating radiology reports, and identifying anatomical landmarks, among other things. Materials and methods: In this study, 52 radiographic images were queried on the OpenAI application ChatGPT-4.0. The responses were evaluated with and without using clues for specific radiographs to see if adding clues during prompting improved diagnostic accuracy. Results: The true prediagnosis rate without any clue was 30.7%. By adding one clue this rate significantly increased to 56.9%. There was not a significant difference in accurate diagnosis of anatomical landmarks, cysts, and tumors (p>0.05). However, including internal structure information improved the diagnostic accuracy (p<0.05) Conclusion: GPT-4.0 showed a tendency to misdiagnose closely located anatomical structures and by adding additional clues its performance showed improvement, while its ability to recognize diverse differential diagnoses remains limited.https://foliamedica.bg/article/135584/download/pdf/ |
| spellingShingle | Shila Kahalian Marieh Rajabzadeh Melisa Öçbe Mahmut Sabri Medisoglu ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images Folia Medica |
| title | ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images |
| title_full | ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images |
| title_fullStr | ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images |
| title_full_unstemmed | ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images |
| title_short | ChatGPT-4.0 in oral and maxillofacial radiology: prediction of anatomical and pathological conditions from radiographic images |
| title_sort | chatgpt 4 0 in oral and maxillofacial radiology prediction of anatomical and pathological conditions from radiographic images |
| url | https://foliamedica.bg/article/135584/download/pdf/ |
| work_keys_str_mv | AT shilakahalian chatgpt40inoralandmaxillofacialradiologypredictionofanatomicalandpathologicalconditionsfromradiographicimages AT mariehrajabzadeh chatgpt40inoralandmaxillofacialradiologypredictionofanatomicalandpathologicalconditionsfromradiographicimages AT melisaocbe chatgpt40inoralandmaxillofacialradiologypredictionofanatomicalandpathologicalconditionsfromradiographicimages AT mahmutsabrimedisoglu chatgpt40inoralandmaxillofacialradiologypredictionofanatomicalandpathologicalconditionsfromradiographicimages |