Search Articles

View query in Help articles search

Search Results (1 to 10 of 23 Results)

Download search results: CSV END BibTex RIS


Performance of ChatGPT-4o on the Japanese Medical Licensing Examination: Evalution of Accuracy in Text-Only and Image-Based Questions

Performance of ChatGPT-4o on the Japanese Medical Licensing Examination: Evalution of Accuracy in Text-Only and Image-Based Questions

Chat GPT with GPT-4 Omni (GPT-4o), released May 13, 2024, represents significantly more natural human-computer interaction; it can accept input as text, audio, images, and video and create output as text, audio, and images [7], promising improved performance on image-based questions. Recent research has shown that GPT-4 has superior performance on psychiatric licensing examinations, emphasizing its potential in various medical fields [8].

Yuki Miyazaki, Masahiro Hata, Hisaki Omori, Atsuya Hirashima, Yuta Nakagawa, Mitsuhiro Eto, Shun Takahashi, Manabu Ikeda

JMIR Med Educ 2024;10:e63129

The Application of Mask Region-Based Convolutional Neural Networks in the Detection of Nasal Septal Deviation Using Cone Beam Computed Tomography Images: Proof-of-Concept Study

The Application of Mask Region-Based Convolutional Neural Networks in the Detection of Nasal Septal Deviation Using Cone Beam Computed Tomography Images: Proof-of-Concept Study

The aim of this research was to develop a real-time AI model to detect NSD and determine its accuracy in detecting NSD in CBCT images. We collected 204 coronal CBCT images of the nasal septum (138 with a deviated nasal septum and 66 with a nondeviated nasal septum) from the dental radiology archives of University Dental Hospital, Sharjah.

Shishir Shetty, Auwalu Saleh Mubarak, Leena R David, Mhd Omar Al Jouhari, Wael Talaat, Natheer Al-Rawi, Sausan AlKawas, Sunaina Shetty, Dilber Uzun Ozsahin

JMIR Form Res 2024;8:e57335

Automated Pain Spots Recognition Algorithm Provided by a Web Service–Based Platform: Instrument Validation Study

Automated Pain Spots Recognition Algorithm Provided by a Web Service–Based Platform: Instrument Validation Study

There are different methods for scanning PDs, including using a flatbed scanner, a device that scans flat, thin documents placed on a glass window; a handheld scanner, a portable device that can scan images while being moved over them; a drum scanner, a high-end scanner that uses a rotating cylinder to capture the image; a multifunctional printer scanner, a printer that also includes a scanner function; and a virtual scanner, a software that can use a camera to scan images.

Corrado Cescon, Giuseppe Landolfi, Niko Bonomi, Marco Derboni, Vincenzo Giuffrida, Andrea Emilio Rizzoli, Paolo Maino, Eva Koetsier, Marco Barbero

JMIR Mhealth Uhealth 2024;12:e53119

Feasibility of Multimodal Artificial Intelligence Using GPT-4 Vision for the Classification of Middle Ear Disease: Qualitative Study and Validation

Feasibility of Multimodal Artificial Intelligence Using GPT-4 Vision for the Classification of Middle Ear Disease: Qualitative Study and Validation

We excluded images with poor quality and those in which multiple diseases were suspected. The remaining images were classified into 4 disease categories: acute otitis media (AOM), middle ear cholesteatoma (chole), chronic otitis media (COM), and otitis media with effusion (OME). The final diagnoses were based on the judgment of the otolaryngologists who treated the patients.

Masao Noda, Hidekane Yoshimura, Takuya Okubo, Ryota Koshu, Yuki Uchiyama, Akihiro Nomura, Makoto Ito, Yutaka Takumi

JMIR AI 2024;3:e58342

The Performance of ChatGPT-4V in Interpreting Images and Tables in the Japanese Medical Licensing Exam

The Performance of ChatGPT-4V in Interpreting Images and Tables in the Japanese Medical Licensing Exam

To assess the multimodal performance of Chat GPT-4 V in medicine, its performance on JMLE questions involving clinical images and tables was tested. Chat GPT-4 V was used to complete the 117th JMLE in the Japanese language (Figure S1 in Multimedia Appendix 1). Its responses were compared to the passing criteria and mean human examinee score of the JMLE.

Soshi Takagi, Masahide Koda, Takashi Watari

JMIR Med Educ 2024;10:e54283

Visual “Scrollytelling”: Mapping Aquatic Selfie-Related Incidents in Australia

Visual “Scrollytelling”: Mapping Aquatic Selfie-Related Incidents in Australia

(B), (C), and (D) Example images acquired from the web-based site. These images illustrate the scrolling story of the heat map focusing on a location that has seen selfie-related incidents. Each incident is indicated in a “chapter,” which provides a description of the incident in that location and a link to the corresponding news report. Images were acquired from Mapbox [7] and Open Street Map [8]. Open Street Map is licensed under the Open Data Commons Open Database License [9].

Samuel Cornell, Amy E Peden

Interact J Med Res 2024;13:e53067

Photos Shared on Facebook in the Context of Safe Sleep Recommendations: Content Analysis of Images

Photos Shared on Facebook in the Context of Safe Sleep Recommendations: Content Analysis of Images

Reference 19: #sleepingbaby on Instagram: nonadherence of images to safe sleeping advice and implicationsimagesPhotos Shared on Facebook in the Context of Safe Sleep Recommendations: Content Analysis of Images

Kelly Pretorius, Sookja Kang, Eunju Choi

JMIR Pediatr Parent 2024;7:e54610