Precision of artificial intelligence in paediatric cardiology multimodal image interpretation DOI Creative Commons
Michael Gritti, Rahil Prajapati, Dolev Yissar

и другие.

Cardiology in the Young, Год журнала: 2024, Номер unknown, С. 1 - 6

Опубликована: Ноя. 11, 2024

Multimodal imaging is crucial for diagnosis and treatment in paediatric cardiology. However, the proficiency of artificial intelligence chatbots, like ChatGPT-4, interpreting these images has not been assessed. This cross-sectional study evaluates precision ChatGPT-4 multimodal cardiology knowledge assessment, including echocardiograms, angiograms, X-rays, electrocardiograms. One hundred multiple-choice questions with accompanying from textbook

Язык: Английский

Textual Proficiency and Visual Deficiency: A Comparative Study of Large Language Models and Radiologists in MRI Artifact Detection and Correction DOI
Yasin Celal Güneş, Turay Cesur, Eren Çamur

и другие.

Academic Radiology, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

Automated MRI Video Analysis for Pediatric Neuro-Oncology: An Experimental Approach DOI Creative Commons
Artur Fabijan, Agnieszka Zawadzka-Fabijan,

Robert Fabijan

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(18), С. 8323 - 8323

Опубликована: Сен. 15, 2024

Over the past year, there has been a significant rise in interest application of open-source artificial intelligence models (OSAIM) field medicine. An increasing number studies focus on evaluating capabilities these image analysis, including magnetic resonance imaging (MRI). This study aimed to investigate whether two most popular AI models, namely ChatGPT 4o and Gemini Pro, can analyze MRI video sequences with single-phase contrast sagittal frontal projections, depicting posterior fossa tumor corresponding medulloblastoma child. The utilized files from contrast-enhanced head planes (frontal sagittal) child diagnosed tumor, type medulloblastoma, confirmed by histopathological examination. Each model was separately provided file, first plane, analyzing three different sets commands general specific. same procedure applied file plane. Pro did not conduct detailed analysis pathological change but correctly identified content indicating it brain MRI, suggested that specialist should perform evaluation. Conversely, conducted failed recognize MRI. attempts detect lesion were random varied depending These could accurately identify or indicate area neoplastic change, even after applying queries. results suggest despite their widespread use various fields, require further improvements specialized training effectively support medical diagnostics.

Язык: Английский

Процитировано

1

Comparative analysis of artificial intelligence-driven assistance in diverse educational queries: ChatGPT vs. Google Bard DOI Creative Commons
Mohammad Al Mashagbeh, Latefa Ali Dardas, Heba Alzaben

и другие.

Frontiers in Education, Год журнала: 2024, Номер 9

Опубликована: Сен. 26, 2024

Artificial intelligence tools are rapidly growing in education, highlighting the imperative need for a thorough and critical evaluation of their performance. To this aim, study tests effectiveness ChatGPT Google Bard answering range questions within engineering health sectors. True/false, multiple choice (MCQs), matching, short answer, essay, calculation among question types investigated. Findings showed that 4 surpasses both 3.5 terms creative problem-solving accuracy across various types. The highest achieved by was true/false questions, reaching 97.5%, while its least accurate performance noted with an 82.5%. Prompting to provide responses apparently prevented them from hallucinating unrealistic or nonsensical responses. majority problems which provided incorrect answers demonstrated correct approach; however, AI models struggled accurately perform simple calculations. In MCQs related sciences, seemed have challenge discerning answer several plausible options. While all three managed essay competently, avoiding any blatantly (unlike other types), some nuanced differences were noticed. consistently adhered more closely prompts, providing straightforward essential responses, superiority over adaptability. ChatGPT4 fabricated references, creating nonexistent authors research titles response prompts sources. utilizing education holds promise, even latest most advanced versions not able questions. There remains significant human cognitive skills further advancements capabilities.

Язык: Английский

Процитировано

0

Precision of artificial intelligence in paediatric cardiology multimodal image interpretation DOI Creative Commons
Michael Gritti, Rahil Prajapati, Dolev Yissar

и другие.

Cardiology in the Young, Год журнала: 2024, Номер unknown, С. 1 - 6

Опубликована: Ноя. 11, 2024

Multimodal imaging is crucial for diagnosis and treatment in paediatric cardiology. However, the proficiency of artificial intelligence chatbots, like ChatGPT-4, interpreting these images has not been assessed. This cross-sectional study evaluates precision ChatGPT-4 multimodal cardiology knowledge assessment, including echocardiograms, angiograms, X-rays, electrocardiograms. One hundred multiple-choice questions with accompanying from textbook

Язык: Английский

Процитировано

0