Roxana Daneshjou

Jan 10, 2025 | jidonline.org | Temerty Faculty |Bryan Ma |Roxana Daneshjou

KeywordsArtificial intelligenceDermatology clinical trialsGenerative pretrained transformer (GPT)Large language modelsRecruitment and retention•The integration of large language models (LLMs) into dermatology clinical trials has the potential to improve patient recruitment and retention by addressing systemic barriers such as health literacy, language limitations, and geographic disparities, thereby promoting greater inclusivity and representation of underrepresented populations.

Jan 8, 2025 | nature.com | Jack Gallifant |Saleem Ameen |Yindalon Aphinyanaphongs |Shan Chen |Giovanni E. Cacciamani |Roxana Daneshjou | +7 more

AbstractLarge language models (LLMs) are rapidly being adopted in healthcare, necessitating standardized reporting guidelines. We present transparent reporting of a multivariable model for individual prognosis or diagnosis (TRIPOD)-LLM, an extension of the TRIPOD + artificial intelligence statement, addressing the unique challenges of LLMs in biomedical applications. TRIPOD-LLM provides a comprehensive checklist of 19 main items and 50 subitems, covering key aspects from title to discussion.

Sep 23, 2024 | nature.com | Roxana Daneshjou

As medical AI development gathers momentum, a new study reveals that much work still needs to be done before the public will willingly embrace AI-based technologies in healthcare.

Apr 8, 2024 | nature.com | Jiyeong Kim |Roxana Daneshjou

AbstractThe development of diagnostic tools for skin cancer based on artificial intelligence (AI) is increasing rapidly and will likely soon be widely implemented in clinical use. Even though the performance of these algorithms is promising in theory, there is limited evidence on the impact of AI assistance on human diagnostic decisions. Therefore, the aim of this systematic review and meta-analysis was to study the effect of AI assistance on the accuracy of skin cancer diagnosis.

Dec 27, 2023 | nature.com | Roxana Daneshjou

AbstractThe inferences of most machine-learning models powering medical artificial intelligence are difficult to interpret. Here we report a general framework for model auditing that combines insights from medical experts with a highly expressive form of explainable artificial intelligence.