Exploring the role of Large Language Models in haematology: A focused review of applications, benefits and limitations.

Link: https://doi.org/10.1111/bjh.19738 Authors: Mudrik, Aya; Nadkarni, Girish N; Efros, Orly; Glicksberg, Benjamin S; Klang, Eyal; Soffer, Shelly Abstract: Large language models (LLMs) have significantly impacted various fields with their ability to understand and generate human-like text. This study explores the potential benefits and limitations of integrating LLMs, such as ChatGPT, into haematology practices. Utilizing systematic…

Read More

Assessing GPT-4 multimodal performance in radiological image analysis.

Link: https://doi.org/10.1007/s00330-024-11035-5 Authors: Brin, Dana; Sorin, Vera; Barash, Yiftach; Konen, Eli; Glicksberg, Benjamin S; Nadkarni, Girish N; Klang, Eyal Abstract: This study aims to assess the performance of a multimodal artificial intelligence (AI) model capable of analyzing both images and textual data (GPT-4V), in interpreting radiological images. It focuses on a range of modalities, anatomical…

Read More

Echocardiographic Predictors of Readiness for Double Switch Operation and Postoperative Ejection Fraction in Patients With Congenitally Corrected Transposition of the Great Arteries Undergoing Left Ventricular Retraining.

Link: https://doi.org/S0894-7317(24)00438-3 Authors: Duong, Son Q; Ho, Deborah; Punn, Rajesh; Sganga, Danielle; Mainwaring, Richard; Ma, Michael; Hanley, Frank L; Lee, Kyong-Jin; Maskatia, Shiraz A Abstract: In patients with congenitally corrected transposition of the great arteries (ccTGA), assessment of readiness for the double switch operation (DSO) after pulmonary arterial band (PAB) placement involves cardiac magnetic resonance…

Read More

Multimodal fusion learning for long QT syndrome pathogenic genotypes in a racially diverse population.

Link: https://doi.org/10.1038/s41746-024-01218-1 Authors: Jiang, Joy; Thi Vy, Ha My; Charney, Alexander; Kovatch, Patricia; Reddy, Vivek; Jayaraman, Pushkala; Do, Ron; Khera, Rohan; Chugh, Sumeet; Bhatt, Deepak L; Vaid, Akhil; Lampert, Joshua; Nadkarni, Girish Nitin Abstract: Congenital long QT syndrome (LQTS) diagnosis is complicated by limited genetic testing at scale, low prevalence, and normal QT corrected interval…

Read More

Distinguishing neonatal culture-negative sepsis from rule-out sepsis with artificial intelligence-derived graphs.

Link: https://doi.org/10.1038/s41390-024-03458-z Authors: Holmes, Emma; Kauffman, Justin; Juliano, Courtney; Duchon, Jennifer; Nadkarni, Girish N Abstract: Novel artificial intelligence methods can aide in identification of cases of conditions using only unstructured electronic health record data. This graph-based method compares comprehensive electronic health records among neonates using temporal data. This provides a scalable solution to distinguish culture…

Read More

Advancing radiology practice and research: harnessing the potential of large language models amidst imperfections.

Link: https://doi.org/10.1093/bjro/tzae022 Authors: Klang, Eyal; Alper, Lee; Sorin, Vera; Barash, Yiftach; Nadkarni, Girish N; Zimlichman, Eyal Abstract: Large language models (LLMs) are transforming the field of natural language processing (NLP). These models offer opportunities for radiologists to make a meaningful impact in their field. NLP is a part of artificial intelligence (AI) that uses computer…

Read More

Differentiation of Prior SARS-CoV-2 Infection and Postacute Sequelae by Standard Clinical Laboratory Measurements in the RECOVER Cohort.

Link: https://doi.org/10.7326/M24-0737 Authors: Erlandson, Kristine M; Geng, Linda N; Selvaggi, Caitlin A; Thaweethai, Tanayott; Chen, Peter; Erdmann, Nathan B; Goldman, Jason D; Henrich, Timothy J; Hornig, Mady; Karlson, Elizabeth W; Katz, Stuart D; Kim, C; Cribbs, Sushma K; Laiyemo, Adeyinka O; Letts, Rebecca; Lin, Janet Y; Marathe, Jai; Parthasarathy, Sairam; Patterson, Thomas F; Taylor, Brittany…

Read More