Publications by authors named "K R Parekh"

Aims And Objectives: This study aimed to compare the accuracy of two AI models - OpenAI's GPT-4 Turbo (San Francisco, CA) and Meta's LLaMA 3.1 (Menlo Park, CA) - when answering a standardized set of pediatric radiology questions. The primary objective was to evaluate the overall accuracy of each model, while the secondary objective was to assess their performance within subsections.

View Article and Find Full Text PDF

Recent advancements in natural language processing (NLP) have profoundly transformed the medical industry, enhancing large cohort data analysis, improving diagnostic capabilities, and streamlining clinical workflows. Among the leading tools in this domain is ChatGPT 4.0 (OpenAI, San Francisco, California, US), a commercial NLP model widely used across various applications.

View Article and Find Full Text PDF

Cell phenotype underlies prostate cancer presentation and treatment resistance and can be regulated by epigenomic features. However, the osteotropic tendency of prostate cancer limits access to metastatic tissue, meaning most prior insights into prostate cancer chromatin biology are from preclinical models that do not fully represent disease complexity. Noninvasive chromatin immunoprecipitation of histones in plasma cell-free in humans may enable capture of disparate prostate cancer phenotypes.

View Article and Find Full Text PDF

Event-related potentials (ERPs) are small voltage changes in the brain that reliably occur in response to auditory or visual stimuli. ERPs have been extensively studied in both humans and animals to identify biomarkers, test pharmacological agents, and generate testable hypotheses about the physiological and genetic basis of schizophrenia. In this chapter, we discuss how ERPs are generated and recorded as well as review canonical ERP components in the context of schizophrenia research in humans.

View Article and Find Full Text PDF

Aims And Objectives: This study evaluates the accuracy of two AI language models, ChatGPT 4.0 and Google Gemini (as of August 2024), in answering a set of 79 text-based pediatric radiology questions from "Pediatric Imaging: A Core Review." Accurate interpretation of text and images is critical in radiology, making AI tools valuable in medical education.

View Article and Find Full Text PDF