Working Group Webinar Library

The explosion of biomedical big data and information over the past decade has created new opportunities for discoveries that can improve the treatment and prevention of human diseases. As a result, the field of medicine is undergoing a paradigm shift driven by AI-powered analytical solutions. This talk will present the use of AI and large language models (LLMs) in recent natural language processing (NLP) research, highlighting their capabilities and limitations in various information-extraction tasks. We will also discuss the use of retrieval-augmented generation to improve standard LLMs in medicine and conclude with a case study on leveraging LLMs to assist and enhance efficiency in patient-to-trial matching. Presenter

This presentation will highlight ongoing and past work on developing NLP and machine learning methods for effectively leveraging social media data for substance use research.

Translational research in Artificial Intelligence (AI) for healthcare has long been constrained by the lack of robust, diverse, and accessible data resources. The newly launched CRITICAL dataset addresses this challenge by providing an unprecedented resource to accelerate innovation in critical care and beyond.

Real world evidence (RWE) offers an opportunity to conduct timely, large, low-cost studies to answer important clinical questions that may not always be feasible to investigate using randomized controlled trials for practical, financial or ethical reasons. However, RWE research also faces several important challenges.

Pulmonary embolism (PE) presents a significant diagnostic challenge, necessitating clear and precise communication between radiologists and referring physicians to optimize patient outcomes. Variability in the language used to convey diagnostic uncertainty in computed tomographic pulmonary angiography (CTPA) reports can exacerbate ambiguity, potentially leading to inappropriate clinical management and compromised patient care.