Jessica S Ancker, MPH, PhD, FACMI

When nudges are better than decision support: Intentional choice architectures in IT, policy, and research

Jessica S Ancker

  • Vanderbilt University
  • Professor, Department of Biomedical Informatics and Department of Health Policy

Abstract: The great promise of innovative technologies such as AI is that they will advance human health by helping us summarize information, make diagnoses, predict health outcomes, or offer recommendations. However, as we develop ways for doctors or patients to use AI outputs for decisions, it is critical to recognize that information alone does not determine peoples’ decisions. We are also heavily influenced by our environment – whether physical or electronic – and the options that it presents us. These options and the ways they are presented are collectively known as the “choice architecture.” Aspects of the choice architecture which encourage people to select certain options are generally known as “nudges.” Using case studies from biomedical informatics, I will show how choice architectures shape our day-to-day decisions in ways that we are not always aware of, and how they may interfere with the ability to apply information to make decisions. I will also demonstrate how people who design information technologies are in a unique position to leverage intentional choice architectures to reduce cognitive burden and nudge people to select the best option. By broadening our understanding of human decision-making processes, we maximize the likelihood that AI will deliver on its promise.

Biography:Dr. Jessica Ancker is a tenured professor in the departments of biomedical informatics and health policy at Vanderbilt University Medical Center in Nashville, TN. Her research focuses on information technologies to support decision-making. She has conducted multiple studies on understanding and improving patients’ ability to use quantitative data for health decisions. She also conducts large-scale evaluation research on the impacts of information technologies on health outcomes. Her work has been funded by the NIH, the NSF, AHRQ, and PCORI. Dr. Ancker serves as vice chair for educational affairs in the department of biomedical informatics and is associate editor of the Journal of the American Medical Informatics Association (JAMIA) and Medical Decision Making.


Transforming Medicine with AI: from PubMed Search to TrialGPT

Zhiyong Lu

  • Senior Investigator, NIH/NLM
  • Deputy Director for Literature Search, NCBI
  • Professor of Computer Science (Adjunct), UIUC

Abstract: The explosion of biomedical big data and information in the past decade or so has created new opportunities for discoveries to improve the treatment and prevention of human diseases. As such, the field of medicine is undergoing a paradigm shift driven by AI-powered analytical solutions. This talk explores the benefits (and risks) of AI and ChatGPT, highlighting their pivotal roles in revolutionizing biomedical discovery, patient care, diagnosis, treatment, and medical research. By demonstrating their uses in some real-world applications such as improving PubMed searches (Fiorini et al., Nature Biotechnology 2018), supporting precision medicine (LitVar, Allot et al., Nature Genetics 2023), and accelerating patient trial matching (TrialGPT), we underscore the potential of AI and ChatGPT in enhancing clinical decision-making, personalizing patient experiences, and accelerating knowledge discovery.

Biography: Dr. Zhiyong Lu is a tenured Senior Investigator at the NIH/NLM IPR, leading research in biomedical text and image processing, information retrieval, and AI/machine learning. In his role as Deputy Director for Literature Search at NCBI, Dr. Lu oversees the overall R&D efforts to improve literature search and information access in resources like PubMed and LitCovid, which are used by millions worldwide each day. Additionally, Dr. Lu is Adjunct Professor of Computer Science at the University of Illinois Urbana-Champaign (UIUC). Dr. Lu serves as an Associate Editor of Bioinformatics, Organizer of the BioCreative NLP challenge, and Chair of the ISCB Text Mining COSI. With over 350 peer-reviewed publications, Dr. Lu is a highly cited author, and a Fellow of the American College of Medical Informatics (ACMI) and the International Academy of Health Sciences Informatics (IAHSI).

Jens Kleesiek, MD PhD, PhD

From Code to Clinic: Ingredients for the Translation of AI Algorithms to the Point of Care

Jens Kleesiek

  • Director Medical Machine Learning, Institute for AI in Medicine (IKIM)
  • Associate Director for Data and IT, West German Cancer Center (WTZ)
  • University Hospital Essen, Germany
  • Full-Professor for Translational Image-guided Oncology, University of Duisburg-Essen, Germany
  • Professor of Physics (Adjunct), Dortmund Technical University, Germany

Abstract: AI algorithms are widely recognized as having a crucial role in the future of healthcare and patient care. However, their successful implementation faces several challenges. Most importantly, tangible benefits for patients remain to be shown. Others include certification, monitoring, and billing. This presentation will discuss challenges and necessary components for delivering algorithms at the point of care. The University Hospital Essen, Germany has developed a suitable ecosystem, comprising both people and machines. Practical examples will be provided, and lessons learned will be discussed.

Biography: Dr. Kleesiek is a full professor at the Institute for Artificial Intelligence in Medicine (IKIM) of the University Medical Center Essen, Germany. As Associate Director of the West German Cancer Center, he is responsible for data and IT. He studied medicine in Heidelberg, Germany, specializing in radiology and medical informatics. He also studied bioinformatics at the University of Hamburg, Germany, earning a PhD in Computer Science. He has several years of experience in management positions in developing medical software for consumers and healthcare professionals. His research focuses on self- and weakly-supervised learning methods for detecting clinically relevant patterns in medical data and integrating multimodal information to improve decision-making at the point of care