PSB 2024: Artificial Intelligence in Clinical Medicine: Generative and Interactive Systems at the Human-Machine Interface


This year’s session will solicit research papers related to revealing new and emerging machine learning and generative artificial intelligence and deep learning tools in the pipeline that aim to solve major challenges in medicine.

Machine learning and deep learning have revolutionized our ability to analyze and find patterns in multi-dimensional and intricate datasets. Recent advances in generative artificial intelligence have led to amazing large language model chatbots and text-to-image-generators. Freely available chatbots (i.e., ChatGPT) have suddenly given the general public access to interactive systems capable of passing medical licensing and clinical reasoning exams. Generative image models have been proposed as a way to transform images to protect patient privacy for the development of classification models. Leveraging these new methods can enhance patient care through several modalities, among them clinical decision support, monitoring tools, image interpretation, and triaging capabilities, even as in-depth studies are needed to assess the impact and implications of such systems on human lives.

A goal of this session is to showcase research that have identified a clinical need that can be addressed by these methods. While algorithms presented in this category will likely need additional validation prior to clinical deployment, there should be a clear clinical use case with humans and machines interacting to improve patient health at the heart of every submitted paper. This use case should be clearly described in the submission. We hope to facilitate a conversation on how machine learning/deep learning researchers and healthcare providers can work together to create a more effective health care system.

Author: Andrew Coelho

Session topics

We are interested in research looking at the applications of recent generative artificial intelligence models in solving real-word and well-defined problems in healthcare, novel methodologies and unique applications of previously developed methods, and clinical implementation of artificial intelligence tools.

The above are just a few of the ways healthcare can be improved from knowledge gained from artificial intelligence and multi-modal medical datasets.

Broadly, we are interested in:

  • Generative artificial intelligence methods to solve real-world problems in healthcare.
  • Applications of recent large language models and chatbots such as ChatGPT in analyzing clinical notes and solving narrow and well-defined healthcare tasks.
  • Generative image and video processing models for medical image and video analysis.
  • Multi-modal healthcare data analysis using artificial intelligence models to solve well-defined clinical tasks.
  • Clinical validation of recent language and image analysis models.
  • Novel applications of artificial intelligence in healthcare.
  • Computational methods for public health that can screen large populations with high specificity.
  • Computational approaches to analyze data, especially of varied types, to help inform diagnosis, including decision support tools to help streamline diagnosis or treatment.
  • Methods for integrating the most up to date literature evidence and guidelines into clinical practice.
  • Tools for analyzing multi-modal data such as lifestyle, environmental, geographic, and healthcare records to gain new insights for delivering better or tailored clinical care.
  • Tools or methods that aid in data-centric artificial intelligence, with applications to medical tasks.
  • Tools and methods for assessing bias in artificial intelligence algorithms.
  • Tools and methods that aid in machine learning auditing and monitoring in the healthcare system.
  • Tools or methods that aid in interpretability or explainability for machine learning in healthcare.

Session organizers

Jonathan H. Chen

Stanford School of Medicine

✉️ e-mail

Roxana Daneshjou*

Stanford School of Medicine University

✉️ e-mail

David Ouyang

Smidt Heart Institute, Cedars-Sinai Medical Center

✉️ e-mail

Emma Pierson

Cornell Tech, Cornell University

✉️ e-mail

Ivana Jankovic

Elevance Health

✉️ e-mail

Sajjad Fouladvand

Stanford School of Medicine

✉️ e-mail

*Primary contact:
Roxana Daneshjou,

Submission Information

The submitted papers are fully reviewed and accepted on a competitive basis.

Important dates

  • August 1, 2023: Call for papers deadline (no extensions will be granted)
  • September 11, 2023: Notification of paper acceptance.
  • October 2, 2023: Camera-ready final papers deadline.
  • December 4, 2023: Poster abstract submission deadline.
  • January 3-7, 2024: Conference dates.
  • All deadlines are due by 11:59 PT

Paper Format and Submission Portal

Please see the PSB paper format template and instructions at

Paper Submissions

Unlike the abstracts at most biology conferences, papers in the PSB proceedings are archival, rigorously peer-reviewed publications. PSB publications are Open Access and linked directly from MEDLINE/PubMed and Google Scholar for wide accessibility. They should be thought of as short journal articles that may be cited on CVs and grant reports.

Travel Fellowships for Trainees

PSB traditionally provides fellowships for select trainees. The application process opens upon paper acceptance. Individuals from underrepresented communities are particularly encouraged to participate in the conference and apply for travel support.

Poster Format and Submission Portal

Poster presenters will be provided with an easel and a poster board 32"W x 40"H (80x100cm). One poster from each paid participant is permitted. See the submission portal web site for the instructions regarding poster submissions.

Last updated: April 11th, 2023