Program for Clinical AI

Advancing the science, adoption, and effective use of artificial intelligence in health care

We develop, validate, and implement artificial intelligence (AI) tools to improve healthcare delivery. Like other areas of our lives, the role of AI in healthcare delivery will only increase over time. A key objective of the Program for Clinical AI (P4AI) is to investigate AI-enabled tools in real-world settings including monitoring AI model performance for drift, equity, and fitness for answering questions across settings and subpopulations. The P4AI team includes experts with a wide range of expertise across the University of Minnesota including the Medical School, School of Public Health, Institute for Health Informatics, and the College of Science and Engineering. We foster both national and international collaborations in natural language processing (NLP) and computer vision including the Federated Computer Vision in Healthcare Collaborative across multiple U.S. academic health systems.

Our services

P4AI Clinical Artificial Intelligence services include opportunities to collaborate on the following:

  • Creation of AI ready datasets 
    • Datasets can be used commercially by UMN researchers, non-commercially by external organizations
  • Model development and training
  • Facilitation of external validation of models with external academic partnerships
  • Database selection 
  • Model validation
  • AI consultation through the lifecycle of your project
  • Real-world deployment of AI/ML models into M Health Fairview

Collaboration Intake Process:

  1. If your request is suitable for a review, we then schedule a Problem Framing meeting to further clarify and define your research questions.
  2. After the Problem Framing meeting, your request is once more evaluated to determine if the scope of work fits within our Program’s purview. If yes, a Scope of Work agreement is created, which defines the scope of work that the P4AI will undertake to fulfill your needs.
  3. Once the Scope of Work agreement has been approved, the work begins. Depending on the scope and complexity, project timelines will vary from weeks to months.
  4. After the evidence review has been completed, we will schedule a meeting to present our findings. You will be provided with final, archivable documents for your use.

P4AI People

P4AI Leadership
Scientific co-Director: Christopher Tignanelli, MD, MS
Scientific co-Director: Gyorgy Simon, PhD

P4AI Full Members
Structured Healthcare Data: Gyorgy Simon, PhD
Computer Vision: Ju Sun, PhD
Natural Language Processing: Rui Zhang, PhD
Robotics and Surgical Automation: Elliot Arsoniadis, MD, PhD
Project Manager: Marley Crews-Hill

Featured Use Cases

Expand all

Featured Use Cases

2023

Re-Aiming Equity Evaluation in Clinical Decision Support: A Scoping Review of Equity Assessments in Surgical Decision Support Systems

Nicholas Ingraham, Emma Jones, Samantha King, James Dries, Michael Phillips, Tyler Loftus, Heather Evans, Genevieve Melton, Chris Tignanelli

Artificial Intelligence-enabled Decision Support in Surgery: State-of-the-art and Future Directions

Tyler Loftus, Maria Altieri, Jeremy Balch, Kenneth Abbott, Jeff Choi, Jayson Marwaha, Daniel Hashimoto, Gabriel Brat, Yannis Raftopoulos, Heather Evans, Gretchen Jackson, Danielle Walsh, Chris Tignanelli

Validation of a Proprietary Deterioration Index Model and Performance in Hospitalized Adults

Thomas Byrd, Bronwyn Southwell, Adarsh Ravishankar, Travis Tran, Abhinab Kc, Tom Phelan, Genevieve Melton-Meaux, Michael Usher, Daren Scheppmann, Sean Switzer, Gyorgy Simon, Chris Tignanelli 

A novel, evidence-based, comprehensive clinical decision support system improves outcomes for patients with traumatic rib fractures

Emma Jones, Ivana Ninkovic, Matthew Bahr, Sarah Dodge, Michael Doering, David Martin, Julie Ottosen, Tadashi Allen, Genevieve Melton, Chris Tignanelli

Ability of artificial intelligence to identify self-reported race in chest x-ray using pixel intensity counts

John Lee Burns, Zachary Zaiman, Jack Vanschaik, Gaoxiang Luo, Le Peng, Brandon Price, Garric Mathias, Vijay Mittal, Akshay Sagane, Chris Tignanelli, Sunandan Chakraborty, Judy W. Gichoya, Saptarshi Purkayastha

2022

A 12-hospital prospective evaluation of a clinical decision support prognostic algorithm based on logistic regression as a form of machine learning to facilitate decision making for patients with suspected COVID-19

Monica Lupei, Danni Li, Nicholas Ingraham, Karyn Baum, Bradley Benson, Michael Puskarich, David Milbrandt, Genevieve Melton, Daren Scheppmann, Michael Usher, Chris Tignanelli

Improved Prediction of Older Adult Discharge After Trauma Using a Novel Machine Learning Paradigm

Rachel Morris, Chris Tignanelli, Terri deRoon-Cassini, Purushottam Laud, Rodney Sparapani

Patient Heterogeneity and the J-Curve Relationship Between Time-to-Antibiotics and the Outcomes of Patients Admitted With Bacterial Infection

Michael Usher, Roshan Tourani, Ben Webber, Chris Tignanelli, Sisi Ma, Lisiane Pruinelli, Michael Rhodes, Nishant Sahni, Andrew Olson, Genevieve Melton, Gyorgy Simon

Performance of a Chest Radiograph AI Diagnostic Tool for COVID-19: A Prospective Observational Study

Ju Sun, Le Peng, Taihui Li, Dyah Adila, Zach Zaiman, Genevieve Melton-Meaux, Nicholas Ingraham, Eric Murray, Daniel Boley, Sean Switzer, John Burns, Kun Huang, Tadashi Allen, Scott Steenburg, Judy Wawira Gichoya, Erich Kummerfeld, Chris Tignanelli

Need for Emergent Intervention within 6 Hours: A Novel Prediction Model for Hospital Trauma Triage

Rachel Morris, Basil Karam, Emily Zolfaghari, Benjamin Chen, Thomas Kirsh, Roshan Tourani, David Milia, Lena Napolitano, Marc de Moya, Marc Conterato, Constantin Aliferis, Sisi Ma, Chris Tignanelli

Semi-automated Clinical Content Curation of COVID-19 Chatbot Remote Patient Monitoring Solution

Tanya Melnik, Joshua Thompson, Jake Vasilakes, Tucker Annis, Sicheng Zhou, Dalton Schutte, Genevieve Melton, Susan Pleasants, Rui Zhang

2021

A fast, resource efficient, and reliable rule-based system for COVID-19 symptom identification

Himanshu Sahoo, Greg Silverman, Nicholas Ingraham, Monica Lupei, Michael Puskarich, Raymond Finzel, John Sartori, Rui Zhang, Benjamin Knoll, Sijia Liu, Hongfang Liu, Genevieve Melton, Christopher Tignanelli, Serguei Pakhomov

Heterogeneity in COVID-19 Patients at Multiple Levels of Granularity: From Biclusters to Clinical Interventions

Suresh Bhavnani, Erich Kummerfeld, Weibin Zhang, Yong-Fang Kuo, Nisha Garg, Shyam Visweswaran, Mukaila Raji, Ravi Radhakrishnan, Georgiy Golvoko, Sandra Hatch, Michael Usher, Genevieve Melton-Meaux, Chris Tignanelli

2020

Natural language processing of prehospital emergency medical services trauma records allows for automated characterization of treatment appropriateness

Chris Tignanelli, Greg Silverman, Elizabeth Lindemann, Alexander Trembley, Jon Gipson, Gregory Beilman, John Lyng, Raymond Finzel, Reed McEwan, Benjamin Knoll, Serguei Pakhomov, Genevieve Melton

P4AI Recent News

CLHSS Team Creates Model That Effectively Predicts Sepsis. A team from CLHSS led by Drs. Mike Usher and Chris Tignanelli created a model that effectively predicts sepsis and identifies which patients would benefit from early antibiotics, leading to better patient outcomes.

Read more