Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Automated Medical Diagnostic Systems

Principal Investigator
Name
Fabien Scalzo
Degrees
B.S., M.S., Ph.D.
Institution
University of California, Los Angeles (UCLA)
Position Title
Assistant Professor in Residence
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCO-711
Initial CDAS Request Approval
Dec 29, 2020
Title
Automated Medical Diagnostic Systems
Summary
In our study, we are pioneering an entirely novel approach to automated medical diagnostic systems. The focus of our research is integrating machine learning and probabilistic reasoning for medical diagnosis. Our group is looking at improving diagnostic procedures by reducing unnecessary tests or recommending necessary ones using probabilistic modeling, while optimizing several criteria including minimizing cost and invasiveness.

Previous work in automated medical diagnostic systems is fairly rare because it is exceedingly difficult and current advances in machine learning are not able to effectively address the sentential decision-making involved. While reinforcement learning has been proposed, there are still many challenges to utilizing reinforcement learning in real world settings like in healthcare. We propose an entirely new approach that integrates machine learning and reasoning by utilizing Same-Decision Probability to propose optimal diagnostic pathways. High quality automated diagnostic systems could significantly improve healthcare outcomes and reduce healthcare costs, drastically improving quality of life for patients.
Aims

- Demonstrate the usefulness of Same-Decision Probability to improve upon standard medical diagnostic procedure by recommending optimal diagnostic pathways
- Utilize probabilistic reasoning techniques, like Same-Decision Probability, to reduce the number of diagnostic tests - including blood tests, physical examinations, imaging, biopsies, etc. - needed to confirm a prostate cancer diagnosis while improving the diagnostic accuracy.
- Utilize probabilistic reasoning techniques, like Same-Decision Probability, to reduce the number of diagnostic tests - including colonoscopies, sigmoidoscopies, stool blood samples, imaging, biopsies, etc. - needed to confirm a colorectal cancer diagnosis while improving the diagnostic accuracy

Collaborators

Fabien Scalzo, (B.S., M.S., Ph.D.)
Charles De Guzman (B.S., M.D. (Seeking))