This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessReview
Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models
by
Baradwaj Simha Sankar
Baradwaj Simha Sankar 1,2,†,
Destiny Gilliland
Destiny Gilliland 1,2,†,
Jack Rincon
Jack Rincon 1,2,
Henning Hermjakob
Henning Hermjakob 3,
Yu Yan
Yu Yan 1,2,4,
Irsyad Adam
Irsyad Adam 1,2,4,
Gwyneth Lemaster
Gwyneth Lemaster 1,
Dean Wang
Dean Wang 1,2,
Karol Watson
Karol Watson
Dr. Karol Watson is
an attending cardiologist and a Professor of Medicine/Cardiology at the School [...]
Dr. Karol Watson is
an attending cardiologist and a Professor of Medicine/Cardiology at the David
Geffen School of Medicine at the University of California, Los Angeles (UCLA),
USA. She is also the Director of the UCLA Women’s Cardiovascular Health Center.
Dr. Watson received her MD from Harvard Medical School and a PhD in Physiology
from UCLA. She also completed a residency in Internal Medicine and a fellowship
in Cardiology at UCLA and continued there as part of the UCLA Specialty
Training and Academic Research program and as Chief Fellow in Cardiovascular
Diseases. The American Society of Hypertension recognizes Dr. Watson as a
Specialist in Hypertension. She chairs the Cholesterol committee of the
Association of Black Cardiologists, and serves on several committees and panels
of the National Institutes of Health, including serving on the NIH Expert Panel
for the Integrated Clinical Guideline for Cardiovascular Risk Reduction.
5,6,
Alex Bui
Alex Bui
Dr. Alex Bui is the Director for both the Medical & Imaging Informatics (MII) Group and the Medical [...]
Dr. Alex Bui is the Director for both the Medical & Imaging Informatics (MII) Group and the Medical Informatics Home Area. He is also the Senior Associate Dean for Bioscience Graduate and Postdoctoral Affairs at David Geffen School of Medicine, University of California, Los Angeles (UCLA), USA. Dr. Bui received his PhD in Computer Science in 2000, upon which he joined the UCLA faculty. His research includes informatics and data science for biomedical research and healthcare in areas related to distributed information architectures and mHealth. His work bridges contemporary computational approaches with the opportunities arising from the breadth of biomedical observations and the electronic health record (EHR), tackling the associated translational challenges.
6,
Wei Wang
Wei Wang
Dr. Wei Wang is the
Leonard Kleinrock, Chair Professor in Computer Science and at the University of [...]
Dr. Wei Wang is the
Leonard Kleinrock, Chair Professor in Computer Science and Computational
Medicine at the University of California, Los Angeles (UCLA) and the director
of the Scalable Analytics Institute (ScAi). She is also a member of the UCLA
Jonsson Comprehensive Cancer Center, Institute for Quantitative and
Computational Biology, and Bioinformatics Interdepartmental Graduate Program.
She received her PhD in Computer Science from UCLA in 1999. Dr. Wang’s research
interests include AI, big data analytics, data mining, machine learning,
natural language processing, bioinformatics and computational biology, and
computational medicine. She has filed seven patents and has published one
monograph and more than three hundred research papers in international journals
and major peer-reviewed conference proceedings, including multiple best paper
awards. She is a Fellow of ACM and IEEE.
6,7,* and
Peipei Ping
Peipei Ping
Dr. Peipei Ping is
the Director of Integrated Data Science Training in Cardiovascular Medicine of a [...]
Dr. Peipei Ping is
the Director of Integrated Data Science Training in Cardiovascular Medicine at
the University of California, Los Angeles (UCLA), USA. She received a B.S. in
Biomedical Engineering from Zhejiang University, China, and a PhD in Cardiovascular
Physiology from the University of Arizona. Dr. Ping has significantly
contributed to cardiovascular research, proteomics phenotyping, and Big Data
science. She characterized the cardioprotective role of PKCε as well as other
underlying mechanisms in cardiac injury and protection, pioneered the
conceptualization and development of functional proteomics approaches to
characterize signaling pathways in the heart, advanced proteomics/metabolomics
technologies, including model systems, quantitative analyses, PTM studies,
protein spatial/temporal dynamics, and omics data-driven biomarker discovery.
1,2,4,5,6,*
1
Department of Physiology, University of California, Los Angeles, CA 90095, USA
2
NIH CFDE ICC-SC, NIH BRIDGE2AI Center & NHLBI Integrated Cardiovascular Data Science Training Program, UCLA, Los Angeles, CA 90095, USA
3
European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Cambridge CB10 1SD, UK
4
Bioinformatics IDP, University of California, Los Angeles, CA 90005, USA
5
Department of Medicine, Cardiology Division, University of California, Los Angeles, CA 90095, USA
6
Medical Informatics Home Area, University of California, Los Angeles, CA 90095, USA
7
Department of Computer Science, University of California, Los Angeles, CA 90095, USA
*
Authors to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Bioengineering 2024, 11(10), 984; https://doi.org/10.3390/bioengineering11100984 (registering DOI)
Submission received: 14 August 2024
/
Revised: 17 September 2024
/
Accepted: 24 September 2024
/
Published: 29 September 2024
Abstract
Foundation Models (FMs) are gaining increasing attention in the biomedical artificial intelligence (AI) ecosystem due to their ability to represent and contextualize multimodal biomedical data. These capabilities make FMs a valuable tool for a variety of tasks, including biomedical reasoning, hypothesis generation, and interpreting complex imaging data. In this review paper, we address the unique challenges associated with establishing an ethical and trustworthy biomedical AI ecosystem, with a particular focus on the development of FMs and their downstream applications. We explore strategies that can be implemented throughout the biomedical AI pipeline to effectively tackle these challenges, ensuring that these FMs are translated responsibly into clinical and translational settings. Additionally, we emphasize the importance of key stewardship and co-design principles that not only ensure robust regulation but also guarantee that the interests of all stakeholders—especially those involved in or affected by these clinical and translational applications—are adequately represented. We aim to empower the biomedical AI community to harness these models responsibly and effectively. As we navigate this exciting frontier, our collective commitment to ethical stewardship, co-design, and responsible translation will be instrumental in ensuring that the evolution of FMs truly enhances patient care and medical decision-making, ultimately leading to a more equitable and trustworthy biomedical AI ecosystem.
Share and Cite
MDPI and ACS Style
Sankar, B.S.; Gilliland, D.; Rincon, J.; Hermjakob, H.; Yan, Y.; Adam, I.; Lemaster, G.; Wang, D.; Watson, K.; Bui, A.;
et al. Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models. Bioengineering 2024, 11, 984.
https://doi.org/10.3390/bioengineering11100984
AMA Style
Sankar BS, Gilliland D, Rincon J, Hermjakob H, Yan Y, Adam I, Lemaster G, Wang D, Watson K, Bui A,
et al. Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models. Bioengineering. 2024; 11(10):984.
https://doi.org/10.3390/bioengineering11100984
Chicago/Turabian Style
Sankar, Baradwaj Simha, Destiny Gilliland, Jack Rincon, Henning Hermjakob, Yu Yan, Irsyad Adam, Gwyneth Lemaster, Dean Wang, Karol Watson, Alex Bui,
and et al. 2024. "Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models" Bioengineering 11, no. 10: 984.
https://doi.org/10.3390/bioengineering11100984
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.