AI and Clinical Practice—Discovery and Scaling Findings From Large, Multicenter Health Care Datasets
Jan 24, 2024
auto_awesome
Atul Butte, Director of the Bakar Computational Health Sciences Institute at UCSF, discusses using AI to democratize healthcare, utilizing large datasets for comparative effectiveness research, ensuring patient data privacy, improving healthcare outcomes through data analysis, and addressing the risks of AI language model extrapolation.
Real-world data can enhance medical practice by evaluating treatment effectiveness beyond RCTs.
AI tools can scale privilege and improve access to quality care for all patients.
Deep dives
The Use of Real-World Data in Research
Dr. Atul Butte discusses the importance of using real-world data in research and how it can help improve the practice of medicine. With a centralized data warehouse containing information from 9.1 million patients, the University of California is able to compare and contrast different treatments and interventions to assess their effectiveness.
The Role of Real-World Evidence
While randomized controlled trials (RCTs) remain the gold standard for evaluating new therapeutics, Dr. Butte emphasizes that real-world evidence (RWE) has an important role to play in answering clinical questions that may not be feasible in an RCT. RWE allows researchers to study the outcomes and variations in practice that occur in the real world, providing insights into the effectiveness and safety of different treatments.
Scaling Privilege Through AI
Dr. Butte discusses the potential of AI to scale privilege and improve access to quality care for all patients. By using AI tools, developed from analyzing large and diverse datasets, health systems can assist clinicians and patients in making informed decisions and provide guidance based on real-world data. This can help ensure that the benefits of optimized care reach patients in all healthcare settings, regardless of their location or access to specialized centers.
How can we leverage AI to transform health care into a more efficient model for delivering care? In this Q&A, JAMA Editor in Chief Kirsten Bibbins-Domingo, PhD, MD, MAS, interviews Atul Butte, MD, PhD, the director of the Bakar Computational Health Sciences Institute at UCSF, to discuss scalable privilege and the need for the broad distribution of AI-driven expertise. Related Content: