Machine Learning & Artificial Intellgience
Machine learning and AI-powered solutions have great potential to support busy health care providers. Malone researchers build better algorithms that help providers diagnose disease earlier, operate more precisely, streamline the patient experience, and more.
PIs: Swaroop Vedula, Greg Hager, Anand Malpani, Mathias Unberath, Brian Caffo
Machine learning (ML) & artificial intelligence (AI) frameworks are expected to play a significant role in driving innovation and discovery in healthcare research. Examples of ML & AI applications in health care include medical imaging and diagnostics, robot-assisted surgeries, and remote care assistance.
To foster research collaborations using ML & AI, we must bridge the knowledge gap between healthcare decision-makers and engineers/data scientists. Specifically, both groups should understand ML & AI methods and how algorithms are validated for healthcare applications.
The Malone team will develop an online course to equip both Hopkins clinicians and engineers with the skills to design, analyze, interpret, and report research on ML & AI in health care.
PIs: Ferdinand Hui, Haris Sair, Paul Yi
RAIL is an open structured artificial intelligence focused research collaboration based in the Hopkins Department of Radiology and Radiological Sciences. The group is comprised of physicians and scientists from Johns Hopkins Hospital, the Whiting School of Engineering, and the Applied Physics Laboratory, leveraging subject matter expertise of clinical imaging domains and computer vision. RAIL aims to be a:
1) a Hopkins wide resource and touchstone for data science collaboration, particularly in image processing and analysis
2) an international leader in research, development, and commercialization of information technology related to artificial intelligence in imaging informatics.
PI: Mathias Unberath
Glaucoma is the second leading cause of blindness globally, with approximately 79.6 million people expected to be affected by the disease by 2020. Automated visual field (VF) testing remains the gold standard for identifying patients with glaucoma and judging worsening of disease. Approximately 5% of patients with glaucoma undergo rapid worsening of their VF test.
Early identification of these rapid progressors may allow ophthalmologists to perform medical and surgical intervention earlier to preserve visual function. The objective of this project is to develop machine learning algorithms that allow for sensitive and specific identification of patients at risk for undergoing rapid progression. This will be achieved with a two-step process:
- We propose to expand a longitudinal dataset of 10,000+ VF (patient functional data) to include optic nervev imaging data routinely acquired in assessment of glaucoma and clinical data.
- We will train machine learning models to predict the risk for future rapid worsening of NFs based on initial function (VF), structural (OCT) and clinical data.
We hypothesize that our machine learning models will be able to predict risk of future progression with high sensitivity and specificity.
News | Machine learning & AI
The team will develop an online course about machine learning aimed at those working in the healthcare research field.
She was named to the annual list for her pioneering work detecting the source of epileptic seizures in the brain.
Winning project teams—chosen from a record 222 proposals—include 120 individuals from across the university.