Physicians at the University of California, Irvine and UCI Health System have launched the UCI Center for Artificial Intelligence in Diagnostic Medicine, which seeks to advance patient care, improve health outcomes and lower costs by leveraging machine learning technology in all areas of healthcare.
Led by Peter D. Chang, MD, and Daniel S. Chow, MD, neuroradiologists in the Department of Radiological Sciences, UCI School of Medicine, the center is a cross-specialty initiative with a specific focus on developing and applying deep learning neural networks to healthcare applications, such as diagnostics, disease prediction and therapy planning.
"Our goal is to empower health care providers, researchers and patients through the use of artificial intelligence in healthcare," said Chang.
The Center for Artificial Intelligence in Diagnostic Medicine will provide a central research core that enables all UCI faculty, physicians and researchers, to collaborate on translating AI-based concepts into clinical tools to improve individual and population health.
"The center will develop machine learning tools that can be implemented for routine clinical use today," said Chow.
Recent research by Chang, Chow and colleagues reflects the translational nature of their work.
In June, Chang was recognized by the American Society of Neuroradiology with the 2018 Cornelius G. Dyke Memorial Award for his work on developing a customized deep learning system with more than 97% accuracy in near real-time detection of brain hemorrhage on non-contrast CT (NCCT) head exams. The system was applied to more than 10,000 UCI Health imaging exams to test its efficiency and accuracy and was validated with prospectively-acquired data. The study included both detection and quantification of brain bleeds, including intracranial, intraparenchymal, epidural/subdural and subarachnoid hemorrhages.
"Intracranial hemorrhages are significant medical emergencies that results in 40% patient mortality, despite aggressive care," said Chang. "Early and accurate diagnosis is necessary for the management of life-threatening brain bleeds and to improve the odds of recovery."
The demonstrated high performance of real-time interpretation on prospective NCCTs ordered from the emergency department over a one-month period suggests the AI tool's clinical usefulness. The center is now preparing the system for clinical use in the UCI Medical Center emergency department.
"The research is an example of how we can use machine learning technology to improve the delivery of acute care in an emergency department by expediting triage of patient care and offering more detailed information to guide clinical decision making," said Chow. "An AI-based imaging may be used either as a triage system to assist radiologists in identifying high-priority exams for interpretation or as a method to rapidly quantify ICH volume, or both."
In other research, published this month in American Journal of Neuroradiology, Chang, Chow and colleagues developed an AI-based imaging technique that accurately analyzes genetic mutations in brain tumors and makes possible the use of virtual biopsies. The findings show improvements to a type of machine learning called convolutional neural networks and demonstrates the capability to recognize key imaging details without human direction.
The system yielded 94 percent diagnostic accuracy in determining relevant genetic mutations patients with either low- or high-grade gliomas, or brain tumors.