IBM Watson Health, Broad Institute to use AI, genomics for predicting risk of cardiovascular disease

IBM Watson Health is partnering with the Broad Institute of MIT and Harvard to use AI and genomics to help clinicians better predict the onset of serious cardiovascular diseases, the company announced Feb. 13.  

The new partnership is an expansion of a 2016 agreement aimed at leveraging machine learning to better understand why and how cancers become resistant to therapies.

Separately, IBM Watson Health also recently announced a $50 million investment in a joint research collaboration with the Vanderbilt University Medical Center and Brigham and Women’s Hospital to utilize AI in solving major public health issues.

"We've built a deep expertise in applying AI to understand the complexities and meaning of immense amounts of data, such as genomics and health records,” John Kelly, senior vice president at IBM Watson Health, said in a statement. “Our latest collaboration will combine these capabilities with clinical insights, and refine how technology can provide explainable and valuable insights to clinicians as they study and treat serious conditions such as cardiovascular disease."

The initiative will utilize population-based and hospital-based biobank data, genomic information and electronic health records (EHRs) to build and expand the predictive power of genetic risk scoring. The entities also plan to build algorithms that can pinpoint and learn from trends in the data points and indicate a potential predisposition to certain health conditions.

The goal for the technology is to produce models that collect and analyze genetic risk factors with a person’s genome, health records and biomarkers to help clinicians more accurately predict the onset of complex and possibly fatal conditions, such as heart attacks, sudden cardiac death and atrial fibrillation.

"We're excited to build upon the advances we've made in polygenic risk scoring utilizing vast amount of genomic data," Sekar Kathiresan, director of the Center for Genomic Medicine at Massachusetts General Hospital (MGH) and institute member and director of the Cardiovascular Disease Initiative at the Broad Institute, said in a statement. "By coupling clinical data with genomic data, there is an exceptional opportunity to make polygenic risk scoring more robust and powerful, and ultimately transformative for patient care. Such transformation could never happen without these kinds of partnerships."

The initiative is expected to be a three-year process. Insights and tools from the initiative are expected to be available for researchers.