IBM, Broad Institute Launch Initiative Using Genomics & AI To Predict Risk Of Cardiovascular Disease
By Bio-IT World Staff
February 14, 2019 | IBM Watson Health and the Broad Institute are expanding their partnership to help clinicians better predict the possibility of serious cardiovascular diseases. By working with genomics, clinical data, and AI, IBM and the Broad Institute hope this three-year project will help provide doctors with tools to tap into the potential of genomics data, and better understand the intrinsic possibility an individual has for a certain disease. Equipped with this knowledge, health professionals can potentially intervene and help to reduce this risk.
The initiative incorporates population-based and hospital-based biobank data, genomic information, and electronic health records to build upon and expand the predictive power of genetic risk scoring. IBM and the Broad Institute are aiming to build algorithms that can pinpoint and learn from trends in these data points, and then indicate a potential predisposition to certain health conditions. The project will also plan to make insights and tools widely available to the research community, including methods to calculate an individual's risk of developing common diseases based on millions of variants in the genome.
Ultimately, this AI technology will aim to produce models which bring together and analyze a multitude of genetic risk factors within an individual's genome, along with existing health records and biomarkers, to help clinicians more accurately predict the onset of complex and often fatal conditions in patients, such as heart attacks, sudden cardiac death, and atrial fibrillation.
This is the next evolution of genomic research between IBM Watson Health and the Broad Institute. In 2016, the two organizations announced a five year initiative to help researchers use machine learning and genomics to better understand why and how cancers become resistant to therapies.
"We're working directly with the physician-scientists at the Broad Institute to evolve how AI can help unlock undiscovered clues about human health," John Kelly, senior vice president of IBM Watson Health, said in a press release. "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. 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 developed AI technologies will require innovation on three fronts: the ability to integrate several disparate types of health data for modeling; the potential to transfer and apply models on patients from different health systems; and the power to communicate insights and explain generated insights and analysis results to patients and doctors in a way that is meaningful and actionable.
Built for specific health conditions, such as cardiac arrest, these algorithms are designed to identify when a confluence of low incidence and rare genetic events come together and combine with clinical, physiological, and environmental factors to form a significant risk factor for a disease. Additionally, these models will learn from various multitudes of disparate data, including the longitudinal and clinical records of individuals, electronic medical records, DNA sequencing, and genetic factors. The risk analysis will aim to help health professionals identify and quantify patients' risk for cardiovascular conditions, as well as the genetic factors contributing to that risk. To better improve how this intelligence can be communicated and used in clinical settings, IBM and the Broad Institute will work closely together to incorporate direct feedback from doctors and caregivers.