AI Entering the Clinical Workflow: Watson Health Aims to Streamline Diagnosis with New Imaging Clinical Review

At the annual Healthcare Information and Management Systems Society (HIMSS) conference, Watson Health introduced IBM Watson Imaging Clinical Review, a cognitive “peer-review” resource that eliminates discrepancies between a patient’s clinical diagnosis and administrative records. The new system streamlines reports and ultimately improves the accuracy in a patient’s record. The software company also announced the expansion of their medical imaging collaborative to 24 international organizations. Their services detect, identify, and predict the risk of diseases such as cancer, diabetes, and eye, brain, and heart conditions.

Watson Imaging Clinical Review’s initial application is for aortic stenosis (AS), a condition that occurs when the heart’s aortic valve is tightened, limited blood flow to the rest of the body and resulting in shortness of breath, fatigue, and chest pain. AS affects 1.5 Americans. In a pilot study, Watson Imaging Clinical Review enabled physicians to identify possible AS in patients who were not previously designated for cardiovascular care. Watson Imaging Clinical Review utilizes cognitive text analytics to interpret “structured and unstructured information” in cardiology reports while integrating data from different sources.

“Watson Imaging Clinical Review is the type of targeted AI-driven tool that providers could put to use to help them standardize care delivered across their organization, and gradually build a critical mass of reproducible results from their patient population,” said Frost & Sullivan’s Principal Medical Imaging Analyst Nadim Michael Daher. “In doing so, it can support a population health-driven approach to personalized care.”