Kaiser Permanente researchers push the envelope with AI and NLP

"In minutes, the software identified nearly 54,000 patients with the condition, a process that would likely have taken years for physicians to perform manually," a physician researcher tells Healthcare IT News.

Although healthcare is squarely in the era of big data and data analytics, it remains difficult in clinical research to accurately identify patients with complex conditions like valvular heart disease through medical records.

THE PROBLEM

And if researchers cannot identify these patients, they cannot study them, track practice patterns or conduct population management.

Part of the problem is that the current methods used to identify highly specific conditions like valvular heart disease use diagnosis or procedure codes. These were created primarily for billing purposes and often are not very useful for clinical care because they can be quite nonspecific and not include detailed data about the condition.