Even though healthcare has entered the era of big data and data analytics, clinical Research still finds it challenging to reliably identify patients with complex illnesses such as valvular heart disease using medical records. And if Research can’t find these patients, they won’t be able to study them, follow practice patterns, or manage populations. One of the issues is that current approaches for identifying particular illnesses such as valvular heart disease rely on diagnosis or procedure codes.
These were designed solely for billing purposes and are frequently ineffective for clinical therapy since they are generic and lack precise information about the disease. Dr. Matthew Solomon, a cardiologist at the Permanente Medical Group and a physician-Research at the Kaiser Permanente Division of Research in Oakland, California, said, “For example, a patient with moderate or severe aortic stenosis, which is a narrowing of one of the primary heart valves, is entirely different than a patient with mild valve disease.”
NLP is a branch of artificial intelligence. First, a complicated set of rules is created to interpret unstructured, free-text reports and convert them into a structured, systematic, and ordered database. Once this is completed, it will be feasible to analyze this population and undertake high-quality population management. The Kaiser Permanente Northern California Division of Research is at the forefront of developing and validating such methods.