IBM today said it was rolling out software that will help doctors and insurance companies reduce costs by better analyzing and managing huge amount of patient data.
IBM said its Content and Predictive Analytics for Healthcare package will let healthcare professionals go beyond traditional search and analysis of unstructured data by applying predictive root cause analysis, natural language and built-in medical terminology support to identify trends and patterns to achieve clinical and operational insights. IBM added that the processing was similar to the core technology found in its celebrated Watson supercomputer.
MORE ON HEALTHCARE: High-tech healthcare technology gone wild
"Doctors and other healthcare professionals can advance diagnosis and treatment by accurately extracting medical facts and understanding relationships buried in large volumes of clinical and operational data. The software transforms raw information into healthcare insight quickly by predicting the probability of outcomes, letting organizations derive insight in minutes versus weeks or months, or not at all. As a result, healthcare professionals can find more effective ways to care for high-risk patients, provide safer patient care, and develop new models for reimbursement for quality care," IBM said.
One of the issues the system could help address is the cost of patients being repeatedly admitted and readmitted to a hospital for similar or multiple chronic diseases. IBM said that according to the New England Journal of Medicine, 1 in 5 patients suffer from preventable readmissions, which represents $17.4 billion of the current $102.6 billion Medicare budget. Beginning in 2012, hospitals will be penalized for high readmission rates with reductions in Medicare discharge payments.
According to IBM, most healthcare organizations are drowning in data but are challenged to gain reliable, actionable insights from this information. In fact, more than 80% of an institution's data today is unstructured. In healthcare, this is in the form of physician notes, registration forms, discharge summaries, documents and more -- and this data is doubling every five years. Different from machine-ready data, this content lacks structure and is arduous for healthcare enterprises to include in business analysis and therefore is routinely left out. As a result, millions of patient notes and records often sit unavailable in separate clinical data silos. This content contains valuable information, but there's historically been no easy way to analyze it.