Building a Smarter Planet. A Smarter Planet Blog.

by Dr. David Ramirez, Medical Director at Seton Health Family

Readmission rates are plaguing many hospitals across the United States and will continue to increase.  According to the New England Journal of Medicine, one in five patients suffers from preventable readmissions, representing $17.4 billion of the current $102.6 billion Medicare budget.  Additionally, hospitals will begin to face penalties for high readmission rates from Medicare beginning in 2013. Initially this will be in key areas such as pneumonia, congestive heart failure (CHF) and acute myocardial infarction.

One area in which Seton Healthcare Family is striving to reduce the occurrence of preventable high cost readmissions is with CHF patients. Costly hospitalizations are big health expenditures for those suffering with CHF and these costs have been estimated to amount to more than $35 billion in the United States alone. Heart failure affects an estimated 5 million people in the United States, with 500,000 new cases diagnosed each year. It is a growing concern for hospitals as more than 50% of patients seek re-admission within 6 months after treatment.

While there’s no silver bullet for preventing all readmissions, hospitals and health providers can take action to significantly decrease the occurrence. At Seton Health Family, we’re utilizing technology, like that in IBM Watson, to meet the rigorous standards and requirements imposed by and for the healthcare community.  We’re one of the first hospitals using IBM’s Content and Predictive Analytics for Healthcare technology, which allows us to mine unstructured healthcare data by using natural language processing and search technologies to produce meaningful knowledge. This is very important as more than 80% of our data is unstructured. It is in the form of physician notes, registration forms, discharge summaries, echocardiograms, and other medical documents. We knew we had to leverage our wealth of unstructured information to discover new, population specific clinical and operational insights.

The solution from IBM provides deep content analysis and evidence-based reasoning for better decision making, giving us the ability to identify patients likely for readmission and introduce early interventions to reduce cost, mortality rates, and improved patient quality of life. By leveraging predictive models that have demonstrated high positive predictive value against extracted elements, we can now understand known risk factors like smoking, and likely discover new risk factors specific to our patient population. Predictive models allow us to eliminate the need for traditional analysis – an arduous and resource intensive task – and transform raw information into healthcare insight quickly. It can reveal trends, patterns and deviations while predicting the probability of outcomes so we can make decisions in minutes versus weeks or months. This is a game changer.

Our goal is to advance diagnosis and treatment by extracting medical facts and understanding relationships that are often buried in large volumes of clinical and operational data. Seton Healthcare Family staff can now intuitively navigate, interpret and take action on our connected, actionable patient data that previously spanned disparate systems. This new generation of analytics that moves beyond traditional data analysis approaches will help us focus on patient care and drive healthcare transformation. Thanks to IBM, we can reach the goal of dramatically reducing unnecessary CHF readmissions.

To learn more about the Seton Health story and how they are harnessing IBM Content and Predictive Analytics for Healthcare, check out this link:  www.ibm.com/press/us/en/pressrelease/35738.wss

This week IBM is hosting its annual Information on Demand Conference and Business Analytics Forum in Las Vegas.  David Ramirez from Seton Health is among several thousand attendees who are learning how to unlock the potential of big data and analytics.  Check out more about the conference here: www.ibm.com/press/IOD2011