Health IT and Electronic Health Activate your FREE membership today |  Log-in

Community Blog

Feb 4 2013   11:47AM GMT

Evidence-based decision making in the operating room: The rise of case-based reasoning

Posted by: Jenny Laurello
case-based reasoning, Data analytics, Decision support, medical errors, Patient safety

Guest post by Frode Sørmo, CTO, Verdande Technology

We all know that the nature of health care is not black and white. A situation can change dramatically on the operating table, regardless of a physician’s preparation. Health care is being redefined to focus on quality outcomes, and physicians need evidence-based support to make the smartest real-time decisions.

Traditionally, physicians have made decisions based on experience and intuition during unexpected and potentially life-threatening situations. While there is something to be said for instinct, there is no substitute for data-backed, evidence-based information when making these calls. The health care industry produces an inordinate amount of data, and many hospitals and physicians do not have the tools or technology to leverage data to assist in making decisions in real time. With the hospital information system industry expected to spend $35 billion on IT by 2015, it’s time to turn some of this attention to cost-efficient analysis of data to improve patient outcomes.

Health care is a business, like any other industry. Hospitals focus on the business of providing the best care at the best price for organizations and patients. However, preventable adverse events cost between $17 billion and $29 billion each year and medical errors cause between 50,000 to 100,000 deaths in the U.S. every year. Looking to the past for guidance is the key to preventing these adverse effects, saving money, and improving patient health.

Best practices and tactics from surgical procedures and techniques that resulted in positive outcomes in the past can be used today because history often repeats itself. The medical profession has a tradition of publishing interesting studies which have provided valuable lessons for future treatment. However, no single person can keep every relevant experience and case in their head, and it can be difficult to recall a case read years earlier while in the middle of a procedure. This is where case-based reasoning (CBR) comes into play. A CBR platform can contain large case databases, and unlike traditional knowledge management techniques, it does not need the physician to actively search for those cases. Rather, the CBR system uses multiple, heterogeneous data types about the patient to index the past experiences. This allows the system to use real-time data from the patient to continuously search the case database for past cases, providing physicians with the information they need in real time to improve patient outcomes. CBR empowers physicians with the evidence-based insight and foresight to make better, smarter, faster real-time surgical decisions to ensure positive patient outcomes by providing a realistic assessment as to whether a similar scenario is likely to occur in the future on the operating table.

Some physicians may question how this data is available where and when they need it. A clinician can retrieve patient data and be alerted to a changing scenario via the device of their choice using a flexible CBR application. An anesthesiologist in the operating room on a traditional PC, a nurse in the intensive care unit on a smart phone and a surgeon on their pager are all supported. With CBR, real-time data from an ongoing operation is constantly interpreted and important events are recognized. Using this data, past cases with similar data patterns are retrieved, and the most relevant are presented to the physician to help them deal with the current case. Once each case is resolved, the physician can then choose to record this as a new case for the system’s files for future retrieval.


How does CBR differ from the traditional predictive analytics technologies used by health care providers today? These predictive analytics solutions are valuable for analyzing historical data for patterns that can inform future medical decisions, but they do not analyze data in real time or serve as decision support tools during a procedure.

During surgery, seemingly minor trends and symptoms can turn into major complications, if not identified and treated in time. CBR helps physicians identify these trends and symptoms early and determine the best course of action for treating the patient. By having accurate, evidence-based information at their fingertips, physicians are assured that if the patient shows similar trends and symptoms as a past case where complications occurred, they have the necessary information and best recommendations available immediately. Better patient outcomes result in shorter stays in the hospital, reduced costs, and fewer lawsuits.

As many health care providers struggle to survive as businesses while providing exemplary quality of care, physicians must look to their past successes and adverse events to perform efficiently in the future. There’s no substitute for individual skill and instinct, but a decision support solution like CBR can only improve patient outcomes while reducing costs and enhancing the quality of care.

Comment on this Post

Leave a comment:

Forgot Password

No problem! Submit your e-mail address below. We'll send you an e-mail containing your password.

Your password has been sent to: