Big Data is headed for the patient bed-side, but there’s still work to be done
The discussion around Big Data in healthcare can frequently feel very removed from the patient experience.
According to Clinical Endocrinology News, Dr. Harlan Krumholz, a professor at Yale, and member of the Patient-Centered Outcomes Research Institute board of governors, has issued the prediction that within five years, Big Data will be transforming the way healthcare is delivered at the patient bedside.
The Prediction And The Problem
Dr. Krumholz believes that dramatic change is coming in the way we think about leveraging everyday clinical data. Part of that belief is based on the opinion that the current scientific enterprise is not capable of keeping up with information needs. To make that shift, a change in the research culture and how information is moved to doctors as they treat patients will have to come.
Dr. Krumholz critiques current research approaches as very reductionist— that in traditional research’s application of the scientific method to test hypotheses, the questions being answered become far-removed from the complexity of the patients being studied, leaving results “anachronistic,” and robbing studies of their potential effects.
The doctor also advocates for the incorporation of non-health related data: “It’s not just the pill, but it’s the pill for a specific patient who’s got a specific profile, who is in a certain social situation, who is taking other medication, maybe has certain access to physicians, and a lot of complicated issues coming together. We need to be able to learn from everyday experience and we need to embrace the complexity, not reject it, so that our studies are taking into account the complex aspects of medicine, not trying to get rid of them so we have clean studies that may not well-relate back to the real-world situations doctors and patients face every day.”
The Potential Impact
A collaborative program between Kaiser Permanente Northern California, Harvard University, and the University of California was featured in the July Issue of Health Affairs. The pilot program is a two-step protocol aimed at reducing antibiotic prescriptions for newborns.
It does so by using objective maternal data to determine preliminary probability of early-onset sepsis. After that, a set of clinical findings is combined with the estimate (again, based on maternal data), yielding a new posterior probability for sepsis risk following birth. Kaiser has estimated that the combination of these two steps could lead to a drop in newborn systemic antibiotic treatment as large as 240,000 diagnoses per year.
Another application is addressed by Dr. David Bates, who serves as chief of the division of general medicine at Brigham and Women’s hospital in Boston. They intend to use Big Data to identify key areas where improvements can be made including identifying high-cost patients, more efficiently caring for them, reducing readmissions, lowering the risk of complications, and more.