Can data mining help us make better medical decisions?


How can data to make hospitals more accountable? As health infrastructures on both sides of the Atlantic undergo extensive modernization, technology companies are exploring ways to make it easier for hospitals to mine information about their operations. The idea is not only that improved clinical data can lead to better decisions at the sharp end of healthcare, but also that it can be used to craft better policy decisions.

The problem is that historically, much clinical information has been recorded on paper, and in different formats, making it very difficult to use it for analysis. With the uptake of electronic health records, however, and with the possibility of integrating different healthcare providers’ systems more closely, that is changing.

George MacGinnis, healthcare expert at PA Consulting, says that some health regions are at the cutting edge of innovation, to the point where they can link information about an ambulance pickup to the record of that individual’s stay at the hospital.

“Someone asked in a meeting ‘should we give aspirin for chest pain when we arrive on a scene?’,” he says. It becomes possible to compare the average length of hospital stay from those who administered the drug, compared to those who were not, in order to make an informed decision.
Clinical data can therefore be used to come up with answers. But perhaps even more interesting is the ability to use business intelligence techniques to mine information for patterns, highlighting trends that administrators were not aware of.

“One thing we’re doing with kids in Toronto is that we’re taking massive amounts of data and analyzing that to predict and do pattern recognition to find whether a kid is likely to spike a fever,” says Paul Grundy, director of healthcare transformation at IBM.

As more data becomes available, and tools to investigate it become more powerful, what might we discover next about the nuances of our complex healthcare systems?

As an example, check out this paper that used data mining to extract information from medical records that could be used to improve care and reduce costs. It looked at how best practices in care could be developed by looking at the differences in decisions made by doctors to the same condition. 

Anthony Plewes

After a Masters in Computer Science, I decided that I preferred writing about IT rather than programming. My 20-year writing career has taken me to Hong Kong and London where I've edited and written for IT, business and electronics publications. In 2002 I co-founded Futurity Media with Stewart Baines where I continue to write about a range of topics such as unified communications, cloud computing and enterprise applications.