Text Mining of Medical Records for Radiodiagnostic Decision-Making

The rapid growth of digitalized medical records presents new opportunities for mining terra bytes of data that may provide new information & knowledge. The knowledge discovered as such could assist medical practitioners in a myriad of ways, for example in selecting the optimal diagnostic tool from among numerous possible choices. We analyzed the radiology department records of children who had undergone a CT scan procedure at Nagasaki University Hospital in the year 2004. We employed Self Organizing Maps (SOM), an unsupervised neural network based text-mining technique for the analysis. This approach led to the identification of keywords with a significance value within the narratives of the medical records that could predict & thereby lower the number of unnecessary CT requests by clinicians. This is important because, in spite of the valuable diagnostic capacity of such procedures, the overuse of medical radiation does pose significant health risks and staggering cost especially with regard to children.