Researchers are developing computer models to comb through thousands of injury reports in large administrative medical datasets or insurance claims data to automatically classify them based on specific words or phrases.

"One goal is to identify the most important causes of injuries so that efforts could be directed toward reducing the burden of injuries on society," says Mark Lehto, an associate professor in Purdue University's School of Industrial Engineering.

The reports, filled out by employers, health-care professionals or claimants, are currently classified by manual coders hired by users such as the National Center for Health Statistics, hospital staff, or insurance industry handlers who review thousands of "injury narratives" included in reports. "This is obviously very labor-intensive," says Lehto.

The Purdue engineer and researchers at the Liberty Mutual Research Institute for Safety in Hopkinton, MA, assigned codes to injury reports from workers' compensation claims using two different models developed with a technique called "Bayesian methods."

"The results were comparable to the human coders,” says Lehto. “The accuracy is surprising considering all of the misspellings, run-on words, abbreviations and inconsistent or missing punctuations seen in these workers' compensation claim narratives."

Research findings were detailed in a paper published in August in the journal Injury Prevention. The paper was written by Lehto and Liberty Mutual research scientists Helen Marucci-Wellman and Helen Corns.

Insurance companies enter, maintain, and manage tens of thousands of claims annually. The study examined approaches for efficient assignment of each claim using a computer approach with one- and two-digit "event code" categories.  The new models might lead to programs that automatically code reports as they are being filed. The models calculated the probability that reports would be classified by human coders in specific categories. One model, called "naive," reviewed individual words, and the other, called "fuzzy," looked at sequences of words and phrases in the narratives, such as "fell off a ladder." The researchers used a database of 14,000 claim cases, with 11,000 used to develop the models and 3,000 used to test the models.

“The approach could lead to new methods of data entry and interfaces for medical devices among other applications,” says Lehto. “In the current study we are using the method to identify particular types of injury causes. This easily could easily be extended to preventative measures.”