New computer models aim to classify, help reduce injury accidents

September 2, 2009 by Emil Venere

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 in society," said Mark Lehto, an associate professor in Purdue University's School of Industrial Engineering.

The reports, usually filled out by employers, health-care professionals or claimants themselves, are currently classified by manual coders hired by users such as the National Center for Health Statistics, staff or insurance industry handlers who review thousands of "injury narratives" included in reports.

"This is obviously very labor-intensive," Lehto said.

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

"The predictions were quite good," Lehto said. "The results were comparable to the human coders. 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."

An example of an injury-claim narrative included in the paper is: "HUSB. & SON WERE REARENDED AT RED TRAFFIC LIGHT BY DRUNKEN DRIVER DRIV-ING AT LEAST 45 MPH INFULL SIZE PICK-UP TRUCK//N."

"Can you imagine reading through 10,000 of these narratives and trying to interpret what the cause of injury is and assign different codes?" said Lehto, the 2008 Liberty Mutual Research Institute for Safety visiting scholar.

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 developed by the U.S. Bureau of Labor Statistics.

"So now we are trying to take these vast sets of data, which have been limited in their utility due to the large expense in hiring manual coders, and we are able to glean important information from the injury narratives and come up with new knowledge on the potential causes and prevention of injuries," Lehto said.

The new models might lead to programs that automatically code reports as they are being filed.

"These models can be easily updated to deal with new types of accidents they haven't encountered before," Lehto said.

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.

"It's important to distinguish that we predicted 3,000 cases that were different than the ones used to develop the models," Lehto said. "These were cases the models hadn't seen before, and the models accurately predicted how these cases would be classified by human coders."

Source: Purdue University (news : web)


Rank 1 /5 (1 vote)
Relevant PhysicsForums posts
  • Is Everyday Technology Killing Us?
    createdFeb 08, 2012
  • Exercise and weight loss
    createdFeb 08, 2012
  • Why do we have head aches? Our brains can't feel anything.
    createdFeb 07, 2012
  • "The end of diseases" by David Agus, interview from Daily Show with Jon Stewart
    createdFeb 04, 2012
  • Oncolytic adenovirus
    createdFeb 04, 2012
  • Nutrition label stuffs and diets
    createdFeb 02, 2012
  • More from Physics Forums - Medical Sciences

More news stories

Overeating may double risk of memory loss

New research suggests that consuming between 2,100 and 6,000 calories per day may double the risk of memory loss, or mild cognitive impairment (MCI), among people age 70 and older. The study was released today and will be ...

Medicine & Health / Neuroscience

created 35 minutes ago | popularity not rated yet | comments 0 | with audio podcast

Injured boomers beware: Know when to see doctor

(AP) -- It happened to nurse Jane Byron years after an in-line skating fall, business owner Haralee Weintraub while doing "men's" push-ups, and avid cyclist Gene Wilberg while lifting a heavy box.

Medicine & Health / Health

created 5 hours ago | popularity 5 / 5 (1) | comments 0

Starve a virus, feed a cure? Findings show how some cells protect themselves against HIV

A protein that protects some of our immune cells from the most common and virulent form of HIV works by starving the virus of the molecular building blocks that it needs to replicate, according to research published online ...

Medicine & Health / Research

created 4 hours ago | popularity 5 / 5 (1) | comments 0 | with audio podcast

FDA-approved drug rapidly clears amyloid from the brain, reverses Alzheimer's symptoms in mice

Neuroscientists at Case Western Reserve University School of Medicine have made a dramatic breakthrough in their efforts to find a cure for Alzheimer's disease. The researchers' findings, published in the journal Science, show t ...

Medicine & Health / Neuroscience

created Feb 09, 2012 | popularity 4.9 / 5 (57) | comments 15 | with audio podcast

Green tea found to reduce disability in the elderly

(Medical Xpress) -- A lot of research has been done over the past several years looking into the health benefits of green tea. As a result, scientists have found that regular consumption of the beverage leads ...

Medicine & Health / Health

created Feb 07, 2012 | popularity 4.4 / 5 (15) | comments 10 | with audio podcast report


Google might launch Drive for cloud storage soon

(PhysOrg.com) -- Google's next big move, according to the Wall Street Journal, is a cloud storage service called Drive. Hardly first to the plate, Google is simply catching up to introducing its cloud reposi ...

Scientists discover molecular secrets of 2,000-year-old Chinese herbal remedy

For roughly two thousand years, Chinese herbalists have treated Malaria using a root extract, commonly known as Chang Shan, from a type of hydrangea that grows in Tibet and Nepal. More recent studies suggest that halofuginone, ...

New method to examine batteries -- MRI from the inside

There is an ever-increasing need for advanced batteries for portable electronics, such as phones, cameras, and music players, but also to power electric vehicles and to facilitate the distribution and storage of energy derived ...

Lab study raises questions over nano-particle impact

Tests involving chickens have raised questions about the impact on health from engineered nano-particles, the ultra-fine grains commonly used in drugs and processed foods, scientists said on Sunday.

A mitosis mystery solved: How chromosomes align perfectly in a dividing cell

Although the process of mitotic cell division has been studied intensely for more than 50 years, Whitehead Institute researchers have only now solved the mystery of how cells correctly align their chromosomes during symmetric ...

Researchers find extensive RNA editing in human transcriptome

In a new study published online in Nature Biotechnology, researchers from BGI, the world's largest genomics organization, reported the evidence of extensive RNA editing in a human cell line by analysis of RNA-seq data, demons ...