Lou Gehrig's Disease may Be Identified Sooner Using Data Mining

by Rajashri on Aug 6 2008 2:45 PM

A "pattern array" software to see movements in rats is being used by a research team led by psychologists at the University of Maryland's School of Medicine. They believe this may be helpful in predicting diseases like Lou Gehrig's syndrome.

In a study report published in the journal Behavioral Neuroscience, the researchers have expressed hope that the use of data mining may enable scientists to test therapies to delay or even prevent disease, starting with hereditary forms.

So far, they have used their software on mutant rats used as an animal model of amyotrophic lateral sclerosis (ALS), a progressive and fatal neurodegenerative disease that's inherited about one in 10 times.

The disease, which attacks the nerve cells that control movement, is identified with Yankee slugger Lou Gehrig, who died of ALS in 1941, two years after diagnosis.

Lead researcher Dr. Neri Kafkafi has revealed that his team mathematically analysed analyzed about 50,000 predetermined movement patterns that resulted when rats roamed freely, one by one, in a small arena.

He says that the software created an abstract space defined by combinations of behaviour such as speed, acceleration and direction of movement.

According to him, mining the resulting behavioural data allowed the research group to test many more facets of behaviour than they could analyse manually.

Dr. Kafkafi says that the movement of two groups of rats - one type with the mutation that results in an ALS-type syndrome, the other type normal controls - were recorded on a videotape, and thereafter the computer was used to "pan" for differences between groups.

He says that the team's efforts led to the identification of a unique motor pattern in mutant rats two months before disease onset, which would equate to roughly five to 10 years in humans.

The researcher is of the opinion that data mining to detect the subtle behavioural expression of mutations may allow investigators to test therapies aimed at preventing, slowing or stopping disease.

He says that the ability to predict more accurately which carriers may express the disease before the symptoms appear may enable researchers to test medicines that may prevent symptoms from emerging.

"Such therapies could very well be effective against the non-genetic version of the disease as well," Dr. Kafkafi says.

The authors note that methods like data mining can be therapeutically useful even before science understands how disease begins.

"The discovery of reliable behavioural endpoints with predictive validity, even before a good understanding of their etiology is achieved, can significantly improve intervention research," they write.