Artificial Intelligence may Help Predict Movement Disorders

Features of movement disorders across varied species can be traced using deep learning algorithms designed by the scientists at Osaka University, that further help in the understanding of Parkinson’s disease. The study “Cross-species behavior analysis with attention-based domain-adversarial deep neural networks” is published in the journal Nature Communications. The study found that the walking patterns of movement disorders are shared among distant evolutionary lineages – worms, mice, and humans.

The study team used animal location tracking along with artificial intelligence to automatically detect species-specific walking behaviors of movement disorders. With this, the team designed machine learning algorithms to aggregate readings from different dopamine-deficient animals and obtain locomotion patterns.

Artificial Intelligence in Movement Disorder

It was found that despite their evolutionary differences, all the organisms were unable to move while maintaining high speeds. Moreover, they exhibited similar movement disorders in the case of dopamine deficiency despite different body scales and locomotion methods.

Although it is established that dopamine deficiency was associated with movement disorders in all of these species, the study team was first to identify the shared locomotion features caused by this deficiency.

“Our project shows that deep learning can be a powerful tool for extracting knowledge from datasets that appear too different to be compared by human researchers,” says study author Takahiro Hara.

The study thereby anticipates that this work will be used to find other common features for disorders that impact evolutionarily distant species.

Source-Medindia