Blepharospasm, a condition that causes uncontrollable muscle contractions around the eye, receives different conclusions on the severity for each patient because the rating scales for the condition are very subjective and unreliable. Two clinicians could come away with two different ideas on how bad the condition is in a single patient.

A more objective scale may be coming to light. Scientists from the Salk Institute for Biological Studies in La Jolla, California, have created a computer program that analyzes video of patients' eyes. This program could also be used for analyzing facial tics and twitches in general.

"The field of neurology has a long tradition of making clinical decisions based on careful observations. We hope to supplement that expertise by leveraging advances in computer vision and machine learning," said Terrence Sejnowski, PhD, head of Salk's Computational Neurobiology Laboratory.

The original rating scales were developed for research into the underlying cause of blepharospasm—which is often unknown—but many studies have shown those ratings have a high degree of variability based on the clinician using them.

"[The ratings are] inherently subjective because they're based on human judgment," said David Peterson, PhD, a project scientist at Salk and the University of California, San Diego and first author of the paper. "And when these measures are used either to optimize treatment in clinical care or during studies of the condition, that variability introduces error."

This new program had a 100 percent accuracy rate in 46 of the 49 patients used for testing. In the other 3 cases, it had a 93 percent accuracy rate.