Evaluating human gait and posture is a clinically effective method for the early diagnosis of diseases involving gait afflictions, such as adult spinal deformity (ASD).

Researchers at University of Tsukuba, Japan developed a method for classifying ASD based on the characteristics of the associated gait disorders using deep learning of gait videos and images, focusing on the cyclic motion during walking and the symmetry of movements.

The findings are published in the journal IEEE access,

Patients with ASD have altered gait patterns because of the spinal deformity; hence, gait analysis may be effective for diagnosis. However, the conventional methods of gait analysis may be inadequate for studying the characteristics of posture and movement during walking, which are essential for diagnosis. Recently, deep learning technology using video images has been used.

Using this technique, researchers have developed a new method to accurately capture the rhythm and symmetry of body movements during walking, which may be used to classify the periodicity and postures adopted by the lower limbs and the body during gait.

They tested this method using walking videos of 81 patients and achieved a correct response rate of 71.43%, which was more accurate than the conventional method (66.30%), and confirmed its effectiveness for diagnosing ASD.

In the future, this technique may allow real-time analysis of moving images in clinical settings to enable instantaneous confirmation and rapid diagnosis of ASD.