Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/122999
Título: Automatic diagnosis of lower back pain using gait patterns
Autores/as: Pandey, Chandrasen
Baghel, Neeraj
Dutta, Malay Kishore
Travieso González, Carlos Manuel 
Clasificación UNESCO: 220990 Tratamiento digital. Imágenes
3314 Tecnología médica
Palabras clave: Gait Analysis
Back Pain
Support vector machine
Fecha de publicación: 2022
Editor/a: Editorial Tecnológica de Costa Rica
Publicación seriada: Tecnología en Marcha 
Resumen: Back pain is a common pain that mostly affects people of all ages and results in different types of disorders such as Obesity, Slipped disc, Scoliosis, and Osteoporosis, etc. The diagnosis of back pain disorder is difficult due to the extent affected by the disorder and exact biomechanical factors. This work presents a machine learning method to diagnose these disorders using the Gait monitoring system. It involves support vector machines that classify between lower back pain and normal, on the bases of 3 Gait patterns that are integrated pressure, the direction of progression, and CISP-ML. The proposed method uses 13 different features such as mean and standard deviation, etc. recorded from 62 subjects (30 normal and 32 with lower back pain). The features alone resulted in higher leave-one-out classification accuracy (LOOCV) 92%. The proposed method can be used for automatically diagnosing the lower back pain and its gait effects on the person. This model can be ported to small computing devices for self-diagnosis of lower back pain in a remote area.
URI: http://hdl.handle.net/10553/122999
ISSN: 0379-3962
Fuente: Tecnología en Marcha[ISSN 0379-3962],v. 35 (4), p. 93-100
URL: http://dialnet.unirioja.es/servlet/articulo?codigo=8828178
Colección:Artículos
Adobe PDF (758,55 kB)
Vista completa

Visitas

65
actualizado el 21-sep-2024

Descargas

17
actualizado el 21-sep-2024

Google ScholarTM

Verifica


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.