Development of an Automated System for Assessing Risk of Low Back Pain Onset Based on Muscle Brightness in Ultrasound Images Using Deep Learning

Development of an Automated System for Assessing Risk of Low Back Pain Onset Based on Muscle Brightness in Ultrasound Images Using Deep Learning - Development of an Automated System for Assessing Risk of Low Back Pain Onset Based on Muscle Brightness in Ultrasound Images Using Deep Learning

Status

Recruiting

Phases

Unknown

Study type

Observational

Source

JPRN

Registry ID

JPRN-UMIN000059011

Enrollment

100

Registered

2025-09-05

Start date

2025-10-01

Completion date

Unknown

Last updated

2026-06-29

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

People with back pain, people without back pain

Interventions

None listed

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Individuals aged 18 and older with low back pain, individuals without low back pain

Exclusion criteria

Exclusion criteria: Individuals experiencing pain that interferes with daily life, individuals with typical physical disabilities such as cerebrovascular disorders or rheumatoid arthritis, individuals with a history of fractures in the lumbar region, pregnant individuals, and individuals with pacemakers

Design outcomes

Primary

Measure	Time frame
Muscle intensity assessment of the lumbar multifidus muscles, information regarding low back pain (name, age, height, weight, gender, severity of low back pain (NRS), kinesiophobia (Tampa Scale for Kinesiophobia, TSK), impact of low back pain on daily activities (Oswestry Disability Index, ODI)	—

Countries

Japan

Contacts

Public ContactTakaaki Nishimura

Nanto Municipal Hospital Department of Community Rehabilitation

t-nishimura@hokuriku-u.ac.jp0763-82-1475

Outcome results