Development of diagnostic and therapeutic support tools for scoliosis using deep learning

Development of diagnostic and therapeutic support tools for scoliosis using deep learning - Development of diagnostic and therapeutic support tools for scoliosis using deep learning

Status

Recruiting

Phases

Unknown

Study type

Interventional

Source

JPRN

Registry ID

JPRN-UMIN000048005

Enrollment

200

Registered

2022-06-10

Start date

2019-09-25

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

Scoliosis

Interventions

X-ray of 6, 12, and 24 months in patients with scoliosis was evaluated.

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: idiopathic scoliosis

Exclusion criteria

Exclusion criteria: Exclude scoliosis from other disorders such as non-idiopathic, neurological, symptomatic, and congenital.

Design outcomes

Primary

Measure	Time frame
For X-ray images of patients with scoliosis, we will compare and examine which is more accurate, the progress prediction by AI or the progress prediction by a spine surgeon. We plan to use images from six months, one year, and two years to study the progress.	—

Secondary

Measure	Time frame
Images other than X-rays are also used as secondary outcomes. Patient groups are stratified and evaluated by degree of bone maturity.	—

Countries

Japan,Asia(except Japan),North America,Australia,Europe

Contacts

Public ContactShoji Seki

University of Toyama Orthopaedic surgery

seki@med.u-toyama.ac.jp0764347353

Outcome results

None listed

Source: JPRN (via WHO ICTRP) · Data processed: Jul 3, 2026