Automated Detection of spine fractures by a deep learning algorithm

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

DRKS

Registry ID

DRKS00029356

Enrollment

1071

Registered

2022-06-29

Start date

2023-03-01

Completion date

Unknown

Last updated

2026-06-01

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

Conditions

spine fracture

Interventions

Group 1: At first 100 CT scans will be included to evaluate the reliability and generability (prevalence 100%) of the algorithm. Diagnostic accuracy for cervical, thoracic, and lumbar spine will be ca

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. population: spinal fracture according to radiology report. 2. population: severe trauma, 09/2014-08/2016

Exclusion criteria

Exclusion criteria: CT data used for training of algorithm, elective/non-Trauma CT scan

Design outcomes

Primary

Measure	Time frame
Analysis of diagnostic accuracy of the deep learning algorithm in detecting all sorts of spinal fractures in two different retrospective populations.	—

Secondary

Measure	Time frame
Secondary: Diagnostic accuracy of the algorithm for cervical, thoracic, lumbar fractures. Tertiary: Determine discrepant results of algorithm and radiologist and retrospective analysis of board certified radiologist as gold standard.	—

Countries

Germany

Contacts

Public ContactLeonie Gölz

BG Unfallkrankenhaus Berlin, Institut für Radiologie und Neuroradiologie

leonie.goelz@ukb.de0049-30-56813801

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Jun 11, 2026