Skip to content

Training and validation of an automated diagnostic deep learning algorithm in dermoscopy

Training and validation of an automated diagnostic deep learning algorithm in dermoscopy - AD-LEARN DERMOSCOPY study

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
DRKS
Registry ID
DRKS00013570
Enrollment
300
Registered
2017-12-14
Start date
2018-01-16
Completion date
Unknown
Last updated
2025-04-07

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

Conditions

C43.9 D22.9

Interventions

Group 1: In this study a retrospective analysis of available, beforehand generated digital images for evaluation of a computer software in comparison to conventional physicians' evaluation of dermosco

Sponsors

Universitätsklinikum Heidelberg
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 120 Years

Inclusion criteria

Inclusion criteria: Patients with dermoscopic images depicting nevi or melanoma

Exclusion criteria

Exclusion criteria: Low Image quality

Design outcomes

Primary

MeasureTime frame
Objective of this retrospective analysis is the assessment of the diagnostic performance of a computer algorithm in analyzing dermoscopic images in comparison to dermatologists. Diagnostic Performance will be assessed by means of sensitivity and specificity. Estimated study Duration is 12 months.

Secondary

MeasureTime frame
There are no secondary objectives in this study

Countries

Germany

Contacts

Public ContactHolger Haenssle

Universitäts-Hautklinik Heidelberg

holger.haenssle@med.uni-heidelberg.de06221 56 8576

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Mar 6, 2026