NCT04890847

Brief Summary

Biomedical deep learning (DL) often relies heavily on generating reliable labels for large-scale data and highly technical requirements for model training. To efficiently develop DL models, we established an integrated platform to introduce automation to both annotation and model training-the primary process of DL model development. Based on this platform, we quantitively validated and compared the annotation strategy and AI model development with the pure manual annotation method performed on medical image datasets from multiple disciplines.

Trial Health

43
At Risk

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Trial has exceeded expected completion date
Enrollment
200

participants targeted

Target at P75+ for all trials

Timeline
Completed

Started Mar 2021

Shorter than P25 for all trials

Geographic Reach
1 country

1 active site

Status
unknown

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

First Submitted

Initial submission to the registry

March 18, 2021

Completed
Same day until next milestone

Study Start

First participant enrolled

March 18, 2021

Completed
14 days until next milestone

Primary Completion

Last participant's last visit for primary outcome

April 1, 2021

Completed
2 months until next milestone

First Posted

Study publicly available on registry

May 18, 2021

Completed
13 days until next milestone

Study Completion

Last participant's last visit for all outcomes

May 31, 2021

Completed
Last Updated

May 18, 2021

Status Verified

May 1, 2021

Enrollment Period

14 days

First QC Date

March 18, 2021

Last Update Submit

May 16, 2021

Conditions

Medical Artificial IntelligenceMedical Imaging

Outcome Measures

Primary Outcomes (1)

  • annotation accuracy

    calculate annotation accuracy for comparison between groups with using the annotation results

    baseline

Secondary Outcomes (3)

  • accuracy of model performance

    baseline

  • AUC of model performance

    baseline

  • annotation time cost

    baseline

Study Arms (2)

human-machine collaboration group

healthcare professionals and machine collaboration for annotation and AI model development

pure mannual group

healthcare professionals for pure manual annotation and AI model development

Eligibility Criteria

Sexall
Healthy VolunteersYes
Age GroupsChild (0-17), Adult (18-64), Older Adult (65+)
Sampling MethodProbability Sample
Study Population

medical imaging for multiple disciplines including ophthalmology, pathology, radiography, blood cells, and endoscopy

You may qualify if:

  • have medical imaging record (including ophthalmology, pathology, radiography, blood cells, and endoscopy)

You may not qualify if:

  • unqualified medical imaging

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

Zhongshan Ophthalmic Center, Sun Yat-sen Univerisity

Guangzhou, Guangdong, 510060, China

RECRUITING

Study Officials

  • Haotian Lin, Ph.D, M.D.

    Zhongshan Ophthalmic Center, Sun Yat-sen Univerisity

    PRINCIPAL INVESTIGATOR

Central Study Contacts

Haotian Lin, Ph.D, M.D.

CONTACT

+86-020-87330274gddlht@aliyun.com

Study Design

Study Type
observational
Observational Model
CASE CONTROL
Time Perspective
CROSS SECTIONAL
Sponsor Type
OTHER
Responsible Party
PRINCIPAL INVESTIGATOR
PI Title
Principal Investigator

Study Record Dates

First Submitted

March 18, 2021

First Posted

May 18, 2021

Study Start

March 18, 2021

Primary Completion

April 1, 2021

Study Completion

May 31, 2021

Last Updated

May 18, 2021

Record last verified: 2021-05

Locations

CN(1)