FindTrial
Sign In

A Study to Validate and Improve an Automated Image Analysis Algorithm to Detect Tuberculosis in Sputum Smear Slides

A Study to Validate and Improve an Automated Image Analysis Algorithm to Detect Tuberculosis in Sputum Smear Slides

Status
Completed
Phases
Unknown
Study type
Observational
Source
ClinicalTrials.gov
Registry ID
NCT05899400
Enrollment
400
Registered
2023-06-12
Start date
2019-09-15
Completion date
2022-12-31
Last updated
2023-06-12

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

Conditions

Tuberculosis, Pulmonary

Brief summary

A Study to Validate and Improve an Automated Image Analysis Algorithm to Detect Tuberculosis in Sputum Smear Slides

Interventions

DIAGNOSTIC_TESTDiascopic iON Image Analysis System

A scanning digital optical train that images sputum slides for automated analysis by a tuberculosis detecting algorithm

Sponsors

National Institutes of Health (NIH)
CollaboratorNIH
National Institute for Biomedical Imaging and Bioengineering (NIBIB)
CollaboratorNIH
Diascopic, LLC
Lead SponsorINDUSTRY

Study design

Observational model
COHORT
Time perspective
RETROSPECTIVE

Eligibility

Sex/Gender
ALL
Healthy volunteers
No

Inclusion criteria

* Samples sourced from Makerere University's Joint Clinical Research Clinic (JCRC) and Laboratory

Exclusion criteria

* No samples from outside Makerere's Domain

Design outcomes

Primary

MeasureTime frameDescription
Determined sensitivity and specificity of the iON device by comparing MTB slide results to their associated bacterial culture results from the same specimen(s).Study completed over the grant period 2019 - 2022Sensitivity, specificity, and average analysis time were determined. An image database of \>40,000 images was also created for internal use.

Countries

Uganda

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026