AI-based System for Lung Tuberculosis Screening: Diagnostic Accuracy Evaluation

NCT05889364 | Unknown

• 1 other identifier: 2018-1
• Study Type: observational
• Target: 308
• Locations: 1 country
• Sites: 1

Brief Summary

Testing of AI solutions to assess diagnostic accuracy for tuberculosis detection.

Conditions

Tuberculosis, Pulmonary

Keywords

AI; deep learning; tuberculosis; radiology; x-ray; e-health; screening; chest; artificial intelligence

Outcome Measures

Primary Outcomes (6)

• Diagnostic accuracy metric 1

  Sensitivity

  Day 1 upon receipt of data

• Diagnostic accuracy metric 2

  Specificity

  Day 2 upon receipt of data

• Diagnostic accuracy metric 3

  Positive predictor values

  Day 3 upon receipt of data

• Diagnostic accuracy metric 4

  Negative predictor values

  Day 4 upon receipt of data

• Diagnostic accuracy metric 5

  Likelihood ratio

  Day 5 upon receipt of data

• Diagnostic accuracy metric 6

  Area under the ROC curve

  Day 6 upon receipt of data

Study Arms (2)

Sample N1

(n=140) with ratio "normal: tuberculosis" 50:50

Diagnostic Test: AI-based x-ray analysis and triage ("normal/tuberculosis suspected")

Sample N2

(n=150) with ratio "normal: tuberculosis" 95:5

Diagnostic Test: AI-based x-ray analysis and triage ("normal/tuberculosis suspected")

Interventions

AI-based x-ray analysis and triage ("normal/tuberculosis suspected") DIAGNOSTIC_TEST

All included x-rays will be analysed by the AI-based system. Then results will be compared with opinions of 2 experienced radiologists (they make peer-review of all included images independently of each other).

Also known as: artificial intelligence analysis of medical images

Sample N1; Sample N2

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

308 chest x-ray images selected from the database of Unified Radiological Information Service (URIS) of Moscow

You may qualify if:

• no pathology in a lung on chest x-ray
• signs of lung tuberculosis on chest x-ray

You may not qualify if:

• any pathology in the lungs (except tuberculosis)

Sponsors & Collaborators

• Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department: lead

Study Sites (1)

Research and Practical Center of Medical Radiology, Department of Health Care of Moscow

Moscow, 109029, Russia

Location

MeSH Terms

Conditions

Tuberculosis, Pulmonary; Tuberculosis

Condition Hierarchy (Ancestors)

Mycobacterium Infections; Actinomycetales Infections; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Infections; Respiratory Tract Infections; Lung Diseases; Respiratory Tract Diseases

Study Officials

• Anton Vladzymyrskyy

  Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Deputy CEO

Study Record Dates

• First Submitted: March 28, 2018
• First Posted: June 5, 2023
• Study Start: February 1, 2018
• Primary Completion: March 15, 2018
• Study Completion: December 30, 2023
• Last Updated: June 5, 2023

Record last verified: 2023-05

Data Sharing

• IPD Sharing: Will not share

Locations

RU (1)