โก Quick Summary
A recent systematic review and meta-analysis evaluated the diagnostic accuracy of artificial intelligence (AI) software for detecting pulmonary tuberculosis (PTB) using chest X-ray (CXR) imaging. The findings indicate that AI tools can significantly enhance diagnostic performance, with sensitivities ranging from 86.0% to 91.0% across various software solutions.
๐ Key Details
- ๐ Dataset: 5,651 references reviewed, 21 selected for analysis
- ๐งฉ AI Tools Evaluated: JF CXR-1, qXR, Lunit INSIGHT CXR, CAD4TB, InferRead DR Chest
- โ๏ธ Technology: Deep learning-based computer-aided detection (CAD)
- ๐ Performance Metrics: Sensitivity: 86.0% – 91.0%; Specificity: 59.0% – 80.0%
๐ Key Takeaways
- ๐ Global Challenge: PTB remains a significant public health issue with 10.8 million new cases reported in 2023.
- ๐ก Early Diagnosis: Timely detection is crucial for controlling TB spread, yet traditional tests are limited.
- ๐ฉป Cost-effective Tool: Chest X-ray is widely used but often hampered by a lack of radiologists in high-burden areas.
- ๐ค AI Solutions: AI-based CAD systems show promise in automating PTB detection.
- ๐ Variability: Diagnostic performance varies among AI tools, necessitating scenario-specific adjustments.
- ๐ฅ Clinical Implications: AI can assist clinicians in making rapid and accurate decisions for TB screening and treatment.
- ๐ Research Scope: The study analyzed literature from multiple databases up to December 2024.
- ๐ Selected Software: Included JF CXR-1, qXR, Lunit INSIGHT CXR, CAD4TB, and InferRead DR Chest.
๐ Background
Pulmonary tuberculosis (PTB) is a major global health concern, with millions of new cases emerging each year. Traditional diagnostic methods, primarily sputum-based tests, often face challenges such as long turnaround times and limited resources, particularly in regions heavily burdened by TB. The use of chest X-ray (CXR) imaging offers a cost-effective alternative, yet its effectiveness is often compromised by a shortage of trained radiologists. This gap has led to the exploration of artificial intelligence (AI) as a potential solution for enhancing diagnostic accuracy and efficiency.
๐๏ธ Study
The systematic review and meta-analysis aimed to evaluate the diagnostic accuracy of five AI-based software solutions for CXR analysis in detecting PTB. Researchers conducted a comprehensive literature search across multiple databases, including PubMed and Embase, to identify relevant studies published up to December 2024. The analysis focused on the sensitivity and specificity of each AI tool, providing valuable insights into their performance in real-world settings.
๐ Results
The meta-analysis included five AI software solutions, each demonstrating varying levels of diagnostic performance. The sensitivity and specificity results were as follows:
JF CXR-1 (86.0% sensitivity, 80.0% specificity),
qXR (90.0% sensitivity, 64.0% specificity),
Lunit INSIGHT CXR (90.0% sensitivity, 63.0% specificity),
CAD4TB (91.0% sensitivity, 60.0% specificity), and
InferRead DR Chest (89.0% sensitivity, 59.0% specificity).
These results highlight the potential of AI tools to assist in the rapid and accurate diagnosis of PTB.
๐ Impact and Implications
The findings from this study underscore the transformative potential of AI in the realm of tuberculosis diagnosis. By integrating AI-based CAD systems into clinical practice, healthcare providers can enhance the speed and accuracy of PTB detection, ultimately leading to improved patient outcomes. This advancement is particularly crucial in high-burden regions where access to radiologists is limited. The implications extend beyond TB, as the methodologies and technologies developed could be adapted for other diagnostic challenges in healthcare.
๐ฎ Conclusion
This systematic review and meta-analysis reveal the significant promise of AI software in enhancing the diagnostic accuracy of PTB through chest X-ray imaging. As healthcare continues to evolve with technological advancements, the integration of AI tools can facilitate more effective screening and treatment strategies for tuberculosis. Continued research and development in this field are essential to fully realize the potential of AI in improving global health outcomes.
๐ฌ Your comments
What are your thoughts on the integration of AI in tuberculosis diagnosis? We would love to hear your insights! ๐ฌ Join the conversation in the comments below or connect with us on social media:
A systematic review and meta-analysis of artificial intelligence software for tuberculosis diagnosis using chest X-ray imaging.
Abstract
BACKGROUND: Pulmonary tuberculosis (PTB) remains a global public health challenge, with 10.8 million new cases reported in 2023. Early diagnosis is crucial for controlling its spread, yet traditional sputum-based tests face limitations in turnaround time and resource availability. Chest X-ray (CXR) is a cost-effective diagnostic tool, but its use in high-tuberculosis (TB) burden regions is restricted by a shortage of radiologists. Artificial intelligence (AI)-based computer-aided detection (CAD) systems, leveraging deep learning, offer a promising solution for automated PTB detection. However, variability in diagnostic performance across AI tools and the need for scenario-specific threshold adjustments remain challenges that need to be addressed. Our meta-analysis evaluated the diagnostic accuracy of five AI-based PTB detection products, aiming to provide insights for advancing AI applications in TB screening and diagnosis.
METHODS: The PubMed, Embase, Web of Science, and Cochrane Library databases were searched for literature related to CXR diagnosis of TB based on AI technology published from the establishment day of the database to December 19, 2024. The keywords were “artificial intelligence”, “tuberculosis”, “chest X-ray”, and “diagnosis”. The literature search, screening, data extraction, quality evaluation, and bias risk assessment were conducted independently by two researchers, and Stata 17.0 software (StataCorp) was used to process and analyze the data.
RESULTS: A total of 5,651 references were retrieved, and 21 references were finally selected according to the inclusion and exclusion criteria. The meta-analysis included five software solutions for CXR analysis: JF CXR-1 (JF Healthcare, Nanchang, China), qXR (Qure.ai, Mumbai, India), Lunit INSIGHT CXR (Lunit, Seoul, South Korea), CAD4TB (Delft Imaging, ‘s-Hertogenbosch, Netherlands), and InferRead DR Chest (Infervision, Beijing, China). Their sensitivity and specificity were as follows: JF CXR-1, 86.0% and 80.0%; qXR, 90.0% and 64.0%; Lunit INSIGHT CXR, 90.0% and 63.0%; CAD4TB, 91.0% and 60.0%; InferRead DR Chest, 89.0% and 59.0%.
CONCLUSIONS: AI software has demonstrated excellent diagnostic performance in assisting the CXR diagnosis of TB and can help clinicians to make rapid and accurate decisions in screening and treating patients with TB.
Author: [‘Han ZL’, ‘Zhang YY’, ‘Li J’, ‘Gao S’, ‘Liu W’, ‘Yang WJ’, ‘Xing ZH’]
Journal: J Thorac Dis
Citation: Han ZL, et al. A systematic review and meta-analysis of artificial intelligence software for tuberculosis diagnosis using chest X-ray imaging. A systematic review and meta-analysis of artificial intelligence software for tuberculosis diagnosis using chest X-ray imaging. 2025; 17:3223-3237. doi: 10.21037/jtd-2025-604