⚡ Quick Summary
A systematic review evaluated the diagnostic performance of artificial intelligence (AI) methods for detecting tuberculosis (TB), revealing an impressive mean accuracy of 91.93% and a mean area under the curve (AUC) of 93.48%. The findings highlight the potential of AI in enhancing TB detection, although further research is needed for real-world applicability.
🔍 Key Details
- 📊 Dataset: 152 studies included from 1146 records
- 🧩 Features used: Radiographic biomarkers and deep learning approaches
- ⚙️ Technology: Convolutional Neural Networks (CNNs) including VGG-16, ResNet-50, and DenseNet-121
- 🏆 Performance: Mean accuracy 91.93%, Mean AUC 93.48%
🔑 Key Takeaways
- 📊 AI methods show great promise in TB detection with high accuracy rates.
- 💡 Deep learning approaches, particularly CNNs, are the most commonly utilized.
- 👩🔬 Majority of studies focused on model development using single modality approaches.
- 🏆 Mean sensitivity was reported at 92.77%, indicating strong detection capabilities.
- 🌍 Transfer learning is gaining traction, with 58.6% of studies employing this method.
- 🔍 Only 0.7% of studies conducted domain-shift analysis, highlighting a gap in research.
- 📈 Future research should focus on real-world applicability and domain-shift analyses.
- 🗓️ Study registered under PROSPERO CRD42023453611.
📚 Background
Tuberculosis (TB) remains a major global health challenge, being the leading cause of mortality among infectious diseases. Traditional diagnostic tools have proven inadequate on their own, prompting the exploration of artificial intelligence (AI) as a potential solution. This systematic review aims to synthesize current knowledge on AI-based algorithms for TB detection, providing insights into their effectiveness and areas for improvement.
🗒️ Study
Following the PRISMA 2020 guidelines, this systematic review analyzed 152 studies from a pool of 1146 records across major databases including Scopus and PubMed. The QUADAS-2 tool was utilized to assess the risk of bias in the included studies, ensuring a comprehensive evaluation of the diagnostic performance of AI methods in TB detection.
📈 Results
The review found that AI methods demonstrated excellent performance across various studies, with a mean accuracy of 91.93% and a mean AUC of 93.48%. Notably, radiographic biomarkers were predominantly used, and deep learning approaches, particularly convolutional neural networks, were the most common. The results also indicated high sensitivity and specificity, with mean sensitivity at 92.77% and mean specificity at 92.39%.
🌍 Impact and Implications
The findings from this review underscore the significant potential of AI-based methods in improving TB detection. By leveraging advanced algorithms, healthcare providers could enhance diagnostic accuracy, leading to better patient outcomes. However, the limited number of studies addressing real-world applicability suggests a need for further research, particularly in conducting domain-shift analyses to simulate actual clinical scenarios.
🔮 Conclusion
This systematic review highlights the promising role of AI in the detection of tuberculosis, showcasing high accuracy and sensitivity rates. As the healthcare landscape continues to evolve, integrating AI technologies into TB diagnostics could revolutionize patient care. Future research should prioritize real-world applicability to fully harness the benefits of these innovative methods.
💬 Your comments
What are your thoughts on the integration of AI in TB detection? We would love to hear your insights! 💬 Leave your comments below or connect with us on social media:
Diagnostic Performance of Artificial Intelligence-Based Methods for Tuberculosis Detection: Systematic Review.
Abstract
BACKGROUND: Tuberculosis (TB) remains a significant health concern, contributing to the highest mortality among infectious diseases worldwide. However, none of the various TB diagnostic tools introduced is deemed sufficient on its own for the diagnostic pathway, so various artificial intelligence (AI)-based methods have been developed to address this issue.
OBJECTIVE: We aimed to provide a comprehensive evaluation of AI-based algorithms for TB detection across various data modalities.
METHODS: Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) 2020 guidelines, we conducted a systematic review to synthesize current knowledge on this topic. Our search across 3 major databases (Scopus, PubMed, Association for Computing Machinery [ACM] Digital Library) yielded 1146 records, of which we included 152 (13.3%) studies in our analysis. QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies version 2) was performed for the risk-of-bias assessment of all included studies.
RESULTS: Radiographic biomarkers (n=129, 84.9%) and deep learning (DL; n=122, 80.3%) approaches were predominantly used, with convolutional neural networks (CNNs) using Visual Geometry Group (VGG)-16 (n=37, 24.3%), ResNet-50 (n=33, 21.7%), and DenseNet-121 (n=19, 12.5%) architectures being the most common DL approach. The majority of studies focused on model development (n=143, 94.1%) and used a single modality approach (n=141, 92.8%). AI methods demonstrated good performance in all studies: mean accuracy=91.93% (SD 8.10%, 95% CI 90.52%-93.33%; median 93.59%, IQR 88.33%-98.32%), mean area under the curve (AUC)=93.48% (SD 7.51%, 95% CI 91.90%-95.06%; median 95.28%, IQR 91%-99%), mean sensitivity=92.77% (SD 7.48%, 95% CI 91.38%-94.15%; median 94.05% IQR 89%-98.87%), and mean specificity=92.39% (SD 9.4%, 95% CI 90.30%-94.49%; median 95.38%, IQR 89.42%-99.19%). AI performance across different biomarker types showed mean accuracies of 92.45% (SD 7.83%), 89.03% (SD 8.49%), and 84.21% (SD 0%); mean AUCs of 94.47% (SD 7.32%), 88.45% (SD 8.33%), and 88.61% (SD 5.9%); mean sensitivities of 93.8% (SD 6.27%), 88.41% (SD 10.24%), and 93% (SD 0%); and mean specificities of 94.2% (SD 6.63%), 85.89% (SD 14.66%), and 95% (SD 0%) for radiographic, molecular/biochemical, and physiological types, respectively. AI performance across various reference standards showed mean accuracies of 91.44% (SD 7.3%), 93.16% (SD 6.44%), and 88.98% (SD 9.77%); mean AUCs of 90.95% (SD 7.58%), 94.89% (SD 5.18%), and 92.61% (SD 6.01%); mean sensitivities of 91.76% (SD 7.02%), 93.73% (SD 6.67%), and 91.34% (SD 7.71%); and mean specificities of 86.56% (SD 12.8%), 93.69% (SD 8.45%), and 92.7% (SD 6.54%) for bacteriological, human reader, and combined reference standards, respectively. The transfer learning (TL) approach showed increasing popularity (n=89, 58.6%). Notably, only 1 (0.7%) study conducted domain-shift analysis for TB detection.
CONCLUSIONS: Findings from this review underscore the considerable promise of AI-based methods in the realm of TB detection. Future research endeavors should prioritize conducting domain-shift analyses to better simulate real-world scenarios in TB detection.
TRIAL REGISTRATION: PROSPERO CRD42023453611; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023453611.
Author: [‘Hansun S’, ‘Argha A’, ‘Bakhshayeshi I’, ‘Wicaksana A’, ‘Alinejad-Rokny H’, ‘Fox GJ’, ‘Liaw ST’, ‘Celler BG’, ‘Marks GB’]
Journal: J Med Internet Res
Citation: Hansun S, et al. Diagnostic Performance of Artificial Intelligence-Based Methods for Tuberculosis Detection: Systematic Review. Diagnostic Performance of Artificial Intelligence-Based Methods for Tuberculosis Detection: Systematic Review. 2025; 27:e69068. doi: 10.2196/69068