Diagnostic accuracy of AI-assisted chest radiographs in tuberculosis screening: A Ghanaian clinical study.
Tuberculosis remains a major global health challenge, particularly in resource-limited settings where access to expert radiological interpretation is constrained. Artificial intelligence offers a promising solution to enhance diagnostic accuracy and efficiency in TB screening.
This study aimed to evaluate the diagnostic performance of an AI-based system compared to a radiologist in screening for TB using chest X-rays from 1,010 patients.
Patients were adults ≥18 years with suspected TB in a high-burden setting. GeneXpert MTB/RIF served as reference to assess accuracy, sensitivity, specificity, PPV, NPV, and AUC for radiologist and AI TB predictions. Comparisons used McNemar's test and Cohen's kappa to evaluate agreement and significance of differences.
The AI system demonstrated superior performance with an accuracy of 91%, sensitivity of 86%, specificity of 93%, PPV of 85%, NPV of 94%, and AUC of 0.90. In contrast, the radiologist achieved an accuracy of 86%, sensitivity of 84%, specificity of 87%, PPV of 76%, NPV of 92%, and AUC of 0.86. McNemar's test revealed a statistically significant difference between the two modalities (p = 0.0021). Cohen's kappa indicated substantial agreement between AI and GeneXpert MTB/RIF result (κ = 0.79), moderate agreement for the radiologist and GeneXpert MTB/RIF result (κ = 0.69), and moderate agreement between radiologist and AI predictions (κ = 0.53).
The AI system outperformed the radiologist in TB screening, demonstrating higher diagnostic accuracy and agreement with GeneXpert MTB/RIF result. These findings support the integration of AI into TB screening workflows, particularly in settings with limited access to expert radiological interpretation.
This study aimed to evaluate the diagnostic performance of an AI-based system compared to a radiologist in screening for TB using chest X-rays from 1,010 patients.
Patients were adults ≥18 years with suspected TB in a high-burden setting. GeneXpert MTB/RIF served as reference to assess accuracy, sensitivity, specificity, PPV, NPV, and AUC for radiologist and AI TB predictions. Comparisons used McNemar's test and Cohen's kappa to evaluate agreement and significance of differences.
The AI system demonstrated superior performance with an accuracy of 91%, sensitivity of 86%, specificity of 93%, PPV of 85%, NPV of 94%, and AUC of 0.90. In contrast, the radiologist achieved an accuracy of 86%, sensitivity of 84%, specificity of 87%, PPV of 76%, NPV of 92%, and AUC of 0.86. McNemar's test revealed a statistically significant difference between the two modalities (p = 0.0021). Cohen's kappa indicated substantial agreement between AI and GeneXpert MTB/RIF result (κ = 0.79), moderate agreement for the radiologist and GeneXpert MTB/RIF result (κ = 0.69), and moderate agreement between radiologist and AI predictions (κ = 0.53).
The AI system outperformed the radiologist in TB screening, demonstrating higher diagnostic accuracy and agreement with GeneXpert MTB/RIF result. These findings support the integration of AI into TB screening workflows, particularly in settings with limited access to expert radiological interpretation.
Authors
Sule Sule, Kyei Kyei, Antwi Antwi, Acquah Acquah, Dzefi-Tettey Dzefi-Tettey, Daniels Daniels, Nyantakyi Nyantakyi
View on Pubmed