Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs

Thiago Fellipe Ortiz de Camargo ^1,2 Guilherme Alberto Sousa Ribeiro ^1,2* Maria Carolina Bueno da Silva ¹ Luan Oliveira da Silva ¹ Pedro Paulo Teixeira e Silva Torres ¹ Denise Rodrigues ³ Mayler Olombrada Nunes E Santos ¹ William Salibe Filho ⁴ Marcela Emer Egypto Rosa ¹ Magdala de Araújo Novaes ⁵ Thiago Augusto Massarutto ⁶ Osvaldo Landi ⁶ Elaine Yanata ¹ Marcio Rodrigues da Cunha Reis ⁷ Gilberto Szarf ¹ Pedro Vieira Santana Netto ¹ Joselisa Peres Queiroz de Paiva ¹

• ¹ Albert Einstein Israelite Hospital, São Paulo, São Paulo, Brazil
• ² Universidade Federal de Goiás, Goiânia, Goiás, Brazil
• ³ Clemente Ferreira Institute, Sao Paulo, Brazil
• ⁴ Faculty of Medicine, University of São Paulo, São Paulo, São Paulo, Brazil
• ⁵ Medical Sciences Center Telehealth Center, Recife, Brazil
• ⁶ Diagnostic Imaging Research and Study Institute Foundation, SAO PAULO, Brazil
• ⁷ Goiano Federal Institute (IFGOIANO), Goiania, Goias, Brazil

Background: Chest X-ray (CXR) interpretation is critical in diagnosing various lung diseases. However, physicians, not specialists, are often the first ones to read them, frequently facing challenges in accurate interpretation. Artificial Intelligence (AI) algorithms could be of great help, but using real-world data is crucial to ensure their effectiveness in diverse healthcare settings. This study evaluates a deep learning algorithm designed for CXR interpretation, focusing on its utility for non-specialists in thoracic radiology physicians. Purpose: To assess the performance of a Convolutional Neural Networks (CNNs)-based AI algorithm in interpreting CXRs and compare it with a team of physicians, including thoracic radiologists, who served as the gold-standard. Methods: A retrospective study from January 2021 to July 2023 evaluated an algorithm with three independent models for Lung Abnormality, Radiological Findings, and Tuberculosis. The algorithm's performance was measured using accuracy, sensitivity, and specificity. Two groups of physicians validated the model: one with varying specialties and experience levels in interpreting chest radiographs (Group A) and another of board-certified thoracic radiologists (Group B). The study also assessed the agreement between the two groups on the algorithm's heatmap and its influence on their decisions. Results: In the internal validation, the Lung Abnormality and Tuberculosis models achieved an AUC of 0.94, while the Radiological Findings model yielded a mean AUC of 0.84. During the external validation, utilizing the ground truth generated by board-certified thoracic radiologists, the algorithm achieved better sensitivity in 6 out of 11 classes than physicians with varying experience levels. Furthermore, Group A physicians demonstrated higher agreement with the algorithm in identifying markings in specific lung regions than Group B (37.56% Group A vs. 21.75% Group B). Additionally, physicians declared that the algorithm did not influence their decisions in 93% of the cases. Conclusion: This retrospective clinical validation study assesses an AI algorithm's effectiveness in interpreting Chest X-rays (CXR). The results show the algorithm's performance is comparable to Group A physicians, using gold-standard analysis (Group B) as the reference. Notably, both Groups reported minimal influence of the algorithm on their decisions in most cases.