Machine learning-based model assists in differentiating Mycobacterium avium Complex Pulmonary Disease from Pulmonary Tuberculosis: A Multicenter Study. - National Genomics Data Center (CNCB-NGDC)

Advanced Search

Machine learning-based model assists in differentiating Mycobacterium avium Complex Pulmonary Disease from Pulmonary Tuberculosis: A Multicenter Study.

Jiacheng Zhang, Tingting Huang, Xu He, Dingsheng Han, Qian Xu, Fukun Shi, Lan Zhang, Dailun Hou

Author Information

Jiacheng Zhang: MRI Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou Key Laboratory of Intelligent Analysis and Utilization of Traditional Chinese Medicine Information, Zhengzhou, 450000, China.
Tingting Huang: Radiological Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou, 450000, China.
Xu He: MRI Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou Key Laboratory of Intelligent Analysis and Utilization of Traditional Chinese Medicine Information, Zhengzhou, 450000, China.
Dingsheng Han: MRI Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou Key Laboratory of Intelligent Analysis and Utilization of Traditional Chinese Medicine Information, Zhengzhou, 450000, China.
Qian Xu: MRI Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou Key Laboratory of Intelligent Analysis and Utilization of Traditional Chinese Medicine Information, Zhengzhou, 450000, China.
Fukun Shi: MRI Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou Key Laboratory of Intelligent Analysis and Utilization of Traditional Chinese Medicine Information, Zhengzhou, 450000, China.
Lan Zhang: MRI Department, The First Affiliated Hospital of Henan University of Chinese Medicine, Zhengzhou Key Laboratory of Intelligent Analysis and Utilization of Traditional Chinese Medicine Information, Zhengzhou, 450000, China. 13837187787@163.com. ORCID
Dailun Hou: Department of Radiology, Beijing Chest Hospital, Capital Medical University, Beijing, 101149, China. hou.dl@mail.ccmu.edu.cn.

PMID: 40169471 DOI: 10.1007/s10278-025-01486-7

The number of Mycobacterium avium-intracellulare complex pulmonary disease patients is increasing globally. Distinguishing Mycobacterium avium-intracellulare complex pulmonary disease from pulmonary tuberculosis is difficult due to similar manifestations and characteristics. We aimed to build and validate a machine learning model using clinical data and computed tomography features to differentiate them. This multi-centered, retrospective study included 169 patients diagnosed with Mycobacterium avium-intracellulare complex and pulmonary tuberculosis from date to date. Data were analyzed, and logistic regression, random forest, and support vector machine models were established and validated. Performance was evaluated using receiver operating characteristic and precision-recall curves. In total, 84 patients with Mycobacterium avium-intracellulare complex pulmonary disease and 85 with pulmonary tuberculosis were analyzed. Patients with Mycobacterium avium-intracellulare complex pulmonary disease were older. Hemoptysis rate, cavity number and morphology, bronchiectasis type, and distribution differed. The support vector machine model performed better. In the training set, the area under the curve was 0.960, and in the validation set it was 0.885. The precision-recall curve showed high accuracy and low recall for the support vector machine model. The support vector machine learning-based model, which integrates clinical data and computed tomography imaging features, exhibited excellent diagnostic performance and can assist in differentiating Mycobacterium avium-intracellulare complex pulmonary disease from pulmonary tuberculosis.

Mycobacterium avium complex pulmonary disease Computed tomography Differentiate Machine learning Pulmonary tuberculosis

Liu Q, Du J, An H, Li X, Guo D, Li J, Gong W, Liang J: Clinical characteristics of patients with non-tuberculous mycobacterial pulmonary disease: a seven-year follow-up study conducted in a certain tertiary hospital in Beijing. Front Cell Infect Microbiol 13:1205225, 2023 [DOI: 10.3389/fcimb.2023.1205225]
Kim C, Park SH, Oh SY, Kim SS, Jo KW, Shim TS, Kim MY: Comparison of chest CT findings in nontuberculous mycobacterial diseases vs. Mycobacterium tuberculosis lung disease in HIV-negative patients with cavities. PLoS One 12:e0174240, 2017
Dahl VN, M��lhave M, Fl��e A, van Ingen J, Sch��n T, Lillebaek T, Andersen AB, Wejse C: Global trends of pulmonary infections with nontuberculous mycobacteria: a systematic review. Int J Infect Dis 125:120-131, 2022 [DOI: 10.1016/j.ijid.2022.10.013]
Van Ingen J, Obradovic M, Hassan M, Lesher B, Hart E, Chatterjee A, Daley CL: Nontuberculous mycobacterial lung disease caused by Mycobacterium avium complex - disease burden, unmet needs, and advances in treatment developments. Expert Rev Respir Med 15:1387-1401, 2021 [DOI: 10.1080/17476348.2021.1987891]
Kumar K, Daley CL, Griffith DE, Loebinger MR: Management of Mycobacterium avium complex and Mycobacterium abscessus pulmonary disease: therapeutic advances and emerging treatments. Eur Respir Rev 31, 2022
Busatto C, Vianna JS, Da Silva LVJ, Ramis IB, da Silva PEA: Mycobacterium avium: an overview. Tuberculosis (Edinb) 114:127-134, 2019 [DOI: 10.1016/j.tube.2018.12.004]
Cooper R, Williams M, Fennelly KP: Abandon the acid-fast bacilli smear for patients with TB on effective treatment. Chest 164:21-23, 2023 [DOI: 10.1016/j.chest.2023.02.006]
Yuan MK, Chang CY, Tsai PH, Lee YM, Huang JW, Chang SC: Comparative chest computed tomography findings of non-tuberculous mycobacterial lung diseases and pulmonary tuberculosis in patients with acid fast bacilli smear-positive sputum. BMC Pulm Med14:65, 2014 [DOI: 10.1186/1471-2466-14-65]
Maru��i�� A, Kuhti�� I, Ma��urani�� I, Jankovi�� M, Glodi�� G, Sabol I, Stani�� L: Nodular distribution pattern on chest computed tomography (CT) in patients diagnosed with nontuberculous mycobacteria (NTM) infections. Wien Klin Wochenschr 133:470-477, 2021 [DOI: 10.1007/s00508-020-01701-1]
Miura K, Nakamura M, Taooka Y, Hotta T, Hamaguchi M, Okimoto T, Tsubata Y, Hamaguchi S, Kuraki T, Isobe T: Comparison of the chest computed tomography findings between patients with pulmonary tuberculosis and those with Mycobacterium avium complex lung disease. Respir Investig 58:137-143, 2020 [DOI: 10.1016/j.resinv.2019.12.006]
Campredon A, Battistella E, Martin C, Durieu I, Mely L, Marguet C, Belleguic C, Murris-Espin M, Chiron R, Fanton A, Bui S: Using chest CT scan and unsupervised machine learning for predicting and evaluating response to lumacaftor-ivacaftor in people with cystic fibrosis. Eur Respir J 210134, 2021
Griffith DE, Aksamit T, Brown-Elliott BA, Catanzaro A, Daley C, Gordin F, Holland SM, Horsburgh R, Huitt G, Iademarco MF, Iseman M: an official ATS/IDSA statement: diagnosis, treatment, and prevention of nontuberculous mycobacterial diseases. Am J Respir Crit Care Med 175:367-416, 2007 [DOI: 10.1164/rccm.200604-571ST]
Li Y, Cai B, Wang B, Lv Y, He W, Xie X, Hou D: Differentiating malignant pleural mesothelioma and metastatic pleural disease based on a machine learning model with primary CT signs: a multicentre study. Heliyon 8:e11383, 2022 [DOI: 10.1016/j.heliyon.2022.e11383]
Gao JW, Rizzo S, MA, Ma LH, Qiu XY, Warth A, Seki N, Hasegawa M, Zou JW, Li Q, Femia M, Lv TF: Pulmonary ground-glass opacity: computed tomography features, histopathology and molecular pathology. Transl Lung Cancer Res 6:68-75, 2017 [DOI: 10.21037/tlcr.2017.01.02]
Canan A, Batra K, Saboo SS, Landay M, Kandathil A: Radiological approach to cavitary lung lesions. Postgrad Med J 97:521-531, 2021 [DOI: 10.1136/postgradmedj-2020-138694]
O��Donnell AE: Bronchiectasis - a clinical review. N Engl J Med 387:533-545, 2022 [DOI: 10.1056/NEJMra2202819]
Zhou QM, Zhe L, Brooke RJ, Hudson MM, Yuan Y: A relationship between the incremental values of area under the ROC curve and of area under the precision-recall curve. Diagn Progn Res 5:13, 2021 [DOI: 10.1186/s41512-021-00102-w]
Minomo S, Kobayashi T, Katayama K, Ryuge M, Kagawa T, Tsuyuguchi K, Matsui H, Suzuki K: Risk factors for hemoptysis in Mycobacterium avium complex lung disease. Respir Investig 59:218-222, 2021 [DOI: 10.1016/j.resinv.2020.09.007]
Wang L, Ding W, Mo Y, Shi D, Zhang S, Zhong L, Wang K, Wang J, Huang C, Zhang S, Ye Z: Distinguishing nontuberculous mycobacteria from Mycobacterium tuberculosis lung disease from CT images using a deep learning framework. Eur J Nucl Med Mol Imaging 48:4293-4306, 2021 [DOI: 10.1007/s00259-021-05432-x]
Oshitani Y, Kitada S, Edahiro R, Tsujino K, Kagawa H, Yoshimura K, Miki K, Miki M, Kida H: Characteristic chest CT findings for progressive cavities in Mycobacterium avium complex pulmonary disease: a retrospective cohort study. Respir Res 21:10, 2020 [DOI: 10.1186/s12931-020-1273-x]
Martinez-Garcia MA, Guan WJ, De-La-Rosa D, Athanazio R, Oscullo G, Shi MX, Pujal-Monta��a P, Endlich BN, Tiberi S, Centis R, Migliori GB: Post-TB bronchiectasis: from pathogenesis to rehabilitation. Int J Tuberc Lung Dis 27:175-181, 2023 [DOI: 10.5588/ijtld.22.0566]
Kwak N, Lee JH, Kim HJ, Kim SA, Yim JJ: New-onset nontuberculous mycobacterial pulmonary disease in bronchiectasis: tracking the clinical and radiographic changes. BMC Pulm Med 20:293, 2020 [DOI: 10.1186/s12890-020-01331-3]
Stek C, Allwood B, Walker NF, Wilkinson RJ, Lynen L, Meintjes G: The immune mechanisms of lung parenchymal damage in tuberculosis and the role of host-directed therapy. Front Microbiol 9:2603, 2018 [DOI: 10.3389/fmicb.2018.02603]
Park TY, Chong S, Jung JW, Park IW, Choi BW, Lim C, Lee CU, Kim YS, Choi HW, Choi JC: Natural course of the nodular bronchiectatic form of Mycobacterium avium complex lung disease: long-term radiologic change without treatment. PLoS One 12:e0185774, 2017 [DOI: 10.1371/journal.pone.0185774]
Xing Z, Ding W, Zhang S, Zhong L, Wang L, Wang J, Wang K, Xie Y, Zhao X, Li N, Ye Z: Machine learning-based differentiation of nontuberculous mycobacteria lung disease and pulmonary tuberculosis using CT images. BioMed Res Int 2020:6287545, 2020 [DOI: 10.1155/2020/6287545]
Yan Q, Zhao W, Kong H, Chi J, Dai Z, Yu D, Cui J: CT-based radiomics analysis of consolidation characteristics in differentiating pulmonary disease of non-tuberculous mycobacterium from pulmonary tuberculosis. Exp Ther Med 27:112, 2024 [DOI: 10.3892/etm.2024.12400]
Liu CJ, Tsai CC, Kuo LC, Kuo PC, Lee MR, Wang JY, Ko JC, Shih JY, Wang HC, Yu CJ: A deep learning model using chest X-ray for identifying TB and NTM-LD patients: a cross-sectional study. Insights Imaging 14:67, 2023 [DOI: 10.1186/s13244-023-01395-9]

Journal Article

No available data.