Transforming Tuberculosis Care: The Role of Deep Learning Models in MDR-TB Prediction
Keywords:
AI-driven TB diagnosis, computer-assisted tuberculosis diagnosis, CNN, Tuberculosis, MDR-TB, Deep Learning
Abstract
Multidrug-resistant TB(MDR-TB), a subtype of TB that remains a global health issue, is a significant barrier to detection and treatment. With a focus on MDR-TB prediction and early identification, this paper investigates the revolutionary implications of AI and ML in TB treatment. This research uses a range of sources to explore possible risks, demographic integration, and the performance of ML algorithms. The literature review focuses on the prospects of DL for TB-diagnosis, covering current breakthroughs, challenges, and resources like UNet and TBXNet. Critical reviews examine the generalizability of AI models, ethical implications, and cost-effectiveness. The study highlighted many important tasks, including exploring demographic integration, examining financial ramifications, and developing optimal ML models. Considering ethical issues and overcoming difficulties in various healthcare settings, the findings suggest that AI and ML may be effective in TB detection.
References
[1]. S. J. Heo, E. J. Lee, S. H. Kim, Y. Kim, and S. Kang, “DL algorithms with demographic information help to detect TB in chest radiographs in annual workers health examination data,” Int. J. Environ. Res. Pub¬lic Health, vol. 16, no. 2, p. 250, 2019.
[2]. M. H. Ali, D. M. Khan, K. Jamal, Z. Ahmad, S. Manzoor, and Z. Khan, “Prediction of multidrug-resistant TB using ML algorithms in SWAT, Pakistan,” J. Healthc. Eng., vol. 2021, p. 2567080, 2021.
[3]. Y. Xie, M. Zhang, Q. Li, Y. Wei, L. Liu, and Z. Huang, “Computer-aided system for the detection of multicategory pulmonary TB in ra-diographs,” J. Healthc. Eng., vol. 2020, p. 9205082, 2020.
[4]. X. Kuang, F. Wang, K. M. Hernandez, Z. Zhang, and R. L. Grossman, “Accurate and rapid prediction of TB drug resistance from genome sequence data using traditional ML algorithms and CNN,” Sci. Rep., vol. 12, no. 1, p. 2427, 2022.
[5]. L. T. Duong, N. H. Le, T. B. Tran, V. M. Ngo, and P. T. Nguyen, “Detection of TB from chest X-ray images: Boosting the performance with vision transformer and transfer learning,” Expert Syst. Appl., vol. 184, no. 115519, p. 115519, 2021.
[6]. S. J. Heo, E. J. Lee, S. H. Kim, Y. Kim, and S. Kang, “DL algorithms with demographic information help to detect TB in chest radiographs in annual workers health examination data,” Int. J. Environ. Res. Pub¬lic Health, vol. 16, no. 2, p. 250, 2019.
[7]. S. Das and M. K. Sanyal, “Machine intelligent diagnostic system (MIDs): An instance of medical diagnosis of TB,” Neural Comput. Appl., vol. 32, no. 19, pp. 1558515595, 2020.
[8]. M. Singh, A. K. Goel, H. Gupta, S. K. Goyal, and A. Jain, “Evolution of ML in TB diagnosis: A review of DL-based medical applications,” Electronics (Basel), vol. 11, no. 17, p. 2634, 2022.
[9]. H. K. Virupakshaiah and N. T R, "Tuberculosis Detection in Chest X-Ray Images Using Deep Learning Techniques," 2025 5th International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), MANDYA, India, 2025, pp. 1-6, doi: 10.1109/ICERECT65215.2025.11376057.
[10]. V. Sharma, Nillmani, S. K. Gupta, and K. K. Shukla, “TB detection in chest X-rays using convolutional neural networks,” Int. J. Comput. Appl., vol. 975, no. 8887, pp. 14, 2020.
[11]. N. P. Nsengiyumva, L. Niyonzima, R. Nyandwi, and J. B. Ntaganda, “Triage of persons with TB symptoms using artificial intelligence-based chest radiograph interpretation: A cost-effectiveness analysis,” Open Forum Infect. Dis., vol. 8, no. 12, p. ofab567, 2021.
[12]. R. Rajakumar, R. S. Uma Maheswari, and S. P. Karuppiah, “TB de¬tection in chest X-ray using Mayfly-algorithm optimized dual-deep-learning features,” J. Xray Sci. Technol., vol. 29, no. 6, 2021.
[13]. A. Iqbal, M. Usman, and Z. Ahmed, “An efficient DL-based frame¬work for TB detection using chest X-ray images,” TB(Edinb.), vol. 136, no. 102234, p. 102234, 2022.
[14]. M. K. Puttagunta and S. Ravi, “Detection of TB based on DL based methods,” J. Phys. Conf. Ser., vol. 1767, no. 1, p. 012004, 2021.
[15]. S. Hansun, A. Argha, S.-T. Liaw, B. G. Celler, and G. B. Marks, “Ma-chine and DL for TB detection on chest X-rays: Systematic literature review,” J. Med. Internet Res., vol. 25, p. e43154, 2023.
[16]. Y. Lee, M. C. Raviglione, and A. Flahault, “Use of digital technology to enhance TB control: Scoping review,” J. Med. Internet Res., vol. 22, no. 2, p. e15727, 2020.
[17]. A. K. Siddiqui and V. K. Garg, "Diagnosis of Pulmonary Tuberculosis through Intelligent Techniques: A Review," 2021 International Conference on Computing Sciences (ICCS), Phagwara, India, 2021, pp. 189-193
[18]. K. C. Santosh, S. Allu, S. Rajaraman, and S. Antani, “Advances in DL for TB screening using chest X-rays: The last 5 years review,” J. Med. Syst., vol. 46, no. 11, p. 82, 2022.
[19]. O. S. Balogun, S. A. Olaleye, M. Mohsin, and P. Toivanen, “Inves-tigating ML methods for TB risk factors prediction: A comparative analysis and evaluation,” J. Comput. Appl., vol. 25, no. 2, 2021.
[20]. O. N. Bridget, R. Prasad, C. Onime, and A. A. Ali, “Drug resistant TB classification using logistic regression,” Int. J. Inf. Technol., vol. 13, no. 2, pp. 741749, 2021.
[21]. Z. Z. Qin, T. W. Leung, Z. Bai, M. Zhang, H. Ye, T. Wang, X. Wang,
[22]. Y. Li, and S. Ruan, “TB detection from chest x-rays for triaging in a high TB-burden setting: An evaluation of five artificial intelligence algorithms,” Lancet Digit. Health, vol. 3, no. 9, pp. e543e554, 2021.
[23]. L. Wang, J. Zhou, W. Pan, L. Zhang, and X. Zhu, “Distinguishing nontuberculous mycobacteria from Mycobacterium TB lung disease from CT images using a DL framework,” Eur. J. Nucl. Med. Mol. Imaging, vol. 48, no. 13, pp. 42934306, 2021.
[24]. K. Munadi, K. Muchtar, N. Maulina, and B. Pradhan, “Image En¬hancement for TB Detection Using DL,” IEEE Access, vol. 8, pp. 217897217907, 2020, doi: 10.1109/ACCESS.2020.3041867.
[25]. R.-I. Chang and Y.-H. Chiu, “A DL-based image processing algo¬rithm for automated TB detection,” J. Inf. Hiding Multimedia Signal Process., vol. 12, no. 1, pp. 1-10, 2021.
[26]. Y. Liu, Y.-H. Wu, Y. Ban, H. Wang, and M.-M. Cheng, “Rethink-ing computer-aided TB diagnosis,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 26462655, 2020.
[27]. L. Ma, Y. Zhang, X. Sun, S. Li, X. Jiang, and Y. Bai, “Developing and verifying automatic detection of active pulmonary TB from multi¬slice spiral CT images based on DL,” J. Xray Sci. Technol., vol. 28, no. 5, pp. 939951, 2020.
[28]. M. I. Grschel, R. Walker, T. J. Scriba, H. P. Boshoff, and W. B. Spann, “GenTB: A user-friendly genome-based predictor for TB resistance powered by ML,” Genome Med., vol. 13, no. 1, p. 138, 2021.
[29]. J.-W. Lin, “Two-stage classification of TB culture diagnosis using convolutional neural network with transfer learning,” presented at the Int. Conf. Inf. Manage., Taiwan, 2021.
[30]. H. H. Rashidi, M. Kalantari, K. Lasfer, N. Arshi, A. Baradaran, and
[31]. N. Kharrazi, “Prediction of TB using an automated ML platform for models trained on synthetic data,” J. Pathol. Inform., vol. 13, no. 100172, p. 10, 2022.
[32]. K. Sethanan, S. Varatharajah, and P. M. Christ, “Computer-aided di¬agnosis using embedded ensemble DL for multiclass drug-resistant TB classification,” Front. Med. (Lausanne), vol. 10, p. 1122222, 2023.
[33]. I. Ahmad and S. Shin, “A perceptual encryption-based image com¬munication system for DL-based TB diagnosis using healthcare cloud services,” Electronics (Basel), vol. 11, no. 16, p. 2514, 2022.
[34]. R. D. J. Samuel and B. R. Kanna, “TB detection system using deep neural networks,” presented at the Int. Conf. Comput. Sci. Eng., India, 2021.
[35]. P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, T. Duan, and A.
[36]. Y. Ng, “CheXaid: DL assistance for physician diagnosis of TB using chest x-rays in patients with HIV,” NPJ Digit. Med., vol. 3, no. 1, p. 115, 2020.
[37]. S. Kouchaki, Y. Yang, T. M. Walker, A. S. Walker, D. J. Wilson, T.
[38]. E. A. Peto, and D. W. Crook, “Application of ML techniques to TB drug resistance analysis,” J. Data Text Mining, vol. 5, no. 2, pp. 67-81, 2020.
[39]. M. Rahman, Y. Cao, X. Sun, B. Li, and Y. Hao, “Deep pre-trained networks as a feature extractor with XGBoost to detect TB from chest X-ray,” Comput. Electr. Eng., vol. 93, no. 107252, p. 107252, 2021.
[40]. S. J. Denholm, H. C. Williams, J. A. Lopez, K. M. Brewster, J. G. Thomas, and R. B. Sweeney, “Predicting bovine TB status of dairy cows from mid-infrared spectral data of milk using DL,” J. Dairy Sci., vol. 103, no. 10, pp. 93559367, 2020.
[41]. P. Msonda, S. A. Uymaz, and S. S. KaraaL´ aß, “Spatial Pyramid Pooling in deep convolutional networks for automatic TB diagnosis,” Trait. Du Signal, vol. 37, no. 6, pp. 10751084, 2020.
[42]. M. Mamalakis, N. Fakotakis, E. Kokotos, K. Papadourakis, and M. Tsiknakis, “DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and TB from X-rays,” Comput. Med. Imaging Graph., vol. 94, no. 102008, p. 102008, 2021.
[43]. S. A. Saif, “TB-image-datasets,” Kaggle, 2019. [Online]. Avail-able: https://www.kaggle.com/datasets/saife245/TB-image-datasets. [Accessed: 1-Jun-2024].
[44]. T. Rahman, A. Khandakar, M. A. Kadir, K. R. Islam, K. F. Islam, Z. B. Mahbub, M. A. Ayari, and M. E. H. Chowdhury, “Reliable Tubercu¬losis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization,” IEEE Access, vol. 8, pp. 191586-191601, 2020.
[45]. M. P. Wolke, “Multidrug-resistant TB CSV dataset,” Kaggle, 2019. [Online]. Available: https://www.kaggle.com/datasets/mpwolke/cusersmarildownloadsmultidrugcsv. [Accessed: 1-Jun-2024].
[2]. M. H. Ali, D. M. Khan, K. Jamal, Z. Ahmad, S. Manzoor, and Z. Khan, “Prediction of multidrug-resistant TB using ML algorithms in SWAT, Pakistan,” J. Healthc. Eng., vol. 2021, p. 2567080, 2021.
[3]. Y. Xie, M. Zhang, Q. Li, Y. Wei, L. Liu, and Z. Huang, “Computer-aided system for the detection of multicategory pulmonary TB in ra-diographs,” J. Healthc. Eng., vol. 2020, p. 9205082, 2020.
[4]. X. Kuang, F. Wang, K. M. Hernandez, Z. Zhang, and R. L. Grossman, “Accurate and rapid prediction of TB drug resistance from genome sequence data using traditional ML algorithms and CNN,” Sci. Rep., vol. 12, no. 1, p. 2427, 2022.
[5]. L. T. Duong, N. H. Le, T. B. Tran, V. M. Ngo, and P. T. Nguyen, “Detection of TB from chest X-ray images: Boosting the performance with vision transformer and transfer learning,” Expert Syst. Appl., vol. 184, no. 115519, p. 115519, 2021.
[6]. S. J. Heo, E. J. Lee, S. H. Kim, Y. Kim, and S. Kang, “DL algorithms with demographic information help to detect TB in chest radiographs in annual workers health examination data,” Int. J. Environ. Res. Pub¬lic Health, vol. 16, no. 2, p. 250, 2019.
[7]. S. Das and M. K. Sanyal, “Machine intelligent diagnostic system (MIDs): An instance of medical diagnosis of TB,” Neural Comput. Appl., vol. 32, no. 19, pp. 1558515595, 2020.
[8]. M. Singh, A. K. Goel, H. Gupta, S. K. Goyal, and A. Jain, “Evolution of ML in TB diagnosis: A review of DL-based medical applications,” Electronics (Basel), vol. 11, no. 17, p. 2634, 2022.
[9]. H. K. Virupakshaiah and N. T R, "Tuberculosis Detection in Chest X-Ray Images Using Deep Learning Techniques," 2025 5th International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), MANDYA, India, 2025, pp. 1-6, doi: 10.1109/ICERECT65215.2025.11376057.
[10]. V. Sharma, Nillmani, S. K. Gupta, and K. K. Shukla, “TB detection in chest X-rays using convolutional neural networks,” Int. J. Comput. Appl., vol. 975, no. 8887, pp. 14, 2020.
[11]. N. P. Nsengiyumva, L. Niyonzima, R. Nyandwi, and J. B. Ntaganda, “Triage of persons with TB symptoms using artificial intelligence-based chest radiograph interpretation: A cost-effectiveness analysis,” Open Forum Infect. Dis., vol. 8, no. 12, p. ofab567, 2021.
[12]. R. Rajakumar, R. S. Uma Maheswari, and S. P. Karuppiah, “TB de¬tection in chest X-ray using Mayfly-algorithm optimized dual-deep-learning features,” J. Xray Sci. Technol., vol. 29, no. 6, 2021.
[13]. A. Iqbal, M. Usman, and Z. Ahmed, “An efficient DL-based frame¬work for TB detection using chest X-ray images,” TB(Edinb.), vol. 136, no. 102234, p. 102234, 2022.
[14]. M. K. Puttagunta and S. Ravi, “Detection of TB based on DL based methods,” J. Phys. Conf. Ser., vol. 1767, no. 1, p. 012004, 2021.
[15]. S. Hansun, A. Argha, S.-T. Liaw, B. G. Celler, and G. B. Marks, “Ma-chine and DL for TB detection on chest X-rays: Systematic literature review,” J. Med. Internet Res., vol. 25, p. e43154, 2023.
[16]. Y. Lee, M. C. Raviglione, and A. Flahault, “Use of digital technology to enhance TB control: Scoping review,” J. Med. Internet Res., vol. 22, no. 2, p. e15727, 2020.
[17]. A. K. Siddiqui and V. K. Garg, "Diagnosis of Pulmonary Tuberculosis through Intelligent Techniques: A Review," 2021 International Conference on Computing Sciences (ICCS), Phagwara, India, 2021, pp. 189-193
[18]. K. C. Santosh, S. Allu, S. Rajaraman, and S. Antani, “Advances in DL for TB screening using chest X-rays: The last 5 years review,” J. Med. Syst., vol. 46, no. 11, p. 82, 2022.
[19]. O. S. Balogun, S. A. Olaleye, M. Mohsin, and P. Toivanen, “Inves-tigating ML methods for TB risk factors prediction: A comparative analysis and evaluation,” J. Comput. Appl., vol. 25, no. 2, 2021.
[20]. O. N. Bridget, R. Prasad, C. Onime, and A. A. Ali, “Drug resistant TB classification using logistic regression,” Int. J. Inf. Technol., vol. 13, no. 2, pp. 741749, 2021.
[21]. Z. Z. Qin, T. W. Leung, Z. Bai, M. Zhang, H. Ye, T. Wang, X. Wang,
[22]. Y. Li, and S. Ruan, “TB detection from chest x-rays for triaging in a high TB-burden setting: An evaluation of five artificial intelligence algorithms,” Lancet Digit. Health, vol. 3, no. 9, pp. e543e554, 2021.
[23]. L. Wang, J. Zhou, W. Pan, L. Zhang, and X. Zhu, “Distinguishing nontuberculous mycobacteria from Mycobacterium TB lung disease from CT images using a DL framework,” Eur. J. Nucl. Med. Mol. Imaging, vol. 48, no. 13, pp. 42934306, 2021.
[24]. K. Munadi, K. Muchtar, N. Maulina, and B. Pradhan, “Image En¬hancement for TB Detection Using DL,” IEEE Access, vol. 8, pp. 217897217907, 2020, doi: 10.1109/ACCESS.2020.3041867.
[25]. R.-I. Chang and Y.-H. Chiu, “A DL-based image processing algo¬rithm for automated TB detection,” J. Inf. Hiding Multimedia Signal Process., vol. 12, no. 1, pp. 1-10, 2021.
[26]. Y. Liu, Y.-H. Wu, Y. Ban, H. Wang, and M.-M. Cheng, “Rethink-ing computer-aided TB diagnosis,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 26462655, 2020.
[27]. L. Ma, Y. Zhang, X. Sun, S. Li, X. Jiang, and Y. Bai, “Developing and verifying automatic detection of active pulmonary TB from multi¬slice spiral CT images based on DL,” J. Xray Sci. Technol., vol. 28, no. 5, pp. 939951, 2020.
[28]. M. I. Grschel, R. Walker, T. J. Scriba, H. P. Boshoff, and W. B. Spann, “GenTB: A user-friendly genome-based predictor for TB resistance powered by ML,” Genome Med., vol. 13, no. 1, p. 138, 2021.
[29]. J.-W. Lin, “Two-stage classification of TB culture diagnosis using convolutional neural network with transfer learning,” presented at the Int. Conf. Inf. Manage., Taiwan, 2021.
[30]. H. H. Rashidi, M. Kalantari, K. Lasfer, N. Arshi, A. Baradaran, and
[31]. N. Kharrazi, “Prediction of TB using an automated ML platform for models trained on synthetic data,” J. Pathol. Inform., vol. 13, no. 100172, p. 10, 2022.
[32]. K. Sethanan, S. Varatharajah, and P. M. Christ, “Computer-aided di¬agnosis using embedded ensemble DL for multiclass drug-resistant TB classification,” Front. Med. (Lausanne), vol. 10, p. 1122222, 2023.
[33]. I. Ahmad and S. Shin, “A perceptual encryption-based image com¬munication system for DL-based TB diagnosis using healthcare cloud services,” Electronics (Basel), vol. 11, no. 16, p. 2514, 2022.
[34]. R. D. J. Samuel and B. R. Kanna, “TB detection system using deep neural networks,” presented at the Int. Conf. Comput. Sci. Eng., India, 2021.
[35]. P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, T. Duan, and A.
[36]. Y. Ng, “CheXaid: DL assistance for physician diagnosis of TB using chest x-rays in patients with HIV,” NPJ Digit. Med., vol. 3, no. 1, p. 115, 2020.
[37]. S. Kouchaki, Y. Yang, T. M. Walker, A. S. Walker, D. J. Wilson, T.
[38]. E. A. Peto, and D. W. Crook, “Application of ML techniques to TB drug resistance analysis,” J. Data Text Mining, vol. 5, no. 2, pp. 67-81, 2020.
[39]. M. Rahman, Y. Cao, X. Sun, B. Li, and Y. Hao, “Deep pre-trained networks as a feature extractor with XGBoost to detect TB from chest X-ray,” Comput. Electr. Eng., vol. 93, no. 107252, p. 107252, 2021.
[40]. S. J. Denholm, H. C. Williams, J. A. Lopez, K. M. Brewster, J. G. Thomas, and R. B. Sweeney, “Predicting bovine TB status of dairy cows from mid-infrared spectral data of milk using DL,” J. Dairy Sci., vol. 103, no. 10, pp. 93559367, 2020.
[41]. P. Msonda, S. A. Uymaz, and S. S. KaraaL´ aß, “Spatial Pyramid Pooling in deep convolutional networks for automatic TB diagnosis,” Trait. Du Signal, vol. 37, no. 6, pp. 10751084, 2020.
[42]. M. Mamalakis, N. Fakotakis, E. Kokotos, K. Papadourakis, and M. Tsiknakis, “DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and TB from X-rays,” Comput. Med. Imaging Graph., vol. 94, no. 102008, p. 102008, 2021.
[43]. S. A. Saif, “TB-image-datasets,” Kaggle, 2019. [Online]. Avail-able: https://www.kaggle.com/datasets/saife245/TB-image-datasets. [Accessed: 1-Jun-2024].
[44]. T. Rahman, A. Khandakar, M. A. Kadir, K. R. Islam, K. F. Islam, Z. B. Mahbub, M. A. Ayari, and M. E. H. Chowdhury, “Reliable Tubercu¬losis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization,” IEEE Access, vol. 8, pp. 191586-191601, 2020.
[45]. M. P. Wolke, “Multidrug-resistant TB CSV dataset,” Kaggle, 2019. [Online]. Available: https://www.kaggle.com/datasets/mpwolke/cusersmarildownloadsmultidrugcsv. [Accessed: 1-Jun-2024].
Published
2026-08-03
How to Cite
Hassan, S., Ahmed, F., Bilal, M., Khalid, K., & Tabassum, S. (2026). Transforming Tuberculosis Care: The Role of Deep Learning Models in MDR-TB Prediction. International Journal of Artificial Intelligence & Mathematical Sciences, 5(1), 21-34. https://doi.org/10.58921/ijaims.v5i1.183
