Clinically Constrained Multi-Stage Architecture for Integrated Tuberculosis Risk, Drug-Resistance and Severity Assessment
DOI:
https://doi.org/10.68337/cpsm.v1.i1.2026-001Keywords:
Tuberculosis, clinical decision support system, machine learning, MDR-TB risk, disease severity prediction, healthcare AIAbstract
Tuberculosis (TB) remains a major global health burden because of high infection and mortality rates, delays in diagnosis, the emergence of drug-resistant strains, and the wide variation in how the disease presents. Diagnosis of TB, estimation of the risk of multidrug resistance (MDR), and early identification of patients with severe illness are usually carried out as separate tasks. This study proposes a clinical decision support system that detects TB, estimates MDR-TB risk, and grades disease severity through a single multi-stage pipeline, with each stage's output checked against rules set by clinicians. The system was evaluated with stratified 5-fold cross-validation on harmonized public clinical datasets. It achieved an area under the receiver operating characteristic curve (AUROC) of 0.91 for TB detection and 0.83 for MDR-TB risk estimation, and a quadratic weighted kappa (QWK) of 0.74 for severity grading, outperforming logistic regression, random forest, and multi-task neural network baselines on all three tasks. The results indicate that a unified, explainable decision support system is a feasible and practical tool for the combined assessment of patients with TB.
References
[1] Sameeullah Memon, Shabana Bibi, and Guozhong He, "Integration of AI and ML in tuberculosis (TB) management: From diagnosis to drug discovery," Diseases, vol. 13, no. 6, Art. no. 184, 2025, doi: 10.3390/diseases13060184.
[2] Shuanglin Gu, Yichen Guo, Han Jiang, Chen Yang, Tengyue Li, Xiuchang Ma, Wenxian Qian, Zihao Liang, Zheng Hu, Apeng Chen, Yi Zeng, and Changhua Yi, "Machine learning of immune-related laboratory indicators enables discrimination between pulmonary and extrapulmonary tuberculosis," Front. Med., vol. 12, Art. no. 1712073, 2025, doi: 10.3389/fmed.2025.1712073.
[3] Joseph Baruch Baluku, Priscilla Sheilla Apolot, Brenda Namanda, Sharon Namiiro, Shamim Katusabe, Diana Karungi, Reagan Nkonge, Mary Madalen Angut, Jasper Nidoi, Robinah Nalwanga, Charles Mondo, Emmanuel Seremba, and Charles Kabugo, "A predictive score for early in-patient tuberculosis mortality: A case-control study," J. Clin. Tuberc. Other Mycobact. Dis., vol. 37, Art. no. 100487, 2024, doi: 10.1016/j.jctube.2024.100487.
[4] Pattama Saisudjarit, Surasak Saokaew, Acharaporn Duangjai, Anurak Prasatkhetragarn, Sukrit Kanchanasurakit, and Pochamana Phisalprapa, "Development and validation of clinical prediction score for mortality in tuberculosis patients," Narra J., vol. 5, no. 2, Art. no. e1701, 2025, doi: 10.52225/narra.v5i2.1701.
[5] Wenting Zhao, Pei Sun, Wei Li, and Linping Shang, "Machine learning-based prediction model for multidrug-resistant organisms infections: Performance evaluation and interpretability analysis," Infect. Drug Resist., vol. 18, pp. 2255-2269, 2025, doi: 10.2147/IDR.S459830.
[6] Yaxi Wang, Gang Wang, Yuxiao Zhao, Cheng Wang, Chen Chen, Yaoyao Ding, Jing Lin, Jingjing You, Silong Gao, and Xufeng Pang, "A deep learning model for predicting multidrug-resistant organism infection in critically ill patients," J. Intensive Care, vol. 11, Art. no. 49, 2023, doi: 10.1186/s40560-023-00695-y.
[7] Liane S. Canas, Trinh H. K. Dong, Daniel Beasley, Joseph Donovan, Jon O. Cleary, Richard Brown, Nguyen Thuy Thuong Thuong, Phu Hoan Nguyen, Ha Thi Nguyen, Reza Razavi, Sebastien Ourselin, Guy E. Thwaites, and Marc Modat, "Computer-aided prognosis of tuberculous meningitis combining imaging and non-imaging data," Sci. Rep., vol. 14, Art. no. 17581, 2024, doi: 10.1038/s41598-024-68308-8.
[8] Komal Saxena, S. Shyni Carmel Mary, Prolay Ghosh, Chinnem Rama Mohan, Mohd Naved, and Mukesh Madanan, "Predicting multi-drug resistant tuberculosis using machine learning on genomic and clinical data," Indian J. Tuberc., vol. 72, suppl. 3, pp. S99-S105, 2025, doi: 10.1016/j.ijtb.2025.11.013.
[9] Bright G. Akwaronwu, Folasade Y. Ayankoya, Shade O. Kuyoro, Innocent Uche Akwaronwu, and Oluwabamise Joseph Adeniyi, "Machine learning for predicting drug resistance in tuberculosis: A systematic review of model performance and clinical applications," Big Data Min. Anal., vol. 9, no. 1, pp. 314-337, 2026, doi: 10.26599/BDMA.2025.9020063.
[10] Ankita Pal and Debasisa Mohanty, "Machine learning-based approach for identification of new resistance associated mutations from whole genome sequences of Mycobacterium tuberculosis," Bioinform. Adv., vol. 5, no. 1, Art. no. vbaf050, 2025, doi: 10.1093/bioadv/vbaf050.
Downloads
Published
Versions
- 2026-10-01 (2)
- 2026-09-30 (1)
Conference Proceedings Volume
Section
Categories
License
Copyright (c) 2026 The Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in Conference Proceedings in Science and Management are made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain copyright in their work and grant the journal first publication rights. Readers are free to share and adapt the published material for any purpose, including commercial use, provided appropriate credit is given to the author, a link to the license is provided, and any changes are indicated.
