Using Machine Learning Methods to Predict Early Treatment Outcomes for Multidrug-Resistant or Rifampicin-Resistant Tuberculosis to Enhance Patient Cure Rates: Development and Validation of Multiple Models
The ML models based on 2- and 6-month culture conversion could accurately predict treatment outcomes for patients with MDR/RR-TB. ML models, particularly the artificial neural network model, outperformed the logistic regression model in both stability and generalizability and offer a rapid and effective tool for evaluating therapeutic efficacy in the early stages of MDR/RR-TB treatment.
Authors
- Yu Pang (ORCID: https://orcid.org/0000-0001-6803-9807)
- Zi-Long Yang
- Yuanyuan Shang (ORCID: https://orcid.org/0000-0002-3538-7730)
- Cong Yao
- Haobin Kuang (ORCID: https://orcid.org/0009-0003-7254-5149)
- Shanshan Li (ORCID: https://orcid.org/0000-0003-4475-4536)
- Liang Li (ORCID: https://orcid.org/0000-0001-5212-5890)
- Yu Dong
- Fuzhen Zhang (ORCID: https://orcid.org/0000-0002-5056-3886)
- Weicong Ren (ORCID: https://orcid.org/0009-0006-1312-1110)
- X. P. Geng
- Ruichao Liu (ORCID: https://orcid.org/0009-0003-4214-5988)
Institutions
- Shandong University (CN)
- Sun Yat-sen University (CN)
- Capital Medical University (CN)
- Beijing Chest Hospital (CN)
- Guangzhou Chest Hospital (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-09-22
- DOI
- https://doi.org/10.2196/69998
- Citations
- 3
- Primary Topic
- Tuberculosis Research and Epidemiology
- Type
- article
- Field-Weighted Citation Impact
- 4.19