Dynamic Prediction of Treatment Failure in Ocular Tuberculosis Using Machine Learning and Explainable AI

Strategic Insights -

Research from Nanyang Technological University has detailed the application of machine learning approaches to predict treatment failure in ocular tuberculosis. This study, published in Translational Vision Science & Technology, utilized the Collaborative Ocular Tuberculosis Study (COTS) dataset of 836 patients with tubercular uveitis across 27 international eye care centers. The researchers employed nine machine learning models, including XGBoost and Random Forest, to predict treatment failure at six, 12, and 24 months using baseline and longitudinal data.

Key Takeaways:

  • The study evaluated the performance of nine machine learning models to predict treatment failure in ocular tuberculosis, including XGBoost and Random Forest.
  • At 6 months, XGBoost achieved an area under the curve (AUC) of 0.915 ± 0.019 and accuracy of 0.879 ± 0.027.
  • At 12 months, Random Forest outperformed with an AUC of 0.921 ± 0.011 and accuracy of 0.944 ± 0.022.
  • At 24 months, Random Forest maintained high accuracy (0.960 ± 0.029) despite a slight drop in AUC (0.888 ± 0.099).
  • The study demonstrated the potential of machine learning models like XGBoost and Random Forest for early and accurate prediction of treatment failure in ocular tuberculosis.
  • Explainable AI tools were used to enhance clinical interpretability of the models.

Statistics:

  • 836 patients with tubercular uveitis were included in the Collaborative Ocular Tuberculosis Study (COTS) dataset.
  • The study utilized data from 27 international eye care centers.
  • At 6 months, XGBoost achieved an AUC of 0.915 ± 0.019 and accuracy of 0.879 ± 0.027.
  • At 12 months, Random Forest outperformed with an AUC of 0.921 ± 0.011 and accuracy of 0.944 ± 0.022.
  • At 24 months, Random Forest maintained high accuracy (0.960 ± 0.029) despite a slight drop in AUC (0.888 ± 0.099).

Sources:

  • NewsRx. Researchers from Nanyang Technological University Report on Findings in Ocular Tuberculosis (Dynamic Prediction of Treatment Failure in Ocular Tuberculosis Using Machine Learning and Explainable AI). TB & Outbreaks Week. November 4, 2025; p 6437.
  • Translational Vision Science & Technology. Dynamic Prediction of Treatment Failure in Ocular Tuberculosis Using Machine Learning and Explainable AI. Translational Vision Science & Technology, 2025;14(10):31.