Predicting Drug-Resistant Tuberculosis Treatment Outcomes: A Leakage-Controlled Evaluation of Topological Data Analysis Augmentation
- 1University of Johannesburg
Abstract
BackgroundWe asked what topological structure adds to a clinical prediction model and how that addition should be measured. Drug-resistant tuberculosis (DR-TB) treatment outcome prediction is the testbed. The contribution is an evaluation design and a bounded null result.
MethodsCross-sectional records for 9210 patients from the NIAID TB Portals programme were collated to one row per patient by worst-case aggregation, giving a 99-feature clinical schema. We derived two topological representations. A Mapper graph, built on a UMAP lens over a Gower dissimilarity, supplied four neighbourhood-position features. Local Vietoris-Rips persistent homology on each patients 26-point neighbourhood supplied degree-0 and degree-1 summaries, vectorised by the best of thirteen catalogued methods. We compared five feature configurations across four classifiers in a pipeline in which every topological step is fitted inside the training partition. A sealed test lockbox of 1776 patients, 463 of them with adverse outcomes, was opened once. We compared discrimination by the area under the receiver operating characteristic curve (AUROC) using paired DeLong tests with Bonferroni correction (corrected threshold 0.0125).
ResultsNo topologically augmented configuration meaningfully improved lockbox AUROC over the clinical-only baseline under any classifier. The best AUROC was 0.7548, achieved by the baseline with XGBoost. Across all sixteen comparisons the upper 95% confidence limit never exceeded +0.014 AUROC. Five comparisons met the corrected threshold. Four favoured the baseline, and one, under the support vector machine, favoured the augmented model by a negligible +0.0005 AUROC. The same features supported neighbourhood-based risk stratification and revealed variation in adverse-outcome composition across patient neighbourhoods: adverse-outcome purity ranged from 5.9% to 30.5% across the fifteen largest Mapper nodes, stably under resampling.
ConclusionsThe findings support a complementary framing of topological data analysis in clinical prediction. Topological features are best understood not as replacements for clinical predictors but as an analytical lens that reveals geometric structure in the patient population not captured by the clinical feature representation alone.
Related
- Crestal Versus Lateral Window Approaches for Maxillary Sinus Floor Augmentation: A Systematic Review and Meta-Analysis of Randomized Controlled Trials
- Shear-Wave Elastography for Predicting the Occurrence and Assessing the Severity of Capsular Contracture After Implant-Based Breast Augmentation and Reconstruction: A Review of the Evidence
- A mixed-methods evaluation of a language model-powered breast cancer note augmentation tool for patients
- Vitamin D supplementation to prevent tuberculosis infection and disease: systematic review and individual participant data meta-analysis of randomised controlled trials
- Effectiveness of integrated tuberculosis and depression treatment led by non-specialist health workers versus standard care among persons with tuberculosis in a low-resource setting: A quasi-experimental non-randomized controlled trial
BibTeX
@misc{mutakwa2026predicting,
title = {{Predicting Drug-Resistant Tuberculosis Treatment Outcomes: A Leakage-Controlled Evaluation of Topological Data Analysis Augmentation}},
author = {D. T. Mutakwa and M. V. Visaya and F. Chirove},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.23.26366286},
url = {https://www.medrxiv.org/content/10.64898/2026.10.23.26366286v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Predicting Drug-Resistant Tuberculosis Treatment Outcomes: A Leakage-Controlled Evaluation of Topological Data Analysis Augmentation
AU - D. T. Mutakwa
AU - M. V. Visaya
AU - F. Chirove
PY - 2026
DA - 2026/10/23
PB - medRxiv
DO - 10.64898/2026.10.23.26366286
UR - https://www.medrxiv.org/content/10.64898/2026.10.23.26366286v1
AB - BackgroundWe asked what topological structure adds to a clinical prediction model and how that addition should be measured. Drug-resistant tuberculosis (DR-TB) treatment outcome prediction is the testbed. The contribution is an evaluation design and a bounded null result. MethodsCross-sectional records for 9210 patients from the NIAID TB Portals programme were collated to one row per patient by worst-case aggregation, giving a 99-feature clinical schema. We derived two topological representations. A Mapper graph, built on a UMAP lens over a Gower dissimilarity, supplied four neighbourhood-position features. Local Vietoris-Rips persistent homology on each patients 26-point neighbourhood supplied degree-0 and degree-1 summaries, vectorised by the best of thirteen catalogued methods. We compared five feature configurations across four classifiers in a pipeline in which every topological step is fitted inside the training partition. A sealed test lockbox of 1776 patients, 463 of them with adverse outcomes, was opened once. We compared discrimination by the area under the receiver operating characteristic curve (AUROC) using paired DeLong tests with Bonferroni correction (corrected threshold 0.0125). ResultsNo topologically augmented configuration meaningfully improved lockbox AUROC over the clinical-only baseline under any classifier. The best AUROC was 0.7548, achieved by the baseline with XGBoost. Across all sixteen comparisons the upper 95% confidence limit never exceeded +0.014 AUROC. Five comparisons met the corrected threshold. Four favoured the baseline, and one, under the support vector machine, favoured the augmented model by a negligible +0.0005 AUROC. The same features supported neighbourhood-based risk stratification and revealed variation in adverse-outcome composition across patient neighbourhoods: adverse-outcome purity ranged from 5.9% to 30.5% across the fifteen largest Mapper nodes, stably under resampling. ConclusionsThe findings support a complementary framing of topological data analysis in clinical prediction. Topological features are best understood not as replacements for clinical predictors but as an analytical lens that reveals geometric structure in the patient population not captured by the clinical feature representation alone.
ER -