{
  "abstract": "Relapse after apparently successful tuberculosis (TB) therapy remains difficult to predict, and how relapse risk evolves throughout treatment remains unclear. Using harmonised clinical data from two Phase 3 trials (2,918 participants), we performed time-resolved prediction of end-of-therapy (EOT) outcomes and post-treatment relapse by training models using tabular data at monthly intervals from baseline to therapy end. Prediction of EOT outcomes improved after month 3 (ROC-AUC up to 0.84), driven by sputum-smear and solid culture. In contrast, relapse prediction among participants with favourable EOT outcomes and completed follow-up improved only modestly through month 3 (ROC-AUC 0.58-0.63) before declining, with age, sex, clinical symptoms and bacterial burden contributing most strongly to prediction. Models trained on large language model-derived embeddings, a more flexible representation of the same variables, matched tabular relapse models in performance throughout therapy, and outperformed tabular EOT outcome models at months 3 and 4 ({Delta}ROC-AUC: 0.12 and 0.14), with longitudinal modelling and sparse variable inclusion only improving relapse prediction at months 4-6 ({Delta}ROC-AUC: 0.09, 0.19 and 0.12), however with reduced interpretability. Models incorporating data after baseline provided incremental improvements in post-treatment relapse risk stratification compared with baseline cavitation and sputum smear alone (4-month relapse-free survival: 94.8%/78.5% for model-derived low/high risk groups, vs. 91.4%/82.9% for baseline easy-/hard-to-treat groups). Overall, these findings suggest that while routine clinical data collected after baseline can improve post-treatment risk stratification, it offers limited predictive value for relapse, underscoring the need for relapse-specific biomarkers.",
  "abstract_shown": true,
  "affiliations": [
    "Helmholtz Munich"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "D. Garger"
    },
    {
      "name": "J. H. Burks"
    },
    {
      "name": "N. I. Paton"
    },
    {
      "name": "D. J. Sloan"
    },
    {
      "name": "G. Maher-Edwards"
    },
    {
      "name": "F. Theis"
    },
    {
      "name": "M. P. Menden"
    },
    {
      "affs": [
        0
      ],
      "name": "F. P. Casale"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cknzgtfnp1hb8.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.15.26362605",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.15.26362605v1.full",
  "id": "cknzgtfnp1hb8",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.15.26362605v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "infectious diseases"
    ],
    [
      "openalex",
      "2725|Tuberculosis Research and Epidemiology"
    ]
  ],
  "openalex": "W7213396389",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.15.26362605v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cknzgtfnp1hb8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:45Z",
      "native_id": "10.64898/2026.09.15.26362605",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.15.26362605v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:infectious diseases",
      "subfield": "infectious-disease"
    }
  ],
  "title": "Time-resolved predictability of end-of-therapy outcome and relapse after cure in Phase 3 tuberculosis trials",
  "title_text": "Time-resolved predictability of end-of-therapy outcome and relapse after cure in Phase 3 tuberculosis trials",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:45Z",
  "url": "https://research.draconitic.com/paper/cknzgtfnp1hb8",
  "venue": "medRxiv",
  "versions": []
}