Metraipolis › archive › dc_e94e2bb33db7

Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction — arXiv:2610.41733

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41733
License (as archived): CC0-1.0
Archived: 2026-11-03T08:05:45.140Z
SHA-256 of the archived text: 5a7e44b56d8c250b608dd63b8b6d049e360193ab28266926df0fe8c565e9a774
Stable URL of this page: https://metraipolis.com/documento/dc_e94e2bb33db7

How to cite

Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction — arXiv:2610.41733 — arXiv (en), https://arxiv.org/abs/2610.41733 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e94e2bb33db7 (Metraipolis archive dc_e94e2bb33db7, sha256 5a7e44b56d8c250b608dd63b8b6d049e360193ab28266926df0fe8c565e9a774)

BibTeX

@misc{dce94e2bb33db7,
  title = {Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction — arXiv:2610.41733},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41733},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e94e2bb33db7; sha256 5a7e44b56d8c250b608dd63b8b6d049e360193ab28266926df0fe8c565e9a774},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41733. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bangla symptom-based disease prediction is commonly evaluated on a small, imbalanced structured benchmark containing many profiles that differ by only one or two symptoms. We test whether train-only asymmetric Bernoulli perturbation improves classification using 725 unique profiles spanning 85 diseases and 172 binary symptoms. Experiments use ten repeated real-profile holdouts and parent-grouped inner cross-validation. The 2 x 2 design separates augmentation from hyperparameter tuning, with exact duplication, random oversampling, class weighting, and SMOTEN as balancing controls. For Bernoulli Naive Bayes (BNB), the gain over tuned raw training does not withstand Holm correction, although BNB attains the highest mean accuracy (97.50%). The boosted-tree models benefit substantially: XGBoost, LightGBM, and CatBoost improve by 18.10, 28.45, and 10.09 percentage points, respectively. A Hamming-distance audit places 91.0% of standard held-out profiles within one symptom bit of the training data. Accuracy decreases on a same-disease 1-bit-purged challenge; nevertheless, XGBoost and LightGBM retain large augmentation gains. We also evaluate robustness to missing and spurious symptoms and the faithfulness of BNB explanations. Overall, Bernoulli perturbation is useful for some model families, but benchmark accuracy should be interpreted together with template proximity.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41733 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:59:53.627Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).