arXiv cs.CL· Sabah Nushra, Shovan Samanta Turzo, Moinul Hossain, Md Kishor Morol·· 11 小时前AI 评分18
孟加拉语症状疾病预测的泄漏控制结构保持增强与模板感知评估
Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction
AI 导读
研究在含 725 个独特档案、85 种疾病和 172 个二值症状的孟加拉语症状疾病预测基准上，测试仅用训练集的不对称 Bernoulli 扰动增强效果。XGBoost、LightGBM 和 CatBoost 分别提升 18.10、28.45 和 10.09 个百分点，而 Bernoulli Naive Bayes 的最高平均准确率 97.50% 在 Holm 校正后不显著。
正文 · 原文
Abstract: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.
| Comments: | 6 pages, 5 figures, 5 tables |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.41733 [cs.LG] |
| (or arXiv:2610.41733v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41733 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sabah Nushra [view email]
[v1]
Fri, 30 Oct 2026 13:42:56 UTC (65 KB)
来源：arXiv cs.CL · arxiv.org