Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance

• URL: http://arxiv.org/abs/2605.23453v1
• Date: Fri, 22 May 2026 10:08:16 GMT
• Title: Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance
• Abstract summary: We re-evaluated prior migraine classification studies, correcting for data leakage and metric bias.<n>We introduced (i) a clinically motivated aggregation of two hemiplegic subtypes following ICHD-3 1.2.3, (ii) a class-dependent hybrid augmentation strategy that assigns generation methods based on per-class sample size, and (iii) the concept of fidelity asymmetry.<n>Experiments were performed on a dataset of 400 patients across seven migraine subtypes under a two-stage protocol.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We conducted a reproducibility-oriented re-evaluation of prior migraine classification studies, correcting for data leakage and metric bias. We then introduced (i) a clinically motivated aggregation of two hemiplegic subtypes following ICHD-3 §1.2.3, (ii) a class-dependent hybrid augmentation strategy that assigns generation methods based on per-class sample size, and (iii) the concept of fidelity asymmetry, motivating proportionally constrained growth as an alternative to full class balance. Experiments were performed on a dataset of 400 patients across seven migraine subtypes under a two-stage protocol, including the six-class configuration described above. Models were evaluated using stratified 5-fold cross-validation with macro-averaged F1 as the primary metric. Correcting methodological flaws reduces previously inflated performance estimates, with the corrected macro-F1 baseline standing at 0.71. The proposed framework consistently outperformed individual augmenters in macro-F1 averaged across the eight evaluated classifiers (0.862 vs. 0.836 for Gaussian Copula, 0.815 for CTGAN, and 0.801 for the no-augmentation baseline), and achieved its peak result of 0.914 with FT-Transformer under proportional augmentation. The no-augmentation FT-Transformer baseline (0.896) shows that, at the per-classifier ceiling, clinically motivated class aggregation accounts for most of the absolute improvement; the framework's principal measurable contribution is the gain in average robustness across classifiers, highlighting the dominant role of problem formulation.

Related papers

• CaresAI at SMM4H-HeaRD 2026: Predicting TNM Staging [2.7998963147546143]
  This study aims to predict Tumor, Node, and Metastasis (TNM) stage labels independently, with the Cancer Genome Atlas (TCGA) pathology report as the sixth shared task of SMM4H-HeaRD 2026.<n>We explore both classical and deep learning approaches using Term Frequency-Inverse Document Frequency (TF-IDF) features and embeddings from ClinicalBERT, BioBERT, and PubMedBERT.<n>Our results show that individual embeddings perform similarly to the TNM label classification, while their combination improves its predictive ability.
  arXiv  Detail & Related papers  (2026-07-03T16:25:35Z)
• A Novel Machine Learning Approach for Central Nervous System Tumor Classification from DNA Methylation [0.0]
  NA methylation profiling has become a powerful approach for central nervous system ( CNS) tumor classification.<n>We propose a novel and methodologically rigorous machine-learning approach for methylation-based CNS tumor classification.<n>Our results show that the proposed model consistently outperforms the previous state of the art across evaluation settings.
  arXiv  Detail & Related papers  (2026-07-01T16:57:58Z)
• Resource-Conscious Modeling for Next- Day Discharge Prediction Using Clinical Notes [39.44014654945035]
  Timely discharge prediction is essential for optimizing bed turnover and resource allocation in elective spine surgery units.<n>This study evaluates the feasibility of lightweight, fine-tuned large language models (LLMs) and traditional text-based models for predicting next-day discharge.
  arXiv  Detail & Related papers  (2026-04-03T22:42:50Z)
• Quantum-Inspired Geometric Classification with Correlation Group Structures and VQC Decision Modeling [0.5039813366558307]
  We propose a geometry-driven quantum-inspired classification framework that integrates Correlation Group Structures (CGR), compact SWAP-test-based overlap estimation, and selective variational quantum decision modelling.<n>CGR organizes features into anchor-centered correlation neighbourhoods, generating nonlinear, correlation-weighted representations.<n>On the Credit Card Fraud dataset (0.17% prevalence), the Delta + VQC pipeline achieves approximately 0.85 minority recall at an alert rate of approximately 1.31%, with ROC-AUC 0.9249 and PR-AUC 0.3251 under full-dataset evaluation.
  arXiv  Detail & Related papers  (2026-04-02T11:50:29Z)
• Automated Identification of Incidentalomas Requiring Follow-Up: A Multi-Anatomy Evaluation of LLM-Based and Supervised Approaches [5.958100741754613]
  We evaluated large language models (LLMs) against supervised baselines for fine-grained, lesion-level detection of incidentalomas.<n>We introduced a novel inference strategy using lesion-tagged inputs and anatomy-aware prompting to ground model reasoning.<n>The anatomy-informed GPT-OSS-20b model achieved the highest performance, yielding an incidentaloma-positive macro-F1 of 0.79.
  arXiv  Detail & Related papers  (2025-12-05T08:49:57Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• MeCaMIL: Causality-Aware Multiple Instance Learning for Fair and Interpretable Whole Slide Image Diagnosis [40.3028468133626]
  Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology.<n>textbfMeCaMIL, a causality-aware MIL framework, explicitly models demographic confounders through structured causal graphs.<n>MeCaMIL achieves superior fairness -- demographic disparity variance drops by over 65% relative reduction on average across attributes.
  arXiv  Detail & Related papers  (2025-11-14T06:47:21Z)
• Normal and Atypical Mitosis Image Classifier using Efficient Vision Transformer [0.5536078880492113]
  We tackle atypical versus normal mitosis classification in the MIDOG 2025 challenge using EfficientViT-L2.<n>A unified dataset of 13,938 nuclei from seven cancer types was used, with atypical mitoses comprising 15.<n>This model achieved balanced accuracy of 0.859, ROC AUC of 0.942, and raw accuracy of 0.85, demonstrating competitive and well-balanced performance across metrics.
  arXiv  Detail & Related papers  (2025-08-28T23:45:06Z)
• Uncertainty-Aware Genomic Classification of Alzheimer's Disease: A Transformer-Based Ensemble Approach with Monte Carlo Dropout [0.0]
  Alzheimer's disease (AD) is genetically complex, complicating genomic data.<n>We developed a transformer-based ensemble model (TrUENet) using Monte Carlo Dropout for uncertainty estimation.
  arXiv  Detail & Related papers  (2025-05-31T18:20:49Z)
• Predicting Length of Stay in Neurological ICU Patients Using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [49.1574468325115]
  This study explores multiple ML approaches for predicting LOS in ICU specifically for the patients with neurological diseases based on the MIMIC-IV dataset.<n>The evaluated models include classic ML algorithms (K-Nearest Neighbors, Random Forest, XGBoost and CatBoost) and Neural Networks (LSTM, BERT and Temporal Fusion Transformer)
  arXiv  Detail & Related papers  (2025-05-23T14:06:42Z)
• CIMIL-CRC: a clinically-informed multiple instance learning framework for patient-level colorectal cancer molecular subtypes classification from H\&E stained images [42.771819949806655]
  We introduce CIMIL-CRC', a framework that solves the MSI/MSS MIL problem by efficiently combining a pre-trained feature extraction model with principal component analysis (PCA) to aggregate information from all patches. We assessed our CIMIL-CRC method using the average area under the curve (AUC) from a 5-fold cross-validation experimental setup for model development on the TCGA-CRC-DX cohort.
  arXiv  Detail & Related papers  (2024-01-29T12:56:11Z)
• Balanced Classification: A Unified Framework for Long-Tailed Object Detection [74.94216414011326]
  Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. We introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution. BACL consistently achieves performance improvements across various datasets with different backbones and architectures.
  arXiv  Detail & Related papers  (2023-08-04T09:11:07Z)
• Vision Transformers for femur fracture classification [59.99241204074268]
  The Vision Transformer (ViT) was able to correctly predict 83% of the test images. Good results were obtained in sub-fractures with the largest and richest dataset ever.
  arXiv  Detail & Related papers  (2021-08-07T10:12:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.