BMDetect: A Multimodal Deep Learning Framework for Comprehensive Biomedical Misconduct Detection

TL;DR

BMDetect is a comprehensive multimodal deep learning framework that combines journal metadata, semantic embeddings, and textual attributes to effectively detect biomedical research misconduct, outperforming existing methods.

Contribution

It introduces a novel multimodal fusion approach and a large-scale benchmark dataset for biomedical misconduct detection, enhancing detection accuracy and interpretability.

Findings

Achieves 74.33% AUC in misconduct detection

Outperforms single-modality baselines by 8.6%

Demonstrates transferability across biomedical subfields

Abstract

Academic misconduct detection in biomedical research remains challenging due to algorithmic narrowness in existing methods and fragmented analytical pipelines. We present BMDetect, a multimodal deep learning framework that integrates journal metadata (SJR, institutional data), semantic embeddings (PubMedBERT), and GPT-4o-mined textual attributes (methodological statistics, data anomalies) for holistic manuscript evaluation. Key innovations include: (1) multimodal fusion of domain-specific features to reduce detection bias; (2) quantitative evaluation of feature importance, identifying journal authority metrics (e.g., SJR-index) and textual anomalies (e.g., statistical outliers) as dominant predictors; and (3) the BioMCD dataset, a large-scale benchmark with 13,160 retracted articles and 53,411 controls. BMDetect achieves 74.33% AUC, outperforming single-modality baselines by 8.6%, and demonstrates transferability across biomedical subfields. This work advances scalable, interpretable tools for safeguarding research integrity.