Saved in:
Bibliographic Details
Main Authors: Zhou, Yize, Zhang, Jie, Wang, Meijie, Yu, Lun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.05763
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908450285420544
author Zhou, Yize
Zhang, Jie
Wang, Meijie
Yu, Lun
author_facet Zhou, Yize
Zhang, Jie
Wang, Meijie
Yu, Lun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BMDetect: A Multimodal Deep Learning Framework for Comprehensive Biomedical Misconduct Detection
Zhou, Yize
Zhang, Jie
Wang, Meijie
Yu, Lun
Machine Learning
Computation and Language
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.
title BMDetect: A Multimodal Deep Learning Framework for Comprehensive Biomedical Misconduct Detection
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2505.05763