Author name cluster

Zan Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

EAAI Journal 2026 Journal Article

A unified neural framework for long-term time series forecasting and granger-style causal analysis

Yanan Zhang
Bo Feng
Zan Chen
Shen Zhang

Reliable long-term time series forecasting (LTSF) in complex multivariate systems requires both effective long-range sequence modeling and informative analysis of cross-variable dependencies. Existing methods usually optimize these goals separately, leading to a mismatch between predictive performance and causal interpretability. To address this issue, we propose Mamba with Kolmogorov-Arnold Network and Jacobian Regularization (MKJR), a unified framework for mutual reinforcement between LTSF and Granger-style causal analysis. MKJR combines a Kolmogorov-Arnold Network (KAN)-based encoder-decoder with an asymmetric bidirectional dual-stream Mamba backbone. The KAN modules perform variable-wise nonlinear embedding and forecasting readout, while exposing encoder-side source-lag structural priors and decoder-side target-aware readout preferences. Built on this representation layer, the dual-stream Mamba captures fine-grained local temporal signatures and broader cross-variable dependency patterns within the same predictor. During training, MKJR uses a matrix-free random-projection Jacobian regularizer to constrain local sensitivity and encourage smoother, more target-relevant lagged predictive dependencies. During evaluation, MKJR fuses encoder-side priors, decoder-side readout preference, and Jacobian sensitivity into lag-resolved Granger-style dependence scores for graph recovery. In this way, better predictive representations provide more reliable dependence evidence, while dependence-aware regularization suppresses diffuse sensitivities and improves forecasting robustness. The resulting design is well suited to complex nonlinear multivariate systems with long forecasting horizons and distribution shifts. Experiments on multiple datasets across forecasting and causal analysis settings show that MKJR achieves the best overall performance and remains highly competitive on individual benchmarks, demonstrating practical value in complex industrial settings.

Details DOI

JBHI Journal 2026 Journal Article

DiffM 4 RI: A Latent Diffusion Model With Modality Inpainting for Synthesizing Missing Modalities in MRI Analysis

Wen Ye
Zhetao Guo
Yuxiang Ren
Yi Tian
Yushi Shen
Zan Chen
Junjun He
Jing Ke

Foundation Models (FMs) have shown great promise for multimodal medical image analysis such as Magnetic Resonance Imaging (MRI). However, certain MRI sequences may be unavailable due to various constraints, such as limited scanning time, patient discomfort, or scanner limitations. The absence of certain modalities can hinder the performance of FMs in clinical applications, making effective missing modality imputation crucial for ensuring their applicability. Previous approaches, including generative adversarial networks (GANs), have been employed to synthesize missing modalities in either a one-to-one or many-to-one manner. However, these methods have limitations, as they require training a new model for different missing scenarios and are prone to mode collapse, generating limited diversity in the synthesized images. To address these challenges, we propose DiffM 4 RI, a diffusion model for many-to-many missing modality imputation in MRI. DiffM 4 RI innovatively formulates the missing modality imputation as a modality-level inpainting task, enabling it to handle arbitrary missing modality situations without the need for training multiple networks. Experiments on the BraTs datasets demonstrate DiffM 4 RI can achieve an average SSIM improvement of 0. 15 over MustGAN, 0. 1 over SynDiff, and 0. 02 over VQ-VAE-2. These results highlight the potential of DiffM 4 RI in enhancing the reliability of FMs in clinical applications.

Details DOI

AIIM Journal 2025 Journal Article

A survey for large language models in biomedicine

Chong Wang
Mengyao Li
Junjun He
Zhongruo Wang
Erfan Darzi
Zan Chen
Jin Ye
Tianbin Li

Recent breakthroughs in large language models (LLMs) offer unprecedented natural language understanding and generation capabilities. However, existing surveys on LLMs in biomedicine often focus on specific applications or model architectures, lacking a comprehensive analysis that integrates the latest advancements across various biomedical domains. This review, based on an analysis of 484 publications sourced from databases including PubMed, Web of Science, and arXiv, provides an in-depth examination of the current landscape, applications, challenges, and prospects of LLMs in biomedicine, distinguishing itself by focusing on the practical implications of these models in real-world biomedical contexts. Firstly, we explore the capabilities of LLMs in zero-shot learning across a broad spectrum of biomedical tasks, including diagnostic assistance, drug discovery, and personalized medicine, among others, with insights drawn from 137 key studies. Then, we discuss adaptation strategies of LLMs, including fine-tuning methods for both uni-modal and multi-modal LLMs to enhance their performance in specialized biomedical contexts where zero-shot fails to achieve, such as medical question answering and efficient processing of biomedical literature. Finally, we discuss the challenges that LLMs face in the biomedicine domain including data privacy concerns, limited model interpretability, issues with dataset quality, and ethics due to the sensitive nature of biomedical data, the need for highly reliable model outputs, and the ethical implications of deploying AI in healthcare. To address these challenges, we also identify future research directions of LLM in biomedicine including federated learning methods to preserve data privacy and integrating explainable AI methodologies to enhance the transparency of LLMs. As this field of LLM rapidly evolves, continued research and development are essential to fully harness the capabilities of LLMs in biomedicine while ensuring their responsible and effective deployment.

Details DOI

EAAI Journal 2025 Journal Article

Granger-guided reduced dual attention long short-term memory for travel demand forecasting during coronavirus disease 2019

Yanan Zhang
Zan Chen
Bo Feng
Xueliang Sui
Shen Zhang

The spread of Coronavirus disease 2019 (COVID-19) is closely related to residents’ travel. Quantities of studies have explored the spread of the epidemic impacted by the travel patterns. However, the researches of changes in residents' travel demand during the evolution of the epidemic are still insufficient. In particular, the lag effect of the epidemic on residents' travel demand has not been fully studied. This paper proposes a novel model named Granger-guided reduced dual attention long short-term memory (GRDA-LSTM) to predict changes in residents' travel demand under the impact of COVID-19. The contribution to artificial intelligence lies in leveraging Granger causality tests to enhance sensitivity to trend changes, incorporating a dual attention mechanism to improve forecasting performance, and utilizing channel reduction to boost efficiency. Experiments have proved that GRDA-LSTM is superior to existing Granger causality-integrated deep learning models. It effectively handles the abruptness and uncertainty of epidemic data, improves prediction accuracy, and meets rapid prediction requirements. The contribution in practical engineering applications is that the research findings not only provide more scientific guidance for traffic management practices in response to future comparable public health crises, but also broaden the research perspective on the impact of long-term public health events on transportation systems.

Details DOI

YNICL Journal 2023 Journal Article

Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies

Santiago Aja-Fernández
Carmen Martín-Martín
Álvaro Planchuelo-Gómez
Abrar Faiyaz
Md Nasir Uddin
Giovanni Schifitto
Abhishek Tiwari
Saurabh J. Shigwan

The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients. The number of gradient directions had an impact on white matter analysis results, with statistically significant differences between groups being drastically reduced when using 21 gradient directions instead of the original 61. Fourteen teams from different institutions were tasked to use DL to enhance three diffusion metrics (FA, AD and MD) calculated from data acquired with 21 gradient directions and a b-value of 1000 s/mm2. The goal was to produce results that were comparable to those calculated from 61 gradient directions. The results were evaluated using both standard image quality metrics and Tract-Based Spatial Statistics (TBSS) to compare episodic and chronic migraine patients. The study results suggest that while most DL techniques improved the ability to detect statistical differences between groups, they also led to an increase in false positive. The results showed that there was a constant growth rate of false positives linearly proportional to the new true positives, which highlights the risk of generalization of AI-based tasks when assessing diverse clinical cohorts and training using data from a single group. The methods also showed divergent performance when replicating the original distribution of the data and some exhibited significant bias. In conclusion, extreme caution should be exercised when using AI methods for harmonization or synthesis in clinical studies when processing heterogeneous data in clinical studies, as important information may be altered, even when global metrics such as structural similarity or peak signal-to-noise ratio appear to suggest otherwise.

Details DOI