The paper introduces MedIDL, a Medical Imaging Disentanglement Learning framework that separates disease-related features from confounding covariates and individual variability in medical images. It achieves this by projecting image features into three orthogonal latent spaces—disease classification, covariate alignment, and a Gaussian head for individual variation—using specialized disentanglement heads. Across seven diverse imaging datasets, MedIDL surpasses state‑of‑the‑art supervised and self‑supervised methods in classification accuracy, and its latent representations and gradient‑based visualizations align with known clinical patterns.
By Shengjie Zhang, Jinglin Zhang, Zhuangzhuang Jiang, Ziqi Yu, Yipin Zhang, Qi Zhang, Xiang Chen, Haibo Yang, Fei Gao, Longbiao Cui, Yuan Zhou, Xiao-Yong Zhang, Alzheimer's Disease Neuroimaging Initiative
arXiv:2609.15285v1 Announce Type: new
Abstract: Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease in which early assessment remains challenging, particularly in low-resou...
By Kadija Abdel Ghader, Emani Babe, Lorenzo Pettinari, Meya Haroune, Sidaty El Hadramy
arXiv:2608. 07385v1 Announce Type: cross Abstract: Learning disentangled representations is a key requirement for developing versatile, general-purpose, and sustainable models in multi-modal wearable computing.
By Ioannis Ziogas, Ensieh Khazaei, Bilal Taha, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis, Dimitrios Hatzinakos
The paper introduces a deep generative model using conditional variational autoencoders to augment vital sign data from healthy individuals so that it mimics patterns of specific clinical conditions. Trained on a publicly available ICU dataset, the model learns the underlying dynamics of ICU data and reshapes healthy data to align with target clinical labels. A proposed distance metric demonstrates that the generated samples are more aligned with intended clinical labels than baseline methods.
By Rafael Pina, Varuna De Silva, Mindula Illeperuma
arXiv:2602. 12542v2 Announce Type: replace-cross Abstract: Deep learning models for clinical event prediction on electronic health records (EHR) often suffer performance degradation when deployed under different data distributions.
By Pengfei Hu, Chang Lu, Feifan Liu, Yue Ning
arXiv:2506. 17182v3 Announce Type: replace Abstract: Disentangled representations separate factors that are shared across conditions from those that are condition-specific.
By Yuli Slavutsky, Ozgur Beker, David Blei, Bianca Dumitrascu
The paper presents a deep denoising autoencoder (DAE) approach for non‑invasive detection of blood flow in arteriovenous fistulas (AVFs) using waveform data processed by a one‑level discrete wavelet transform. The DAE performs dimensionality reduction and reconstruction, producing a latent representation that achieves 93% accuracy in detecting AVF dysfunction and 92% accuracy in identifying patient‑specific characteristics. Lightweight versions of the model can maintain performance on less powerful devices, indicating practical applicability for routine AVF monitoring.
By Li-Chin Chen, Yi-Heng Lin, Li-Ning Peng, Feng-Ming Wang, Yu-Hsin Chen, Po-Hsun Huang, Shang-Feng Yang, Yu Tsao
arXiv:2608. 04193v1 Announce Type: cross Abstract: Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability.
By Xinyu Wang, Yixuan Li, Hanwei Wu, Qincheng Lu, Chi-Kuang Yeh, Xiao-Wen Chang, Ziyang Song
arXiv:2608. 08561v1 Announce Type: new Abstract: In medical applications, raw data is frequently associated with significant privacy concerns, lending particular importance to the encoding of summary statistics from the literature.
By Felix Weitk\"amper, Monchito Avila, Elizabeth Nanjala, Siska, Grace Zawadi
arXiv:2606. 09725v1 Announce Type: new Abstract: Disentanglement, the separation of factors of variation in data using neural networks, remains a long-standing challenge in machine learning.
By Jhonny J. Velasquez Olivera, Christo K. Thomas, Walid Saad
arXiv:2603. 04113v2 Announce Type: replace-cross Abstract: Demographic attributes can be predicted from medical images, raising concerns about bias in clinical AI systems.
By Mehmet Yigit Avci (and for the Alzheimer's Disease Neuroimaging Initiative), Akshit Achara (and for the Alzheimer's Disease Neuroimaging Initiative), Andrew King (and for the Alzheimer's Disease Neuroimaging Initiative), Jorge Cardoso (and for the Alzheimer's Disease Neuroimaging Initiative)
arXiv:2512. 09185v4 Announce Type: replace-cross Abstract: Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment.
By Hao Chen, Rui Yin, Yifan Chen, Qi Chen, Chao Li