Journal article · 2026 · Open access

Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data

Yi Zhang, Zhang Cz, Zijian Li, Tianxiang Xu, Kunyu Zhang, Zhan Gao, Meinuo Li, Xiaohan Zhang, Qichao Qi, Bing Chen

IEEE Transactions on Consumer Electronics, 72(3), 6681–6690 · Published 4 March 2026 · DOI 10.1109/tce.2026.3670687

Open PDFView at the publisherCite this paper

In brief

“Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data” is a 2026 journal article by Yi Zhang and 9 co-authors, published in IEEE Transactions on Consumer Electronics. OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
0
References
45
Authors
10

Abstract

Large language models (LLMs) exhibit exceptional performance across diverse domains, yet their propensity to memorise training data poses substantial privacy risks, particularly within sensitive healthcare contexts where medical data is often imperfect, insufficiently labelled, or contains privacy-sensitive patient information. Here, we present a hierarchical dual-strategy framework for selective knowledge unlearning in medical LLMs that enables precise removal of specialised knowledge whilst preserving fundamental medical competencies, specifically addressing challenges in biomedical and healthcare intelligence using imperfect data. Our approach synergistically integrates geometric-constrained gradient updates, which selectively modulate parameters encoding target knowledge while safeguarding essential capabilities, with concept-aware token-level interventions that systematically distinguish between preservation-critical and unlearning-targeted tokens through a unified four-level medical concept hierarchy. Through comprehensive evaluation on the MedMCQA dataset targeting surgical knowledge removal, and cross-domain validation on the MHQA dataset encompassing anxiety, depression, trauma, and obsessive-compulsive disorder domains, we demonstrate that our method achieves superior selective unlearning performance (82.7% forgetting rate, 88.5% knowledge preservation) compared to existing approaches. Notably, our framework maintains robust privacy guarantees while requiring modification of only 0.1% of model parameters, establishing a paradigm for privacy-preserving medical AI systems that addresses regulatory compliance, hospital auditability, and ethical imperatives in clinical research environments. This work contributes to advancing biomedical and healthcare intelligence by providing an effective solution for auditing and managing imperfect and privacy-sensitive medical data in real-world clinical applications.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Zhang, Y., Cz, Z., Li, Z., Xu, T., Zhang, K., Gao, Z., Li, M., Zhang, X., Qi, Q., & Chen, B. (2026). Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data. IEEE Transactions on Consumer Electronics, 72(3), 6681–6690. https://doi.org/10.1109/tce.2026.3670687

MLA 9

Zhang, Yi, et al. “Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data.” IEEE Transactions on Consumer Electronics, vol. 72, no. 3, 2026, pp. 6681–6690. https://doi.org/10.1109/tce.2026.3670687.

Chicago

Zhang, Yi, Zhang Cz, Zijian Li, Tianxiang Xu, Kunyu Zhang, Zhan Gao, Meinuo Li, Xiaohan Zhang, Qichao Qi, and Bing Chen. 2026. “Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data.” IEEE Transactions on Consumer Electronics 72 (3): 6681–6690. https://doi.org/10.1109/tce.2026.3670687.

Harvard

Zhang, Y. et al. (2026) ‘Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data’, IEEE Transactions on Consumer Electronics, 72(3), pp. 6681–6690. doi:10.1109/tce.2026.3670687.

IEEE

Y. Zhang et al., “Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data,” IEEE Transactions on Consumer Electronics, vol. 72, no. 3, pp. 6681–6690, 2026, doi: 10.1109/tce.2026.3670687.

BibTeX

@article{zhang2026hierarchical,
  title     = {{Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data}},
  author    = {Zhang, Yi and Cz, Zhang and Li, Zijian and Xu, Tianxiang and Zhang, Kunyu and Gao, Zhan and Li, Meinuo and Zhang, Xiaohan and Qi, Qichao and Chen, Bing},
  journal   = {IEEE Transactions on Consumer Electronics},
  year      = {2026},
  volume    = {72},
  number    = {3},
  pages     = {6681--6690},
  doi       = {10.1109/tce.2026.3670687},
  url       = {https://doi.org/10.1109/tce.2026.3670687}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • large language models
  • medical LLMs
  • data memorization
  • privacy preservation

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Zhang, Y., Cz, Z., Li, Z., Xu, T., Zhang, K., Gao, Z., Li, M., Zhang, X., Qi, Q., & Chen, B. (2026). Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data. IEEE Transactions on Consumer Electronics, 72(3), 6681–6690. https://doi.org/10.1109/tce.2026.3670687

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yi Zhang, Zhang Cz, Zijian Li, Tianxiang Xu, Kunyu Zhang, Zhan Gao, Meinuo Li, Xiaohan Zhang, Qichao Qi, Bing Chen.

What is the DOI of this paper?

10.1109/tce.2026.3670687, permanently at https://doi.org/10.1109/tce.2026.3670687. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.