Anshul THAKUR

A collaborative large language model for drug analysis. Nature Biomedical Engineering, 1-12.https://doi.org/10.1038/s41551-025-01471-z

A multimodal multidomain multilingual medical foundation model for zero shot clinical diagnosis. npj Digital Medicine, 8(1), 86.10.1038/s41746-024-01339-7.https://doi.org/10.1038/s41746-024-01339-7

A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals. The Lancet Digital Health, 6(2), e93-e104.

Adversarial De-confounding in Individualised Treatment Effects Estimation. In International Conference on Artificial Intelligence and Statistics, pp. 837-849. PMLR, 2023

Are Time Series Foundation Models Ready for Vital Sign Forecasting in Healthcare?. In Proceedings of the 4th Machine Learning for Health Symposium (Proceedings of Machine Learning Research (Vol. 259, pp. 401-419).https://proceedings.mlr.press/v259/gu25a.html

CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks. Journal of Healthcare Informatics Research, 8(3), 555-575. https://doi.org/10.1007/s41666-024-00169-2

Continuous patient state attention model for addressing irregularity in electronic health records. BMC Medical Informatics and Decision Making, 24(1), 117. https://doi.org/10.1186/s12911-024-02514-2

COPER: Continuous Patient State Perceiver. 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), 2022, pp. 1-4. DOI: 10.1109/BHI56158.2022.9926807

Data encoding for healthcare data democratization and information leakage prevention. Nature Communications, 15(1), 1582. https://doi.org/10.1038/s41467-024-45777-z

Dysregulated immune proteins in plasma in the UK Biobank predict Multiple Myeloma 12 years before clinical diagnosis. Blood Advances, bloodadvances-2025016120.https://doi.org/10.1182/bloodadvances.2025016120

Efficient Task Grouping Through Sample-wise Optimisation Landscape Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence.10.1109/TPAMI.2025.3588685

F^ 3OCUS-Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 20006-20017).10.1109/cvpr52734.2025.01863