Privacy-Preserving Federated Learning with Layer 2 Blockchain Anchoring for Auditable Clinical Trial Eligibility Screening
Open accessThe DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Abstract
Matching patients to clinical trials with large language models is technically feasible, but the prevailing methodology fine-tunes commercial models through external interfaces, transmitting sensitive patient records to third parties, and the resulting screening decisions lack a record that an external auditor can verify. This paper proposes an end-to-end alternative combining privacy-preserving Federated Learning (FL) with a blockchain provenance layer settled on a Layer 2 rollup. On the learning side, we construct an extended benchmark of 3000 patient and trial pairs covering 12 medical conditions and compare FedAvg, FedProx, and FedDyn under simulated clinical heterogeneity with a worst-case label-skew stress client. With all models evaluated on one held-out test set at matched compute, FedDyn reaches an F1 score of 0.885 (0.883 ± 0.008 across five training seeds), matching the early-stopped centralized baseline of 0.878, while an extended 50-epoch centralized run reaches 0.945 (0.944 ± 0.023). Holdout experiments on unseen protocols and unseen conditions quantify the remaining generalization gap. A stratified membership inference evaluation with bootstrap confidence intervals provides preliminary evidence that federated training roughly halves the attacker’s membership advantage. The direction of this reduction is stable across all five seeds, although its confidence interval includes zero and attack area under the curve (AUC) values remain close to the 0.5 random-guessing level throughout. On the provenance side, every decision passes through a deterministic gate. Its evidence is AES-256-GCM-encrypted and stored off-chain on InterPlanetary File System (IPFS), while only cryptographic commitments are anchored by access-controlled smart contracts on the rollup, with a Merkle checkpoint on Ethereum Layer 1. On public test networks, Layer 2 settlement reduces the cost of anchoring each decision by a factor of approximately 53 relative to Layer 1, and the provenance of all 300 test-cohort decisions is independently re-verified end to end. Three Layer 2 hardening mechanisms, an L1 checkpoint, EIP-712 signed consent, and forced inclusion, are demonstrated at feasibility level. The implementation is publicly available on GitHub.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
A systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019) · arXiv · doi:10.48550/arxiv.1910.01108 · Cited by 4,653
Federated Optimization in Heterogeneous Networks
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2018) · arXiv · doi:10.48550/arxiv.1812.06127 · Cited by 4,023
The future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015
Domain-specific language model pretraining for biomedical natural language processing
Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., & Poon, H. (2022) · ACM Transactions on Computing for Healthcare · doi:10.1145/3458754 · Cited by 2,170
Federated Learning with Non-IID Data
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., & Chandra, V. (2018) · arXiv · doi:10.48550/arxiv.1806.00582 · Cited by 2,077
Zhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906
Alsentzer, E., Murphy, J., Boag, W., Weng, W.-H., Jindi, D., Naumann, T., & McDermott, M. (2019) · Proceedings of the 2nd Clinical Natural Language Processing Workshop · doi:10.18653/v1/w19-1909 · Cited by 1,736
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S. J., Stich, S. U., & Suresh, A. T. (2019) · arXiv · doi:10.48550/arxiv.1910.06378 · Cited by 1,734
Blockchain technology overview
Yaga, D., Mell, P., Roby, N., & Scarfone, K. (2018) · doi:10.6028/nist.ir.8202 · Cited by 1,551
Bootstrap Methods: Another Look at the Jackknife
Efron, B. (1992) · Springer Series in Statistics · doi:10.1007/978-1-4612-4380-9_41 · Cited by 1,374
Federated Learning Based on Dynamic RegularizationPreprint
Acar, D. A. E., Zhao, Y., Navarro, R. M., Mattina, M., Whatmough, P. N., & Saligrama, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.04263 · Cited by 1,089
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
Yeom, S., Giacomelli, I., Fredrikson, M., & Jha, S. (2018) · 2018 IEEE 31st Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2018.00027 · Cited by 1,001
Salem, A., Zhang, Y., Humbert, M., Berrang, P., Fritz, M., & Backes, M. (2019) · Proceedings 2019 Network and Distributed System Security Symposium · doi:10.14722/ndss.2019.23119 · Cited by 852
Neural Networks: Tricks of the Trade
(1998) · Lecture Notes in Computer Science · doi:10.1007/3-540-49430-8 · Cited by 810
Flower: A Friendly Federated Learning Research Framework
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Li, K. H., Parcollet, T., de Gusmão, P. P. B., et al. (2020) · arXiv · doi:10.48550/arxiv.2007.14390 · Cited by 622
Using Blockchain for Electronic Health Records
Shahnaz, A., Qamar, U., & Khalid, A. (2019) · IEEE Access · doi:10.1109/access.2019.2946373 · Cited by 590
Membership Inference Attacks From First Principles
Carlini, N., Chien, S., Nasr, M., Song, S., Terzis, A., & Tramèr, F. (2022) · 2022 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp46214.2022.9833649 · Cited by 502
Layer 2 Blockchain Scaling: a SurveyPreprint
Sguanci, C., Spatafora, R., & Vergani, A. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10881 · Cited by 225
Blockchain Scaling Using Rollups: A Comprehensive Survey
Thibault, L. T., Sarry, T., & Hafid, A. S. (2022) · IEEE Access · doi:10.1109/access.2022.3200051 · Cited by 216
Ditto: Fair and Robust Federated Learning Through Personalization
Li, T., Hu, S., Beirami, A., & Smith, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04221 · Cited by 205
Personalized Federated Learning with Moreau Envelopes
Dinh, C. T., Tran, N. H. K., & Nguyen, T. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.08848 · Cited by 203
Hyperledger Healthchain: Patient-Centric IPFS-Based Storage of Health Records
Mani, V., Manickam, P., Alotaibi, Y. A., Alghamdi, S. A., & Khalaf, O. I. (2021) · Electronics · doi:10.3390/electronics10233003 · Cited by 180
Omar, I. A., Jayaraman, R., Salah, K. M., Simsekler, M. C. E., Yaqoob, I., & Ellahham, S. H. (2020) · BMC Medical Research Methodology · doi:10.1186/s12874-020-01109-5 · Cited by 141
Blockchain protocols in clinical trials: Transparency and traceability of consent
Benchoufi, M., Porcher, R., & Ravaud, P. (2018) · F1000Research · doi:10.12688/f1000research.10531.5 · Cited by 129
Eren, H., Karaduman, Ö., & Gençoğlu, M. T. (2025) · Applied Sciences · doi:10.3390/app15063225 · Cited by 91
Sultana, S. A., Rupa, C., Malleswari, R. P., & Gadekallu, T. R. (2023) · Information · doi:10.3390/info14080446 · Cited by 84
A Survey on Data Availability in Layer 2 Blockchain Rollups: Open Challenges and Future Improvements
Saif, M. B., Migliorini, S., & Spoto, F. (2024) · Future Internet · doi:10.3390/fi16090315 · Cited by 55
Practical Limitations of Ethereum’s Layer-2
Neiheiser, R., Inácio, G., Rech, L. D. O., Montez, C., Matos, M., & Rodrigues, L. (2023) · IEEE Access · doi:10.1109/access.2023.3237897 · Cited by 53
(2020) · Lecture notes in computer science · doi:10.1007/978-3-030-51280-4 · Cited by 45
Exploiting Ethereum Smart Contracts for Clinical Trial Management
Omar, I. A., Jayaraman, R., Salah, K. M., & Simsekler, M. C. E. (2019) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa47632.2019.9035341 · Cited by 25
Artenie, A. C., Silaghi, D. L., & Popescu, D. E. (2025) · Computers · doi:10.3390/computers14090359 · Cited by 9
Self-citationYun, J., Lu, Y., Liu, X., & Guan, J. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2268 · Cited by 7
Leveraging blockchain and LLMs for patient–clinical trial matching
Hawashin, D., Salah, K., Jayaraman, R., Ellahham, S. H., & Yaqoob, I. (2025) · Array · doi:10.1016/j.array.2025.100657 · Cited by 4
Blockchain and Artificial Intelligence: Convergence, Applications and Challenges
Artenie, A. C., Morar, C. D., & Popescu, D. E. (2026) · International Conference on Development and Application Systems (DAS) · doi:10.1109/das69882.2026.11553350 · Cited by 1
Self-citation
Research works printed but not linked: 4
- Wang, J., Liu, Q., Liang, H., Joshi, G., and Poor, H.V. (2020). Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization. arXiv.
- Li, 2020, Federated Learning: Challenges, Methods, and Future Directions, IEEE Signal Process. Mag., 37, 50
- Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A., and Seth, K. (2016). Practical Secure Aggregation for Federated Learning on User-Held Data. arXiv.
- Peterson, P., Baker, E., and McGaw, B. (2010). Bootstrap Method. International Encyclopedia of Education, Elsevier. [3rd ed.].
Cited by
Still being checked.
Metadata
- Authors
- Artenie, A. C., Morar, C. D., Popa, C.-A., & Moldovan, O. G.
- Affiliations
- Politehnica University of Timisoara (RO)
- University of Oradea (RO)
- Corresponding author
- Artenie, Andrada Cristina
- Morar, Catalin Daniel
- Popa, Călin-Adrian
- Moldovan, Ovidiu Gheorghe
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2026-09-19
- Volume
- 16
- Issue
- 18
- Pages
- 9296
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W7214054349
- Cited by
- 0
- References
- 40
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- University of Oradea
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- privacy-preserving federated learning, Layer 2 blockchain, clinical trial eligibility screening, large language models, membership inference attacks, FedAvg, FedProx, cryptographic commitments, smart contracts, IPFS, patient data privacy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.