CoChat

Decentralised health record management with blockchain: privacy and security in cloud-based systems

Open access

The DOI matches its Crossref record; 63 of the 64 references it cites were found in a registry or an index; none of the 8 sources its claims cite is checked for support yet.

Abstract

The rise of Electronic Health Records (EHRs) has created a new challenge for healthcare organisations: how to manage, share and secure the growing amounts of health data. Conventional cloud-based EHR systems remain susceptible to centralised trust, limited auditability, and inflexible access-control mechanisms, and most existing blockchain-based systems don’t collectively support adaptive policy enforcement, privacy-preserving authentication, and anomaly-aware access validation. To address these limitations, this paper introduces the decentralised EHR management framework HealthBlockSecure, which combines permissioned blockchain infrastructure, encrypted off-chain storage, authentication with zero-knowledge proofs (ZKPs), decentralised identities, smart-contract-based policy enforcement, and the PrivAccessNet deep learning model. PrivAccessNet can provide context-aware access validation and anomaly detection based on request and policy attributes, and the external ZKP verification service can provide minimal-disclosure authentication without revealing sensitive identity information. Experimental evaluation with SyntheticMass and MIMIC-IV showed a mean access-violation prevention rate of 96.3% for five re-experiments and an audit-verification accuracy of 99.2%. It also identified all simulated tampering attempts using SHA-256 integrity verification. In general, HealthBlockSecure delivers an integrated solution for privacy-sensitive, auditable, and adaptive management of access to EHRs, with secure-access validation latency measured in the near-real-time range. The complete HealthBlockSecure implementation is publicly available at https://github.com/Sripada-RamaSree/HealthBlockSecure .

Overview

CoChat Summary

TL;DR

The paper introduces HealthBlockSecure, a decentralised EHR management framework combining permissioned blockchain, encrypted off-chain storage, ZKP authentication, DIDs, smart-contract policy enforcement, and the PrivAccessNet deep learning model. In controlled experiments on SyntheticMass and MIMIC-IV, it reports high access-violation prevention, audit-verification accuracy, and tamper detection, with added latency versus centralised OAuth.

Key findings

  • Across five repeated runs, HealthBlockSecure achieved a mean access-violation prevention rate of 96.3 ± 0.7% and audit-verification accuracy of 99.2 ± 0.3%; a representative 600-attempt run prevented 582/600 (97.0%), including 150/150 unregistered-user attempts, 195/200 role-based policy violations, 144/150 expired-token reuses, and 93/100 invalid ZKP authentication attempts.
  • SHA-256 integrity verification detected all 50 tampered records among 500 access events, and complete audit-trail retrieval was achieved for 30 patients (100%).
  • End-to-end access latency was 1.43 s for MIMIC-IV and 0.82 s for SyntheticMass; read-only access averaged 0.58 s and full access 1.46 s; latency rose to 1.52 s, 2.11 s, and 2.31 s at 10, 50, and 100 concurrent users, respectively. Throughput was 38/21 transactions per second for sequential light/heavy load and 63/47 for parallel light/heavy load.
  • ZKP authentication took 185 ms versus 92 ms for conventional identity checks; secure-access validation latency was 203 ms versus 97 ms for centralised OAuth, while violation prevention was 96.3% versus 74.5% and audit completeness 100% versus 68%. Ablation showed prevention dropped to 92.8% without ZKP, 88.7% without smart contracts, and 90.4% without PrivAccessNet; audit verification dropped to 71.6% without blockchain.

Methods

  • Design: HealthBlockSecure uses a layered architecture (user, blockchain, cloud storage) with Hyperledger Fabric 2.x, Go smart contracts, AES-encrypted off-chain storage (AWS S3 and IPFS-compatible references), ECC-protected session keys, DIDs, external Python zk-SNARK verification via REST API, SHA-256 integrity hashes, and PrivAccessNet for context-aware access validation.
  • Data/sample: SyntheticMass (10,000 patient records) and MIMIC-IV (~5,000 records) were used; 1,000 access requests per dataset were simulated from doctors, nurses, and researchers, with 30% unauthorised or expired-token cases and 70% compliant cases in a Docker/Docker Compose prototype.
  • Analysis: PrivAccessNet is a three-hidden-layer dense network (64/32/16 neurons) with ReLU, batch normalisation, dropout 0.30, sigmoid output, Adam optimiser (learning rate 0.001), binary cross-entropy loss, batch size 32, maximum 50 epochs, early stopping, and a 20% validation subset; evaluation covered latency, throughput, violation prevention, audit verification, ZKP latency, ablation, controlled baselines, and five repeated runs with confidence intervals.

Limitations

  • Stated: the evaluation was a controlled simulation using public datasets and synthetic access requests, not real healthcare networks, institutional policies, infrastructure, or user behaviour; PrivAccessNet was trained on simulated access events and would need adaptation using real access logs under privacy, ethical, and governance constraints.
  • Stated: computational and operational overhead arises from blockchain endorsement, ordering, commitment, ZKP proof transmission and external verification, serialisation, communication, PrivAccessNet inference, encrypted cloud retrieval, key handling, and local decryption; this may worsen under higher concurrency or resource-constrained settings, and long-term deployment raises concerns about replicated blockchain storage, synchronisation, infrastructure maintenance, off-chain storage management, ledger growth, certificate management, policy representation, interoperability, and identity-management integration.
  • Evident from the text: comparisons with existing blockchain healthcare frameworks are literature-based contextual benchmarks rather than direct experiments; the reported experiments did not automate online retraining; and results are for a containerised prototype, not production-scale healthcare deployment.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41598-026-79427-9

Cites

63 of 64 references verified1 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Layered architectural framework of HealthBlockSecure for decentralised and privacy-preserving EHR management.
Fig. 1 Layered architectural framework of HealthBlockSecure for decentralised and privacy-preserving EHR management.CC-BY-NC-ND · From the PDF
Fig. 2 Architectural design of PrivAccessNet for policy-aware and privacy-preserving EHR access control.
Fig. 2 Architectural design of PrivAccessNet for policy-aware and privacy-preserving EHR access control.CC-BY-NC-ND · From the PDF
Fig. 3 Workflow diagram of the proposed blockchain-based health record management framework.
Fig. 3 Workflow diagram of the proposed blockchain-based health record management framework.CC-BY-NC-ND · From the PDF
Fig. 4 Multi-dimensional access latency profile of HealthBlockSecure under dataset, access-type, and concurrency conditions.
Fig. 4 Multi-dimensional access latency profile of HealthBlockSecure under dataset, access-type, and concurrency conditions.CC-BY-NC-ND · From the PDF
Fig. 5 Throughput performance across access modes and blockchain load conditions.
Fig. 5 Throughput performance across access modes and blockchain load conditions.CC-BY-NC-ND · From the PDF
Fig. 6 Analysis of access-violation attempts, successful denials, and prevention rates.
Fig. 6 Analysis of access-violation attempts, successful denials, and prevention rates.CC-BY-NC-ND · From the PDF
Fig. 7 Multi-scenario audit integrity verification performance of HealthBlockSecure.
Fig. 7 Multi-scenario audit integrity verification performance of HealthBlockSecure.CC-BY-NC-ND · From the PDF
Image 8
CC-BY-NC-ND · From the PDF
Fig. 9 Security-latency trade-off profile of HealthBlockSecure and centralised OAuth-based EHR systems.
Fig. 9 Security-latency trade-off profile of HealthBlockSecure and centralised OAuth-based EHR systems.CC-BY-NC-ND · From the PDF
Image 10
CC-BY-NC-ND · From the PDF
Image 11
CC-BY-NC-ND · From the PDF
Image 12
CC-BY-NC-ND · From the PDF

Verification

Claims the paper makes

0 Valid · 6 Not valid · 4 Not checked · 133 Own results and interpretations

56 more claims

Create a free account to see all 143 claims and every source verdict.

See all claims — free account
  • It may state two separate claims as one. 52
  • Probably not a substantial claim. 45

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

4 of 4

Citations

Cites

Show all 64 references

Research works printed but not linked: 2

  1. Reegu, F. A. et al. Blockchain-based framework for interoperable electronic health record. Ann. Romanian Soc. Cell Biol. 25(3), 6486-6495 (2021).
  2. Tatineni, S. Integrating AI, blockchain and cloud technologies for data management in healthcare. J. Comput. Eng. Technol. (JCET) 5(1), 7-20 (2022).

Cited by

Still being checked.

Metadata

Authors
Sree, S. R., Radhika, D., Veerabhadram, V., Sirisha, S. M., Jyoshna, B., & Raghavender, E.
Affiliations
  • Aditya University (IN)
  • CR Rao Advanced Institute of Mathematics, Statistics and Computer Science (IN)
  • SRKR Engineering College (IN)
Corresponding author
Sree, S. Rama
Venue
Scientific Reports
Published
2026-11-11
ISSN
2045-2322 (ISSN-L)
OpenAlex
W7225783750
Cited by
0
References
60
FWCI
0.00
Type
journal article
Language
en
Open access
Licence
Locations
Scientific Reports (publishedVersion, cc-by-nc-nd)
Topics
  • Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
  • Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
  • Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
Keywords
electronic health records, blockchain, access control, zero-knowledge proofs, decentralized identity, smart contracts, anomaly detection, data integrity verification, health 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.

A language model drew the claims from the paper on 2026-11-20, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-11-20 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Decentralised health record management with blockchain: privacy and security in cloud-based systems. https://app.cochat.ai/papers/10.1038/s41598-026-79427-9
The paper
Sree, S. R., Radhika, D., Veerabhadram, V., Sirisha, S. M., Jyoshna, B., & Raghavender, E. (2026). Decentralised health record management with blockchain: privacy and security in cloud-based systems. Scientific Reports. https://doi.org/10.1038/s41598-026-79427-9

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.