End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care

Gaurang Sharma; Juha Pajula; Tuomas Granlund; Petri Alhainen; Tommi Kiljander; Ornela Bardhi; Jaakko Lähteenmäki; Aada Illikainen; Antti Väänänen; Noora Lipsonen; Sari Kaari; Ville Salaspuro; Mika Hilvo

doi:10.1007/978-3-032-28829-5_24

End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care

Gaurang Sharma^*
, Juha Pajula
, Tuomas Granlund
, Petri Alhainen
, Tommi Kiljander
, Ornela Bardhi
, Jaakko Lähteenmäki
, Aada Illikainen
, Antti Väänänen
, Noora Lipsonen
, Sari Kaari
, Ville Salaspuro
, Mika Hilvo

^*Corresponding author for this work

Solita Oy
Mediconsult Oy
Bittium Oyj
Success Clinic Oy

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

Cardiovascular disease (CVD) risk assessment comprises multiple data-intensive processes, including patient consent management, data acquisition, electronic health record (EHR) integration, and predictive model development, each introducing distinct privacy risks. This study presents a privacy-first, end-to-end system architecture for CVD risk management spanning both primary and secondary prevention. For primary prevention, we developed predictive models without sharing data via real-world federated learning (FL) infrastructure, supported by a secure platform for server deployment and controlled data access. For secondary prevention, we developed privacy-aware workflows for consent management, electrocardiogram (ECG) monitoring, and integration of electronic health records (EHRs). Furthermore, we leveraged the integrated data to build secure clinical decision-support tools that mitigate hallucinations and adapt dynamically to updates in patient records. Together, these components form a generalizable, privacy-preserving architecture for AI-driven cardiovascular care that applies to other data-intensive clinical domains.

Original language	English
Title of host publication	Digital Health and Wireless Solutions
Subtitle of host publication	Connected Digital Health: Digital Twins, Wearables, Wireless Systems, and Secure Architectures - 2nd Nordic Conference, NCDHWS 2026, Proceedings
Editors	Mariella Särestöniemi, Daljeet Singh, Erika Jarva, Jarmo Reponen
Publisher	Springer
Pages	333-355
Number of pages	23
ISBN (Electronic)	978-3-032-28829-5
ISBN (Print)	978-3-032-28828-8
DOIs	https://doi.org/10.1007/978-3-032-28829-5_24
Publication status	Published - 2026
MoE publication type	A4 Article in a conference publication
Event	2nd Nordic Conference on Digital Health and Wireless Solutions, NCDHWS 2026 - Oulu, Finland Duration: 16 Jun 2026 → 17 Jun 2026

Publication series

Series	Communications in Computer and Information Science
Volume	3011 CCIS
ISSN	1865-0929

Conference

Conference	2nd Nordic Conference on Digital Health and Wireless Solutions, NCDHWS 2026
Country/Territory	Finland
City	Oulu
Period	16/06/26 → 17/06/26

Funding

This work was supported by the Business Finland-funded E! ITEA Secur-e-health project (4220/31/2021). We thank Antti Kaihovaara and Juha Kunnas from CSIT for providing services, expertise, and support to implement EntraID authentication for the platform. We also acknowledge Kzero for providing its technology for the platform’s passwordless authentication option and Heba Sourkatti for her contributions to data processing, which facilitated the analyses in this study.

Keywords

Cardiovascular Care
Federated Learning
Health data
Machine Learning
Primary Prevention
Secondary Prevention

Access to Document

10.1007/978-3-032-28829-5_24Licence: CC BY

Cite this

Sharma, G., Pajula, J., Granlund, T., Alhainen, P., Kiljander, T., Bardhi, O., Lähteenmäki, J., Illikainen, A., Väänänen, A., Lipsonen, N., Kaari, S., Salaspuro, V., & Hilvo, M. (2026). End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care. In M. Särestöniemi, D. Singh, E. Jarva, & J. Reponen (Eds.), Digital Health and Wireless Solutions: Connected Digital Health: Digital Twins, Wearables, Wireless Systems, and Secure Architectures - 2nd Nordic Conference, NCDHWS 2026, Proceedings (pp. 333-355). Springer. https://doi.org/10.1007/978-3-032-28829-5_24

Sharma, Gaurang ; Pajula, Juha ; Granlund, Tuomas et al. / End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care. Digital Health and Wireless Solutions: Connected Digital Health: Digital Twins, Wearables, Wireless Systems, and Secure Architectures - 2nd Nordic Conference, NCDHWS 2026, Proceedings. editor / Mariella Särestöniemi ; Daljeet Singh ; Erika Jarva ; Jarmo Reponen. Springer, 2026. pp. 333-355 (Communications in Computer and Information Science, Vol. 3011 CCIS).

@inproceedings{ec1dbe2cbf4b48adb5373c93fc31081a,

title = "End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care",

abstract = "Cardiovascular disease (CVD) risk assessment comprises multiple data-intensive processes, including patient consent management, data acquisition, electronic health record (EHR) integration, and predictive model development, each introducing distinct privacy risks. This study presents a privacy-first, end-to-end system architecture for CVD risk management spanning both primary and secondary prevention. For primary prevention, we developed predictive models without sharing data via real-world federated learning (FL) infrastructure, supported by a secure platform for server deployment and controlled data access. For secondary prevention, we developed privacy-aware workflows for consent management, electrocardiogram (ECG) monitoring, and integration of electronic health records (EHRs). Furthermore, we leveraged the integrated data to build secure clinical decision-support tools that mitigate hallucinations and adapt dynamically to updates in patient records. Together, these components form a generalizable, privacy-preserving architecture for AI-driven cardiovascular care that applies to other data-intensive clinical domains.",

keywords = "Cardiovascular Care, Federated Learning, Health data, Machine Learning, Primary Prevention, Secondary Prevention",

author = "Gaurang Sharma and Juha Pajula and Tuomas Granlund and Petri Alhainen and Tommi Kiljander and Ornela Bardhi and Jaakko L{\"a}hteenm{\"a}ki and Aada Illikainen and Antti V{\"a}{\"a}n{\"a}nen and Noora Lipsonen and Sari Kaari and Ville Salaspuro and Mika Hilvo",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2026.; 2nd Nordic Conference on Digital Health and Wireless Solutions, NCDHWS 2026 ; Conference date: 16-06-2026 Through 17-06-2026",

year = "2026",

doi = "10.1007/978-3-032-28829-5\_24",

language = "English",

isbn = "978-3-032-28828-8",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "333--355",

editor = "Mariella S{\"a}rest{\"o}niemi and Daljeet Singh and Erika Jarva and Jarmo Reponen",

booktitle = "Digital Health and Wireless Solutions",

address = "Germany",

}

Sharma, G , Pajula, J, Granlund, T, Alhainen, P, Kiljander, T, Bardhi, O, Lähteenmäki, J, Illikainen, A, Väänänen, A, Lipsonen, N, Kaari, S, Salaspuro, V & Hilvo, M 2026, End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care. in M Särestöniemi, D Singh, E Jarva & J Reponen (eds), Digital Health and Wireless Solutions: Connected Digital Health: Digital Twins, Wearables, Wireless Systems, and Secure Architectures - 2nd Nordic Conference, NCDHWS 2026, Proceedings. Springer, Communications in Computer and Information Science, vol. 3011 CCIS, pp. 333-355, 2nd Nordic Conference on Digital Health and Wireless Solutions, NCDHWS 2026, Oulu, Finland, 16/06/26. https://doi.org/10.1007/978-3-032-28829-5_24

End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care. / Sharma, Gaurang ; Pajula, Juha; Granlund, Tuomas et al.
Digital Health and Wireless Solutions: Connected Digital Health: Digital Twins, Wearables, Wireless Systems, and Secure Architectures - 2nd Nordic Conference, NCDHWS 2026, Proceedings. ed. / Mariella Särestöniemi; Daljeet Singh; Erika Jarva; Jarmo Reponen. Springer, 2026. p. 333-355 (Communications in Computer and Information Science, Vol. 3011 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care

AU - Sharma, Gaurang

AU - Pajula, Juha

AU - Granlund, Tuomas

AU - Alhainen, Petri

AU - Kiljander, Tommi

AU - Bardhi, Ornela

AU - Lähteenmäki, Jaakko

AU - Illikainen, Aada

AU - Väänänen, Antti

AU - Lipsonen, Noora

AU - Kaari, Sari

AU - Salaspuro, Ville

AU - Hilvo, Mika

N1 - Publisher Copyright: © The Author(s) 2026.

PY - 2026

Y1 - 2026

N2 - Cardiovascular disease (CVD) risk assessment comprises multiple data-intensive processes, including patient consent management, data acquisition, electronic health record (EHR) integration, and predictive model development, each introducing distinct privacy risks. This study presents a privacy-first, end-to-end system architecture for CVD risk management spanning both primary and secondary prevention. For primary prevention, we developed predictive models without sharing data via real-world federated learning (FL) infrastructure, supported by a secure platform for server deployment and controlled data access. For secondary prevention, we developed privacy-aware workflows for consent management, electrocardiogram (ECG) monitoring, and integration of electronic health records (EHRs). Furthermore, we leveraged the integrated data to build secure clinical decision-support tools that mitigate hallucinations and adapt dynamically to updates in patient records. Together, these components form a generalizable, privacy-preserving architecture for AI-driven cardiovascular care that applies to other data-intensive clinical domains.

AB - Cardiovascular disease (CVD) risk assessment comprises multiple data-intensive processes, including patient consent management, data acquisition, electronic health record (EHR) integration, and predictive model development, each introducing distinct privacy risks. This study presents a privacy-first, end-to-end system architecture for CVD risk management spanning both primary and secondary prevention. For primary prevention, we developed predictive models without sharing data via real-world federated learning (FL) infrastructure, supported by a secure platform for server deployment and controlled data access. For secondary prevention, we developed privacy-aware workflows for consent management, electrocardiogram (ECG) monitoring, and integration of electronic health records (EHRs). Furthermore, we leveraged the integrated data to build secure clinical decision-support tools that mitigate hallucinations and adapt dynamically to updates in patient records. Together, these components form a generalizable, privacy-preserving architecture for AI-driven cardiovascular care that applies to other data-intensive clinical domains.

KW - Cardiovascular Care

KW - Federated Learning

KW - Health data

KW - Machine Learning

KW - Primary Prevention

KW - Secondary Prevention

UR - https://www.scopus.com/pages/publications/105042893413

U2 - 10.1007/978-3-032-28829-5_24

DO - 10.1007/978-3-032-28829-5_24

M3 - Conference article in proceedings

AN - SCOPUS:105042893413

SN - 978-3-032-28828-8

T3 - Communications in Computer and Information Science

SP - 333

EP - 355

BT - Digital Health and Wireless Solutions

A2 - Särestöniemi, Mariella

A2 - Singh, Daljeet

A2 - Jarva, Erika

A2 - Reponen, Jarmo

PB - Springer

T2 - 2nd Nordic Conference on Digital Health and Wireless Solutions, NCDHWS 2026

Y2 - 16 June 2026 through 17 June 2026

ER -

Sharma G , Pajula J, Granlund T, Alhainen P, Kiljander T, Bardhi O et al. End-to-End Architecture for Secure Cardiovascular Disease Risk Assessment and Clinical Care. In Särestöniemi M, Singh D, Jarva E, Reponen J, editors, Digital Health and Wireless Solutions: Connected Digital Health: Digital Twins, Wearables, Wireless Systems, and Secure Architectures - 2nd Nordic Conference, NCDHWS 2026, Proceedings. Springer. 2026. p. 333-355. (Communications in Computer and Information Science, Vol. 3011 CCIS). doi: 10.1007/978-3-032-28829-5_24