Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Currently submitted to: JMIR Medical Informatics

Date Submitted: Feb 26, 2026
Open Peer Review Period: Mar 6, 2026 - May 1, 2026
(currently open for review)

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Digital Architecture of the Croatian National Lung Cancer Screening Program: Observational Implementation Study

  • Antun Aboud; 
  • Kristina Krpina; 
  • Stjepan Oreskovic; 
  • Miroslav Samarzija

ABSTRACT

Background:

Scaling lung cancer screening from controlled trials to nationwide implementation requires interoperable digital infrastructure capable of coordinating primary care, radiology, pulmonology, and centralized governance. Although low-dose computed tomography (LDCT) reduces lung cancer mortality in high-risk populations, few countries have embedded screening programs directly within national health information systems to enable standardized workflows, real-time monitoring, and data-driven quality control.

Objective:

To describe the digital architecture, interoperability framework, and real-world performance of the Croatian National Lung Cancer Screening Program (CNLCSP), implemented as a native extension of the Central Health Information System of the Republic of Croatia (CEZIH).

Methods:

This retrospective observational implementation study analyzed structured program data collected between October 2020 and December 2025. The CNLCSP targets individuals aged 50–75 years with ≥30 pack-years of smoking history who are current smokers or former smokers who quit within 15 years. The program operates entirely within CEZIH through role-specific modules for general practitioners (GPs), radiologists, pulmonologists, and national coordinators. Core digital functionalities include electronic eligibility verification, paperless referral and scheduling, structured radiology and pulmonology reporting based on modified I-ELCAP guidelines, AI-assisted volumetric nodule analysis integrated into the reporting workflow with mandatory radiologist second reading, secure DICOM-based telemedicine image transfer, and a centralized analytics module providing real-time dashboards of predefined quality indicators, including radiation dose metrics.

Results:

From October 2020 to December 2025, over 54,000 individuals were screened, generating more than 80,000 LDCT examinations across 27 radiology centers and 6 pulmonology centers, involving more than 2,000 GPs. Positive radiological findings were reported in 4.45% of examinations. Continuous digital monitoring supported a mean effective radiation dose of 0.85 mSv, below the program limit of 1.5 mSv. The interoperable CEZIH-based infrastructure enabled expansion from 16 to 27 radiology centers while maintaining standardized reporting and centralized oversight.

Conclusions:

Embedding lung cancer screening as a native component of a national health information system enables scalable implementation, structured data capture, AI-supported clinical workflows with human oversight, and real-time governance. The Croatian model illustrates how digital integration within existing health infrastructure can support population-level screening and may serve as a transferable informatics framework for other health systems.


 Citation

Please cite as:

Aboud A, Krpina K, Oreskovic S, Samarzija M

Digital Architecture of the Croatian National Lung Cancer Screening Program: Observational Implementation Study

JMIR Preprints. 26/02/2026:94210

DOI: 10.2196/preprints.94210

URL: https://preprints.jmir.org/preprint/94210

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.