Skip to main content

CPB-REPORT: An automated perioperative data integration platform in cardiac surgery

In brief

Automated cardiac surgery platform reached 90% completeness and 97.8% data concordance

At one high-volume cardiac surgery center, the platform captured 2,915 patients and reduced registry data-entry time by 20 minutes per patient. Completeness rose from 68% at launch to 90% in 2025, and automated data matched source records 97.8% of the time; it also enabled early detection of an infection cluster, though results at other centers remain unknown.

Journal
International journal of medical informatics (Q1)
Published
2 November 2026
Study design
Unclassified
Evidence level
Level 5, Expert Opinion (CEBM 5)
Authors
Mohamed Rekik, Olivier Montandrau, Mohamet Koné, Alexy Tran-Dinh, Konstantinos Zannis, Marc Beaussier
PMID
43063846
DOI
10.1016/j.ijmedinf.2026.106793

Why clinicians should know about it

  • Picked for Health Informatics (top studies of the week, 22 November 2026): Real-world EHR integration platform improves completeness, accuracy, and workflow

Abstract

BACKGROUND: Cardiac surgery under cardiopulmonary bypass generates large volumes of perioperative data fragmented across multiple clinical information systems, limiting their integration for quality improvement and research. Cardiac surgery registries still rely predominantly on manual data entry, which is time-consuming, error-prone, and often incomplete. OBJECTIVE: To report the real-world implementation of an automated perioperative data integration platform and evaluate its performance in terms of data completeness, accuracy, clinical workflow, and patient safety. METHODS: We developed CPB-REPORT, a secure web-based platform using an Extract-Transform-Load architecture, integrating data from electronic health records, anaesthesia, and critical care systems into a unified database aligned with the national cardiac surgery registry. The platform was deployed in a high-volume cardiac surgery centre and initially combined automated extraction of registry variables and structured manual entry. A concordance study was performed to evaluate the robustness of automatically integrated data. RESULTS: Between May 2022 and May 2026, CPB-REPORT prospectively captured all cardiac surgery procedures performed at the institution: 2,915 patients underwent 2,927 procedures, each documented across 174 fields and transmitted to the national registry. Compared with the previous fully manual process, the platform reduced data entry time by 20 min per patient. Dataset completeness improved from 68 % at platform deployment to 90 % in 2025. The concordance study showed an overall concordance of 97.8 % between automatically extracted and source-record values (95 % CI: 94.7-99.4 %), with excellent intraclass correlation coefficients for continuous variables. Real-time outcome monitoring enabled early detection of a surgical site infection cluster in 2022. No cybersecurity incident occurred. CONCLUSION: The present work demonstrates that Extract-Transform-Load-based perioperative data integration is achievable in routine cardiac surgery practice using standard hospital infrastructure. The platform offers a transferable methodological model for integrating clinical information systems with international registries in line with European data-protection and interoperability frameworks.

Abstract as published, via PubMed.

View on PubMedFull text at the publisherOpen in the app

For healthcare professionals. The summary is generated by AI from the published abstract, and the evidence level is assigned automatically from the study design on the Oxford CEBM hierarchy. Neither is medical advice. Read the full paper before changing practice.