Accepted for/Published in: JMIR Research Protocols
Date Submitted: May 6, 2025
Date Accepted: Aug 29, 2025
Artificial intelligence-based algorithm to detect heart and lung disease from acute chest CT scans: A protocol for a development and validation study
ABSTRACT
Background:
Dyspnoea is a common cause of hospitalisation, posing diagnostic challenges among elderly, multimorbid patients. Chest computed tomography (CT) scans are increasingly used in dyspnoeic patients and offer superior diagnostic accuracy over chest radiographs but face limited use due to shortage of radiologists.
Objective:
We aim to develop and validate artificial intelligence algorithms to enable automatic analysis of acute CT scans and provide immediate feedback on the likelihood of pneumonia, pulmonary embolism, and cardiac decompensation. This protocol will focus on cardiac decompensation.
Methods:
We designed a retrospective method development and validation study. The study has been approved by The Danish National Committee on Health Research Ethics, Denmark (ID: 1575037). We extracted 4672 acute chest CT scans with corresponding radiological reports from Copenhagen University Hospital – Bispebjerg and Frederiksberg, Denmark, from 2016 to 2021. The scans will be randomly split into training (2/3) and internal validation (1/3) sets. Development of the artificial intelligence algorithm involves parameter tuning and feature selection using cross-validation. Internal validation uses the radiological reports as the ground truth, with algorithm specific thresholds be based on ≥90% true positive and negative rates for the heart and lung diseases. The artificial intelligence models will be validated in low-dose chest CT scans from consecutive patients admitted with acute dyspnoea and in coronary CT angiography scans from patients with acute coronary syndrome.
Results:
As of May 2025, CT data extraction is complete. Algorithm development, including image segmentation and natural language processing, is ongoing. Internal and external validation are planned, with overall validation expected to conclude in 2025 and final results available in 2026.
Conclusions:
The results are expected to enhance clinical decision-making by providing immediate, artificial intelligence driven insights from CT scans, beneficial for both clinicians and patients.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.