EUVIMEDEUVIMED entdecken
ValidierungsstudieStudienprotokollOpen Access

AI-Based Algorithm to Detect Heart and Lung Disease From Acute Chest Computed Tomography Scans: Protocol for an Algorithm Development and Validation Study

Anne Sophie Overgaard Olesen iD, Kristina Miger iD, Silas Nyboe Ørting iD, Jens Petersen iD, Marleen de Bruijne iD, Mikael Ploug Boesen iD, Michael Brun Andersen iD, Johannes Grand iD, Jens Jakob Thune iD, Olav Wendelboe Nielsen iD

JMIR Research Protocols · 2025

DOI: 10.2196/77030 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift JMIR Research Protocols, 2025. Verfasst von Anne Sophie Overgaard Olesen und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Bispebjerg Hospital, Copenhagen, Denmark. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Algorithms, Lung Diseases, Artificial Intelligence. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Dyspnea is a common cause of hospitalization, posing diagnostic challenges among older adult patients with multimorbid conditions. Chest computed tomography (CT) scans are increasingly used in patients with dyspnea and offer superior diagnostic accuracy over chest radiographs but face limited use due to a shortage of radiologists.

Objective

This study aims to develop and validate artificial intelligence (AI) 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. This study has been approved by the Danish National Committee on Health Research Ethics (1575037). We extracted 4672 acute chest CT scans with corresponding radiological reports from the 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 AI algorithm involves parameter tuning and feature selection using cross validation. Internal validation uses radiological reports as the ground truth, with algorithm-specific thresholds based on true positive and negative rates of 90% or greater for heart and lung diseases. The AI models will be validated in low-dose chest CT scans from consecutive patients admitted with acute dyspnea and in coronary CT angiography scans from patients with acute coronary syndrome.

Results

As of August 2025, CT data extraction has been completed. Algorithm development, including image segmentation and natural language processing, is ongoing. However, for pulmonary congestion, the algorithm development has been completed. Internal and external validation are planned, with overall validation expected to conclude in 2025 and the final results to be available in 2026.

Conclusions

The results are expected to enhance clinical decision-making by providing immediate, AI-driven insights from CT scans, which will be beneficial for both clinicians and patients. International Registered Report Identifier (IRRID) DERR1-10.2196/77030

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedAlgorithmsLung DiseasesArtificial IntelligenceHeart DiseasesHumansRetrospective StudiesDenmarkRadiography, ThoracicPulmonary EmbolismDyspnea

Stichwörter der Autor:innen

AIacute careartificial intelligencecardiac decompensationcomputed tomographydiagnostic imagingdyspneamachine learning

Autor:innen und Institutionen

  • Department of Cardiology, Bispebjerg Hospital, Copenhagen, Denmark.
  • Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
  • Department of Radiology, Bispebjerg Hospital, Copenhagen, Denmark.
  • Department of Radiology, Herlev Hospital, Herlev, Denmark.
  • Department of Cardiology, Hvidovre Hospital, Hvidovre, Denmark.
  • Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.

ORCID-Profile: Anne Sophie Overgaard Olesen, Kristina Miger, Silas Nyboe Ørting, Jens Petersen, Marleen de Bruijne, Mikael Ploug Boesen, Michael Brun Andersen, Johannes Grand, Jens Jakob Thune, Olav Wendelboe Nielsen

Zitieren

APA

Olesen, A. S. O., Miger, K., Ørting, S. N., Petersen, J., de Bruijne, M., Boesen, M. P., Andersen, M. B., Grand, J., Thune, J. J., & Nielsen, O. W. (2025). AI-Based Algorithm to Detect Heart and Lung Disease From Acute Chest Computed Tomography Scans: Protocol for an Algorithm Development and Validation Study. JMIR Research Protocols. https://doi.org/10.2196/77030

Vancouver

Olesen ASO, Miger K, Ørting SN, Petersen J, de Bruijne M, Boesen MP, et al. AI-Based Algorithm to Detect Heart and Lung Disease From Acute Chest Computed Tomography Scans: Protocol for an Algorithm Development and Validation Study. JMIR Research Protocols. 2025. doi:10.2196/77030

BibTeX
@article{Olesen2025,
  author = {Olesen, Anne Sophie Overgaard and Miger, Kristina and Ørting, Silas Nyboe and Petersen, Jens and de Bruijne, Marleen and Boesen, Mikael Ploug and Andersen, Michael Brun and Grand, Johannes and Thune, Jens Jakob and Nielsen, Olav Wendelboe},
  title = {AI-Based Algorithm to Detect Heart and Lung Disease From Acute Chest Computed Tomography Scans: Protocol for an Algorithm Development and Validation Study},
  journal = {JMIR Research Protocols},
  year = {2025},
  doi = {10.2196/77030}
}
Kostenlos starten →