EUVIMEDEUVIMED entdecken
Crossref

XRAInet: AI‐based decision support for pneumothorax and pleural effusion management

Mustafa Alper Akay iD, Ozan Can Tatar iD, Elif Tatar iD, Beyza Nur Tağman iD, Semih Metin iD, Onursal Varlıklı iD

Pediatric Pulmonology · 2024

DOI: 10.1002/ppul.27133 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pediatric Pulmonology, 2024. Verfasst von Mustafa Alper Akay und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatric Surgery, Faculty of Medicine, Kocaeli University, Kocaeli, Turkey. Hauptthemen laut MEDLINE: Pneumothorax, Pleural Effusion, Thoracostomy. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 14 Literaturangaben. Gefördert von: None.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This study aimed to develop and assess the performance of an artificial intelligence (AI)‐driven decision support system, XRAInet, in accurately identifying pediatric patients with pleural effusion or pneumothorax and determining whether tube thoracostomy intervention is warranted.

Methods

In this diagnostic accuracy study, we retrospectively analyzed a data set containing 510 X‐ray images from 170 pediatric patients admitted between 2005 and 2022. Patients were categorized into two groups: Tube (requiring tube thoracostomy) and Conservative (managed conservatively). XRAInet, a deep learning‐based algorithm, was trained using this data set. We evaluated its performance using various metrics, including mean Average Precision (mAP), recall, precision, and F1 score.

Results

XRAInet, achieved a mAP score of 0.918. This result underscores its ability to accurately identify and localize regions necessitating tube thoracostomy for pediatric patients with pneumothorax and pleural effusion. In an independent testing data set, the model exhibited a sensitivity of 64.00% and specificity of 96.15%.

Conclusion

In conclusion, XRAInet presents a promising solution for improving the detection and decision‐making process for cases of pneumothorax and pleural effusion in pediatric patients using X‐ray images. These findings contribute to the expanding field of AI‐driven medical imaging, with potential applications for enhancing patient outcomes. Future research endeavors should explore hybrid models, enhance interpretability, address data quality issues, and align with regulatory requirements to ensure the safe and effective deployment of XRAInet in healthcare settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PneumothoraxPleural EffusionThoracostomyHumansRetrospective StudiesChildFemaleMaleChild, PreschoolArtificial IntelligenceInfantDecision Support Systems, ClinicalAdolescentDeep LearningRadiography, ThoracicAlgorithmsDecision Support TechniquesSensitivity and SpecificityChest Tubes

Stichwörter der Autor:innen

decision support systemsdeep learningdiagnostic imagingpleural effusionpneumothorax

Autor:innen und Institutionen

  • Department of Pediatric Surgery, Faculty of Medicine, Kocaeli University, Kocaeli, Turkey.
  • Department of General Surgery, Faculty of Medicine, Kocaeli University, Kocaeli, Turkey.

ORCID-Profile: Mustafa Alper Akay, Ozan Can Tatar, Elif Tatar, Beyza Nur Tağman, Semih Metin, Onursal Varlıklı

Förderung

  • None

Zitieren

APA

Akay, M. A., Tatar, O. C., Tatar, E., Tağman, B. N., Metin, S., & Varlıklı, O. (2024). XRAInet: AI‐based decision support for pneumothorax and pleural effusion management. Pediatric Pulmonology. https://doi.org/10.1002/ppul.27133

Vancouver

Akay MA, Tatar OC, Tatar E, Tağman BN, Metin S, Varlıklı O. XRAInet: AI‐based decision support for pneumothorax and pleural effusion management. Pediatric Pulmonology. 2024. doi:10.1002/ppul.27133

BibTeX
@article{Akay2024,
  author = {Akay, Mustafa Alper and Tatar, Ozan Can and Tatar, Elif and Tağman, Beyza Nur and Metin, Semih and Varlıklı, Onursal},
  title = {XRAInet: AI‐based decision support for pneumothorax and pleural effusion management},
  journal = {Pediatric Pulmonology},
  year = {2024},
  doi = {10.1002/ppul.27133}
}
Kostenlos starten →