EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Development and testing of a deep learning algorithm to detect lung consolidation among children with pneumonia using hand-held ultrasound

David Kessler, Meihua Zhu, Cynthia R Gregory, Courosh Mehanian, Jailyn Avila, Nick Avitable, Di Coneybeare, Devjani Das, Almaz Dessie, Thomas M Kennedy, Joni Rabiner, Laurie Malia und 12 weitere

PLOS ONE · 27.08.2024 · 19 (8) · e0309109

DOI: 10.1371/journal.pone.0309109 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift PLOS ONE, online erschienen am 27.08.2024. Verfasst von David Kessler und 23 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, Columbia University Vagelos College of Physicians & Surgeons, New York Presbyterian Morgan Stanley Children's Hospi…. Hauptthemen laut MEDLINE: Deep Learning, Ultrasonography, Pneumonia, Lung. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Defense Sciences Office, DARPA, Bill and Melinda Gates Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and objectives Severe pneumonia is the leading cause of death among young children worldwide, disproportionately impacting children who lack access to advanced diagnostic imaging. Here our objectives were to develop and test the accuracy of an artificial intelligence algorithm for detecting features of pulmonary consolidation on point-of-care lung ultrasounds among hospitalized children.

Methods

This was a prospective, multicenter center study conducted at academic Emergency Department and Pediatric inpatient or intensive care units between 2018–2020. Pediatric participants from 18 months to 17 years old with suspicion of lower respiratory tract infection were enrolled. Bedside lung ultrasounds were performed using a Philips handheld Lumify C5-2 transducer and standardized protocol to collect video loops from twelve lung zones, and lung features at both the video and frame levels annotated. Data from both affected and unaffected lung fields were split at the participant level into training, tuning, and holdout sets used to train, tune hyperparameters, and test an algorithm for detection of consolidation features. Data collected from adults with lower respiratory tract disease were added to enrich the training set. Algorithm performance at the video level to detect consolidation on lung ultrasound was determined using reference standard diagnosis of positive or negative pneumonia derived from clinical data.

Results

Data from 107 pediatric participants yielded 117 unique exams and contributed 604 positive and 589 negative videos for consolidation that were utilized for the algorithm development process. Overall accuracy for the model for identification and localization of consolidation was 88.5%, with sensitivity 88%, specificity 89%, positive predictive value 89%, and negative predictive value 87%.

Conclusions

Our algorithm demonstrated high accuracy for identification of consolidation features on pediatric chest ultrasound in children with pneumonia. Automated diagnostic support on an ultraportable point-of-care device has important implications for global health, particularly in austere settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningUltrasonographyPneumoniaLungHumansChildChild, PreschoolMaleFemaleAdolescentInfantProspective StudiesAlgorithmsPoint-of-Care Systems

Autor:innen und Institutionen

  • Department of Emergency Medicine, Columbia University Vagelos College of Physicians & Surgeons, New York Presbyterian Morgan Stanley Children's Hospital, NY, NY, United States of America.
  • Oregon Health & Science University, Portland, Oregon, United States of America.
  • University of Oregon, Eugene, OR, United States of America.
  • Global Health Labs Inc, Bellevue, WA, United States of America.
  • University of Kentucky, Lexington, KY, United States of America.
  • University of Vermont Larner College of Medicine, Burlington, VT, United States of America.

ORCID-Profile: Matthew P Horning, Christina Lancioni

Förderung

  • Defense Sciences Office, DARPA
  • Bill and Melinda Gates Foundation

Zitieren

APA

Kessler, D., Zhu, M., Gregory, C. R., Mehanian, C., Avila, J., Avitable, N., Coneybeare, D., Das, D., Dessie, A., Kennedy, T. M., Rabiner, J., Malia, L., Ng, L., Nye, M., Vindas, M., Weimersheimer, P., Kulhare, S., Millin, R., Gregory, K., …, & Lancioni, C. (2024). Development and testing of a deep learning algorithm to detect lung consolidation among children with pneumonia using hand-held ultrasound. PLOS ONE, 19(8), e0309109. https://doi.org/10.1371/journal.pone.0309109

Vancouver

Kessler D, Zhu M, Gregory CR, Mehanian C, Avila J, Avitable N, et al. Development and testing of a deep learning algorithm to detect lung consolidation among children with pneumonia using hand-held ultrasound. PLOS ONE. 2024;19(8):e0309109. doi:10.1371/journal.pone.0309109

BibTeX
@article{Kessler2024,
  author = {Kessler, David and Zhu, Meihua and Gregory, Cynthia R and Mehanian, Courosh and Avila, Jailyn and Avitable, Nick and Coneybeare, Di and Das, Devjani and Dessie, Almaz and Kennedy, Thomas M and Rabiner, Joni and Malia, Laurie and Ng, Lorraine and Nye, Megan and Vindas, Marc and Weimersheimer, Peter and Kulhare, Sourabh and Millin, Rachel and Gregory, Kenton and Zheng, Xinliang and Horning, Matthew P and Stone, Mike and Wang, Fen and Lancioni, Christina},
  title = {Development and testing of a deep learning algorithm to detect lung consolidation among children with pneumonia using hand-held ultrasound},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {8},
  pages = {e0309109},
  doi = {10.1371/journal.pone.0309109}
}
Kostenlos starten →