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

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.
Competing Interests: Dr. Kenton Gregory received compensation as Principal Investigator for a DARPA award to Inventive Government Solutions Inc, previously owned by Intellectual Ventures Laboratory. Dr. Kenton Gregory also received compensation as a Fellow from Intellectual Ventures Laboratory for a portion of this work. This potential conflict for Drs. Kenton and Cynthia Gregory has been reviewed and managed by OHSU. Since the time this research was completed, Global Health Labs Inc. acquired all the assets of Inventive Government Solutions and Intellectual Ventures Laboratory. Drs. Mehanian and Millin, as well as S. Kulhare and M. Horning, received salary support through Global Health Labs Inc., a non-profit organization that may have a commercial interest in the results of this research and technology. Global Health Labs Inc. has been awarded proprietary ownership of the code utilized in the algorithm. These commercial affiliations do not alter our adherence to PLOS ONE policies on sharing data and materials
(Copyright: © 2024 Kessler et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)