Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1085
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-14T06:55:59.416819Z
status: published
lens: trace
sector: health
headline: Development and evaluation of a deep learning model for computer-aided diagnosis of neonatal pneumothorax on chest radiographs
dek: Background Neonatal pneumothorax can progress rapidly, yet detection on supine chest radiographs remains challenging. Objective To develop and evaluate an artificial intelligence model for detecting pneumothorax on supine neonatal chest radiographs. Materials and methods This retrospective single-center study included neonates admitted to the neonatal intensive care unit between January 2011 and December 2024. The dataset comprised 648 radiographs from 288 neonates with pneumothorax and 5,511 radiographs from 3,…
gain_title: A ResNet-18-based model trained on neonatal ICU radiographs detected pneumothorax on supine chest radiographs with AUC 0.975, 87.6% sensitivity and 95.3% specificity in the test set.
problem_title: Model performance may be influenced by underlying pulmonary abnormalities, and lung-level localization was substantially lower for left-lung pneumothorax at 67.6% compared to right-lung.
trace_subject: AI detection of pneumothorax on supine neonatal chest radiographs in NICU patients
gain_reading: A ResNet-18-based model trained on neonatal ICU radiographs detected pneumothorax on supine chest radiographs with AUC 0.975, 87.6% sensitivity and 95.3% specificity in the test set.
gain_evidence: area under the curve of 0.975 (95% confidence interval (CI), 0.961-0.986; sensitivity, 87.6%; specificity, 95.3%; accuracy, 94.5%; positive predictive value, 68.5%; negative predictive value, 98.5%) | model showed promising diagnostic performance for detecting pneumothorax on supine neonatal chest radiographs
problem_reading: Model performance may be influenced by underlying pulmonary abnormalities, and lung-level localization was substantially lower for left-lung pneumothorax at 67.6% compared to right-lung.
problem_evidence: Underlying pulmonary abnormalities may influence model performance | 48 of 71 left-lung instances (67.6%)
quick_read: Researchers developed and evaluated a ResNet-18-based deep learning model to detect pneumothorax on supine neonatal chest radiographs using a retrospective dataset from a single NICU between 2011 and 2024. The model was pre-trained on normal adult radiographs and tested on held-out neonatal cases with patient-level splitting and a fixed threshold from cross-validation.

By the September 2026 publication date, the model had demonstrated high test-set discrimination with AUC 0.975 and strong negative predictive value, but with lower left-lung localization and potential sensitivity to underlying lung disease. The findings suggest promise for computer-aided diagnosis in a challenging supine imaging context, while generalizability remains uncertain without multi-center prospective validation.
limitation: Single-center retrospective design limits generalizability, and underlying pulmonary abnormalities may degrade performance; authors state external validation is needed before clinical use.
tag: Dual reading
key_points: Retrospective single-center study of neonates admitted to the NICU between January 2011 and December 2024 with 648 pneumothorax radiographs from 288 neonates and 5,511 control radiographs from 3,377 controls. | Model used publicly available normal adult chest radiographs for pre-training and knowledge distillation, with data split at the patient level and eight-fold cross-validation to set threshold. | Grad-CAM localization matched clinically determined side in 84 of 92 right-lung instances (91.3%) but only 48 of 71 left-lung instances (67.6%).
rundown: The study assembled 648 radiographs from 288 neonates with pneumothorax and 5,511 radiographs from 3,377 controls from a single NICU over 13 years, splitting data at the patient level into training, validation and test sets.

A ResNet-18-based model was pre-trained on publicly available normal adult chest radiographs with knowledge distillation, and Grad-CAM was used for lung-level localization while logistic regression identified factors associated with misclassification.

Test set results showed high overall discrimination but asymmetric localization accuracy by side, and the authors flagged pulmonary comorbidities as a factor linked to misclassification requiring further external validation.
sources:
- peer_reviewed | Pediatric Radiology | https://doi.org/10.1007/s00247-026-06778-w | 2026-09-12
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

57e83cdb4b8a821af41e2a1020364e3e9a3c906cbb2241332938f3beb54dd451

previous

0000000000000000000000000000000000000000000000000000000000000000