ArticleEmergency radiology2022
Limited generalizability of deep learning algorithm for pediatric pneumonia classification on external data.
Article in Emergency radiology, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed, 24 citations in OpenAlex.
- Hepatobiliary phase radiomics for identifying subclinical liver dysfunction in compensated chronic liver disease: development and external validation.Abdominal radiology (New York) · 2026Article
- Pediatric radiology informatics within a larger academic practice.Pediatric radiology · 2026Review
- Cross-institutional validation of a polar map-free 3D deep learning model for obstructive coronary artery disease prediction using myocardial perfusion imaging: insights into generalizability and bias.European journal of nuclear medicine and molecular imaging · 2025Article
- Machine Learning in Pediatric Healthcare: Current Trends, Challenges, and Future Directions.Journal of clinical medicine · 2025Review
- A hybrid dense convolutional network and fuzzy inference system for pneumonia diagnosis with dynamic symptom tracking.PloS one · 2025Article
- Addressing Class Imbalance with Latent Diffusion-based Data Augmentation for Improving Disease Classification in Pediatric Chest X-rays.Proceedings. IEEE International Conference on Bioinformatics and Biomedicine · 2024Article
- Evaluating the Performance and Bias of Natural Language Processing Tools in Labeling Chest Radiograph Reports.Radiology · 2024Article
- Deep Learning for Pneumonia Detection in Chest X-ray Images: A Comprehensive Survey.Journal of imaging · 2024Review
- Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification.Diagnostics (Basel, Switzerland) · 2024Article
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images.PLOS digital health · 2024Article
- Can Deep Adult Lung Segmentation Models Generalize to the Pediatric Population?Expert systems with applications · 2023Article
- A review of PET attenuation correction methods for PET-MR.EJNMMI physics · 2023Review
- Tackling prediction uncertainty in machine learning for healthcare.Nature biomedical engineering · 2023Review
- Performance and Usability of Code-Free Deep Learning for Chest Radiograph Classification, Object Detection, and Segmentation.Radiology. Artificial intelligence · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors at 2 institutions in 2 countries.
Funding
No grant is acknowledged in the PubMed record.
Abstract
purpose(1) Develop a deep learning system (DLS) to identify pneumonia in pediatric chest radiographs, and (2) evaluate its generalizability by comparing its performance on internal versus external test datasets.
methodsRadiographs of patients between 1 and 5 years old from the Guangzhou Women and Children's Medical Center (Guangzhou dataset) and NIH ChestXray14 dataset were included. We utilized 5232 radiographs from the Guangzhou dataset to train a ResNet-50 deep convolutional neural network (DCNN) to identify pediatric pneumonia. DCNN testing was performed on a holdout set of 624 radiographs from the Guangzhou dataset (internal test set) and 383 radiographs from the NIH ChestXray14 dataset (external test set). Receiver operating characteristic curves were generated, and area under the curve (AUC) was compared via DeLong parametric method. Colored heatmaps were generated using class activation mapping (CAM) to identify important image pixels for DCNN decision-making.
resultsThe DCNN achieved AUC of 0.95 and 0.54 for identifying pneumonia on internal and external test sets, respectively (p < 0.0001). Heatmaps generated by the DCNN showed the algorithm focused on clinically relevant features for images from the internal test set, but not for images from the external test set.
conclusionOur model had high performance when tested on an internal dataset but significantly lower accuracy when tested on an external dataset. Likewise, marked differences existed in the clinical relevance of features highlighted by heatmaps generated from internal versus external datasets. This study underscores potential limitations in the generalizability of such DLS models.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.