ArticleIEEE access : practical innovations, open solutions2021
Discovery of a Generalization Gap of Convolutional Neural Networks on COVID-19 X-Rays Classification.
Article in IEEE access : practical innovations, open solutions, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 18 papers, 1 of them a synthesis that pooled it.
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
18 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Public Covid-19 X-ray datasets and their impact on model bias - A systematic review of a significant problem.Medical image analysis · 2021Pooled it
- From Embeddings to Accuracy: Comparing Foundation Models for Radiographic Classification.Journal of imaging informatics in medicine · 2026Article
- CIRCA: comprehensible online system in support of chest X-rays-based screening by COVID-19 example.Scientific reports · 2025Article
- Tailoring task arithmetic to address bias in models trained on multi-institutional datasets.Journal of biomedical informatics · 2025Article
- Deep Learning for Pneumonia Detection in Chest X-ray Images: A Comprehensive Survey.Journal of imaging · 2024Review
- Joint classification and segmentation for an interpretable diagnosis of acute respiratory distress syndrome from chest x-rays.Journal of medical imaging (Bellingham, Wash.) · 2023Article
- A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer inEuropean journal of nuclear medicine and molecular imaging · 2023Article
- A Web-Based Platform for the Automatic Stratification of ARDS Severity.Diagnostics (Basel, Switzerland) · 2023Article
- Biases associated with database structure for COVID-19 detection in X-ray images.Scientific reports · 2023Article
- DeepHeme: A generalizable, bone marrow classifier with hematopathologist-level performance.bioRxiv : the preprint server for biology · 2023Article
- RETRACTED ARTICLE: Covid-19 classification using sigmoid based hyper-parameter modified DNN for CT scans and chest X-rays.Multimedia tools and applications · 2023Article
- Generalizability assessment of COVID-19 3D CT data for deep learning-based disease detection.Computers in biology and medicine · 2022Article
- BEMD-3DCNN-based method for COVID-19 detection.Computers in biology and medicine · 2022Article
- Automatic coronavirus disease 2019 diagnosis based on chest radiography and deep learning - Success story or dataset bias?Medical physics · 2022Article
- Generalization Challenges in Drug-Resistant Tuberculosis Detection from Chest X-rays.Diagnostics (Basel, Switzerland) · 2022Article
- New patch-based strategy for COVID-19 automatic identification using chest x-ray images.Health and technology · 2022Article
- Current limitations to identify covid-19 using artificial intelligence with chest x-ray imaging (part ii). The shortcut learning problem.Health and technology · 2021Review
- Lessons learned in transitioning to AI in the medical imaging of COVID-19.Journal of medical imaging (Bellingham, Wash.) · 2021Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
A number of recent papers have shown experimental evidence that suggests it is possible to build highly accurate deep neural network models to detect COVID-19 from chest X-ray images. In this paper, we show that good generalization to unseen sources has not been achieved. Experiments with richer data sets than have previously been used show models have high accuracy on seen sources, but poor accuracy on unseen sources. The reason for the disparity is that the convolutional neural network model, which learns features, can focus on differences in X-ray machines or in positioning within the machines, for example. Any feature that a person would clearly rule out is called a confounding feature. Some of the models were trained on COVID-19 image data taken from publications, which may be different than raw images. Some data sets were of pediatric cases with pneumonia where COVID-19 chest X-rays are almost exclusively from adults, so lung size becomes a spurious feature that can be exploited. In this work, we have eliminated many confounding features by working with as close to raw data as possible. Still, deep learned models may leverage source specific confounders to differentiate COVID-19 from pneumonia preventing generalizing to new data sources (i.e. external sites). Our models have achieved an AUC of 1.00 on seen data sources but in the worst case only scored an AUC of 0.38 on unseen ones. This indicates that such models need further assessment/development before they can be broadly clinically deployed. An example of fine-tuning to improve performance at a new site is given.
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.