ArticleJournal of medical Internet research2024
Impact of Gold-Standard Label Errors on Evaluating Performance of Deep Learning Models in Diabetic Retinopathy Screening: Nationwide Real-World Validation Study.
Article in Journal of medical Internet research, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 6 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
6 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Deep learning for cardiac CT segmentation for congenital heart disease: A systematic review.PloS one · 2026Pooled it
- Use and Performance of Language-based Artificial Intelligence (AI) Models to Screen for Depressive Disorders.Current psychiatry reports · 2026Review
- The AI-Augmented Ophthalmologist for chronic ocular diseases: a patient-centered framework for human-AI collaboration.Frontiers in cell and developmental biology · 2026Review
- A scoping review of artificial intelligence as a medical device for ophthalmic image analysis in Europe, Australia and America.NPJ digital medicine · 2025Article
- Research progress of artificial intelligence in the early screening, diagnosis, precise treatment and prognosis prediction of three central gynecological malignancies.Frontiers in oncology · 2025Review
- Segmentation of Low-Grade Brain Tumors Using Mutual Attention Multimodal MRI.Sensors (Basel, Switzerland) · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundFor medical artificial intelligence (AI) training and validation, human expert labels are considered the gold standard that represents the correct answers or desired outputs for a given data set. These labels serve as a reference or benchmark against which the model's predictions are compared.
objectiveThis study aimed to assess the accuracy of a custom deep learning (DL) algorithm on classifying diabetic retinopathy (DR) and further demonstrate how label errors may contribute to this assessment in a nationwide DR-screening program.
methodsFundus photographs from the Lifeline Express, a nationwide DR-screening program, were analyzed to identify the presence of referable DR using both (1) manual grading by National Health Service England-certificated graders and (2) a DL-based DR-screening algorithm with validated good lab performance. To assess the accuracy of labels, a random sample of images with disagreement between the DL algorithm and the labels was adjudicated by ophthalmologists who were masked to the previous grading results. The error rates of labels in this sample were then used to correct the number of negative and positive cases in the entire data set, serving as postcorrection labels. The DL algorithm's performance was evaluated against both pre- and postcorrection labels.
resultsThe analysis included 736,083 images from 237,824 participants. The DL algorithm exhibited a gap between the real-world performance and the lab-reported performance in this nationwide data set, with a sensitivity increase of 12.5% (from 79.6% to 92.5%, P<.001) and a specificity increase of 6.9% (from 91.6% to 98.5%, P<.001). In the random sample, 63.6% (560/880) of negative images and 5.2% (140/2710) of positive images were misclassified in the precorrection human labels. High myopia was the primary reason for misclassifying non-DR images as referable DR images, while laser spots were predominantly responsible for misclassified referable cases. The estimated label error rate for the entire data set was 1.2%. The label correction was estimated to bring about a 12.5% enhancement in the estimated sensitivity of the DL algorithm (P<.001).
conclusionsLabel errors based on human image grading, although in a small percentage, can significantly affect the performance evaluation of DL algorithms in real-world DR screening.
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.