Artificial Intelligence to Differentiate Pediatric Pseudopapilledema and True Papilledema on Fundus Photographs.

PURPOSE: To develop and test an artificial intelligence (AI) model to aid in differentiating pediatric pseudopapilledema from true papilledema on fundus photographs.

DESIGN: Multicenter retrospective study.

SUBJECTS: A total of 851 fundus photographs from 235 children (age < 18 years) with pseudopapilledema and true papilledema.

METHODS: Four pediatric neuro-ophthalmologists at 4 different institutions contributed fundus photographs of children with confirmed diagnoses of papilledema or pseudopapilledema. An AI model to classify fundus photographs as papilledema or pseudopapilledema was developed using a DenseNet backbone and a tribranch convolutional neural network. We performed 10-fold cross-validation and separately analyzed an external test set. The AI model's performance was compared with 2 masked human expert pediatric neuro-ophthalmologists, who performed the same classification task.

MAIN OUTCOME MEASURES: Accuracy, sensitivity, and specificity of the AI model compared with human experts.

RESULTS: The area under receiver operating curve of the AI model was 0.77 for the cross-validation set and 0.81 for the external test set. The accuracy of the AI model was 70.0% for the cross-validation set and 73.9% for the external test set. The sensitivity of the AI model was 73.4% for the cross-validation set and 90.4% for the external test set. The AI model's accuracy was significantly higher than human experts on the cross validation set ( P  < 0.002), and the model's sensitivity was significantly higher on the external test set ( P  = 0.0002). The specificity of the AI model and human experts was similar (56.4%-67.3%). Moreover, the AI model was significantly more sensitive at detecting mild papilledema than human experts, whereas AI and humans performed similarly on photographs of moderate-to-severe papilledema. On review of the external test set, only 1 child (with nearly resolved pseudotumor cerebri) had both eyes with papilledema incorrectly classified as pseudopapilledema.

CONCLUSIONS: When classifying fundus photographs of pediatric papilledema and pseudopapilledema, our AI model achieved > 90% sensitivity at detecting papilledema, superior to human experts. Due to the high sensitivity and low false negative rate, AI may be useful to triage children with suspected papilledema requiring work-up to evaluate for serious underlying neurologic conditions.

FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.