A deep learning system for differential diagnosis of skin diseases

Abstract

Skin conditions affect an estimated 1.9 billion people worldwide. A shortage of dermatologists causes long wait times and leads patients to seek dermatologic care from general practitioners. However, the diagnostic accuracy of general practitioners has been reported to be only 0.24-0.70 (compared to 0.77-0.96 for dermatologists), resulting in referral errors, delays in care, and errors in diagnosis and treatment. In this paper, we developed a deep learning system (DLS) to provide a differential diagnosis of skin conditions for clinical cases (skin photographs and associated medical histories). The DLS distinguishes between 26 skin conditions that represent roughly 80% of the volume of skin conditions seen in primary care. The DLS was developed and validated using de-identified cases from a teledermatology practice serving 17 clinical sites via a temporal split: the first 14,021 cases for development and the last 3,756 cases for validation. On the validation set, where a panel of three board-certified dermatologists defined the reference standard for every case, the DLS achieved 0.71 and 0.93 top-1 and top-3 accuracies respectively. For a random subset of the validation set (n=963 cases), 18 clinicians reviewed the cases for comparison. On this subset, the DLS achieved a 0.67 top-1 accuracy, non-inferior to board-certified dermatologists (0.63, p<0.001), and higher than primary care physicians (PCPs, 0.45) and nurse practitioners (NPs, 0.41). The top-3 accuracy showed a similar trend: 0.90 DLS, 0.75 dermatologists, 0.60 PCPs, and 0.55 NPs. These results highlight the potential of the DLS to augment general practitioners to accurately diagnose skin conditions by suggesting differential diagnoses that may not have been considered. Future work will be needed to prospectively assess the clinical impact of using this tool in actual clinical workflows.

References in corpus (2)

• Popular Ensemble Methods: An Empirical Study
• Prototypical Clustering Networks for Dermatological Disease Diagnosis

Cited by in corpus (19)

• Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary
• Disparities in Dermatology AI: Assessments Using Diverse Clinical Images
• Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set
• Integrated multimodal artificial intelligence framework for healthcare applications
• Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification
• Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing
• Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions
• Early Melanoma Diagnosis with Sequential Dermoscopic Images
• Annotation-efficient cancer detection with report-guided lesion annotation for deep learning-based prostate cancer detection in bpMRI
• Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study
• Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images
• Automated Ensemble Multimodal Machine Learning for Healthcare
• AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI
• Crowdsourcing Dermatology Images with Google Search Ads: Creating a Real-World Skin Condition Dataset
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• Improving Acne Image Grading with Label Distribution Smoothing
• Tissue Concepts: supervised foundation models in computational pathology
• eSkinHealth: A Multimodal Dataset for Neglected Tropical Skin Diseases
• Evaluating AI systems under uncertain ground truth: a case study in dermatology