Artificial intelligence for nailfold capillaroscopy analyses - a proof of concept application in juvenile dermatomyositis.
Peyman Hosseinzadeh KassaniLouis EhwerhemuephaChloe Martin-KingRyan KassabEllie GibbsGabrielle MorganLauren M PachmanPublished in: Pediatric research (2023)
Proposed NFC-Net can accurately predict children with JDM from healthy controls using nailfold capillaroscopy (NFC) images. Additionally, it predicts the scores to JDM disease activity versus no activity. Equipped with gradients, NFC-Net is explainable and gives visual information beside the reported accuracies. NFC-Net is computationally efficient since it is applied to substantially downscaled NFC images. Furthermore, the model can be wrapped within an edge-based device like a mobile application that is accessible to both clinicians and patients.
Keyphrases
- disease activity
- artificial intelligence
- deep learning
- rheumatoid arthritis
- systemic sclerosis
- systemic lupus erythematosus
- end stage renal disease
- rheumatoid arthritis patients
- machine learning
- interstitial lung disease
- ankylosing spondylitis
- big data
- ejection fraction
- convolutional neural network
- newly diagnosed
- chronic kidney disease
- peritoneal dialysis
- juvenile idiopathic arthritis
- palliative care
- prognostic factors
- young adults
- social media