AI to support the early diagnosis of Systemic Sclerosis (SSc)

We recently published a joint work with the Department of Rheumatology, University Hospital of Zurich, the Department of Quantitative Biomedicine, and the Department of Rheumatology and Immunology, University Hospital Bern. The study assessed the capacity of AI to detect patterns of microangiopathy in nailfold capillaroscopy (NFC) images of patients with Systemic Sclerosis (SSc). We used local registers from the University Hospital Zurich and ‘off-the-shelf’ artificial intelligence models (ViT). In their editorial Maurizio Cutolo, Emanuele Gotelli and Vanessa Smith conclude, “the ViT is welcome and seems to represent a further valid system for an early and fast reading of the NFC images/morphological biomarkers in SSc, reaching for the first time the fusion of EULAR-validated algorithms for the delineation of the scleroderma pattern from the non-scleroderma pattern and artificial intelligence.

Interpretable Machine Learning

How can we better understand what our models are telling us?

Data Traffic Control - make your data files human-friendly

Data files are the building materials we work with every day, all day. Working with them should be effortless.

A Quest for Reproducible Data Science

Have you ever tried to reproduce someone else’s analysis and got different results?