BICL leader publishes groundbreaking AI study on differentiation of different rheumatologic diseases

Frank Roemer, MD, BICL’s CMO and Director of Research, together with his colleagues from the Rheumatology/Immunology and AI Departments of the Friedrich-Alexander-University of Erlangen-Nürnberg (FAU), Germany, as senior author published a landmark paper on the capabilities of an AI algorithm to differentiate different rheumatologic disease entities such as RA and psoriatic arthritis based on MRI data. The researchers investigated MRI scans from 649 patients (135 seronegative RA, 190 seropositive RA, 177 PsA, 147 psoriasis) that were fed into ResNet neural networks. AUROC was 75% for seropositive RA vs. PsA, 74% for seronegative RA vs. PsA and 67% for seropositive vs. seronegative RA. All MRI sequences were relevant for classification. The study supports the potential of AI in helping establishing a correct rheumatologic diagnosis based on MRI only. Find the full paper here:

Advanced neural networks for classification of MRI in psoriatic arthritis, seronegative, and seropositive rheumatoid arthritis. Folle L, Bayat S, Kleyer A, Fagni F, Kapsner LA, Schlereth M, Meinderink T, Breininger K, Tacilar K, Krönke G, Uder M, Sticherling M, Bickelhaupt S, Schett G, Maier A, Roemer F, Simon D.Rheumatology (Oxford). 2022 Mar 25:keac197. doi: 10.1093/rheumatology/keac197.