Background Psoriasis is an emerging paradoxical side effect in patients with inflammatory bowel disease (IBD) when treated with anti‐TNF alpha. Patients with severe skin lesions unresponsive to topical therapy need to withdraw from treatment. Aim To estimate the incidence of paradoxical psoriasis in a large cohort of IBD patients treated with anti‐TNF alpha and to analyse its clinical correlates. Methods A retrospective cohort study on all IBD patients who started anti‐TNF alpha at our IBD Centre from January 2008 to December 2013 was performed. Proportional hazards regression models were used to estimate the association between each predictor and time to the development of psoriasis. Time‐dependent predictors were updated at each available time point. Results Four hundred and two patients were included. Participants contributed a total of 839 person‐years of follow‐up, during which 42 incident cases of psoriasis were recorded, with an incidence rate of five per 100 person‐years. Cox‐regression survival analysis revealed smoking as independent predictor of psoriasis (HR: 2.37, 95% CI: 1.36–4.48; P = 0.008). Conversely, concomitant immunosuppressive therapy was inversely related to psoriasis (HR: 0.33, 95% CI: 0.12–0.92; P = 0.03). Conclusions Paradoxical psoriasis is a relevant side effect of anti‐TNF alpha therapy, with an incidence rate of five per 100 person‐years. Smoking is confirmed as the main risk factor for developing lesions. The combination therapy with anti‐TNF alpha plus immunosuppressants is associated with a reduced risk of paradoxical psoriasis.

Extracellular vesicles (EVs) are increasingly recognized as promising non-invasive biomarkers for cancer and other diseases, but their clinical translation remains limited by the lack of comprehensive characterization strategies. Spectroscopic approaches such as Fourier-transform infrared (FTIR) spectroscopy can provide a global biochemical fingerprint of intact EVs, but their interpretation requires advanced analytical tools. In this study, we applied an autoencoder-based framework to attenuated total reflection FTIR (ATR-FTIR) spectra of blood-derived components, including plasma, red blood cells (RBCs), RBC-ghosts, and EVs, comprising 278 samples collected from 135 patients, to obtain latent features capable of capturing biologically meaningful variability. The autoencoder compressed spectra into 12 latent features while preserving spectral information with low reconstruction error. Unsupervised UMAP projection of the latent features separated the blood components into different clusters, supporting their biological relevance. The model was then applied to EV spectra from patients with hepatocellular carcinoma (HCC) and cirrhotic controls. Four features significantly differed between the two groups, and an elastic-net regularized logistic model evaluated with a leave-one-out cross-validation framework retained a single latent feature, achieving an out-of-fold ROC AUC of 0.785 (95% CI 0.602–0.967), with performance broadly comparable to that typically reported for AFP, the most commonly used biomarker for HCC. This study provides the first proof-of-concept that an autoencoder can be applied to FTIR spectra of EVs, extracting biologically relevant latent features with potential application in cancer detection.