PICaSSO Histologic Remission Index (PHRI) in Ulcerative Colitis – Development of a Novel Simplified Histological Score for Monitoring Mucosal Healing and Predicting Clinical Outcomes and its Applicability in an Artificial Intelligence System

Histological assessment is critical for the management of ulcerative colitis (UC). We aimed to develop a simple histologic index, aligned to endoscopy, correlated with clinical outcomes, and easy to apply to a computer aided diagnosis (CAD) system to evaluate inflammatory activity. Methods We analysed 614 biopsies from 307 UC patients enrolled into our prospective multicentre study, exploring the correlations between histological and endoscopic scores as well as adverse clinical outcomes. We then developed the PICaSSO histologic remission index (PHRI) and validated its reproducibility in comparison to multiple histologic indices. Finally, to implement PHRI into a CAD system, we trained and tested a novel deep learning strategy based on a convolutional neural network architecture to detect neutrophils, calculate PHRI and identify active from quiescent UC using a subset of 84 biopsies. Results PHRI showed the strongest correlation with endoscopic scores (MES, UCEIS, and PICaSSO) and with clinical outcomes. Our inter-reader agreement was almost perfect (ICC 0.84). A PHRI score of 1 could accurately stratify patients’ risk of adverse outcomes within 12 months. Our preliminary artificial intelligence algorithm identified active from quiescent UC with 80% sensitivity and 100% specificity. Conclusions PHRI is the simplest histological index in UC and it exhibits the highest correlation with endoscopic activity and clinical outcomes. A PHRI-based CAD was accurate in predicting histologic remission.