P121 Clinicomic profiles new feature patterns based on a simplified location classification for Crohn’s disease

Abstract Background Crohn’s disease (CD) is a heterogeneous and complicated condition that often has delayed diagnoses poor outcomes. Disease location site-specific mechanisms have received increasing attention in recent studies. Suboptimal classification adds complexity to clinical management for CD the interpretation of its characteristics. This study aims clarify clinicopathological characteristics patients through prospective cohort. Methods The data from 1173 with definite simplified based on anatomical traits (G1: esophagus+stomach+duodenum; G2: jejunum+ileum; G3: ileocecum; G4: colon+rectum) were used feature patterns (Figure 1). Results Of enrolled patients, 437 newly diagnosed, 736 prevalent patients. A higher proportion L4 involvement (45.8%) lower L2 (6.8%) observed under Montreal classification. Single G2 (17.8%), G2+G3 (22.2%), G3+G4 (12.5%) G2+G3+G4 (27.8%) four major types 2A-2B). G4 presented C-reactive protein, had more stricturing/penetrating behavior, single oldest age at diagnosis (Table clinicomic machine learning methods including principal component analysis, cluster analysis partial least squares discriminant identified hemoglobin, platelet count protein as three key indicators. decision tree indicators behavior stratified all into six (simply/complicatedly active, simply/complicatedly anemia stable), which formed two-twisted-cycle model natural history 2C). Most started their cycles active phase, “simply” cycle was mainly advanced by medications, while most “complicatedly” needed multidisciplinary care. Comparisons among subgroups showed same rise-and-fall pattern G2+G4- proportion, G2-G4+ opposite trend 2, Figure 2D-2E). An external validation group (n=301) confirmed above results. role could be interpreted an important factor determining start point trajectory model. Conclusion Site-specific clarified classification, new profiled may provide insights phenotyping, risk stratification precision treatment.