Prognostic Prediction Models for Ulcerative Colitis: Systematic Review and Meta-Analysis

Background: Ulcerative colitis (UC) is a chronic inflammatory disease with highly variable symptoms and severity. Prognostic models for UC support precision medicine by enabling personalized treatment strategies. However, the quality and clinical utility of these models remain inadequately assessed. Objective: This study aimed to systematically review and critically evaluate the development, performance, and applicability of prognostic prediction models for UC. Methods: To identify prognostic models for UC, a comprehensive search was conducted in PubMed, Embase, the Cochrane Library, Web of Science, SinoMed, China National Knowledge Infrastructure, Wanfang, and VIP Database up to November 2, 2024. Extracted data included study characteristics, model development methods, validation metrics (e.g., area under the curve [AUC], concordance index [C-index]). The risk of bias and applicability was evaluated using the Prediction Model Risk of Bias Assessment Tool (PROBAST). A meta-analysis was conducted to assess model performance. Results: A total of 30 studies involving 7,816 UC patients were included, with the largest numbers conducted in China (n=11) and Japan (n=4). Most studies were retrospective (n=22), with 67% being multi-center studies. The primary objectives of the UC prognostic models included predicting therapeutic effect and response to treatment, particularly to tumor necrosis factor-alpha inhibitors (e.g., infliximab, adalimumab), and assessing risks of surgery, disease progression, or relapse. Logistic regression was the most frequently used method for both predictor selection (n=6) and model construction (n=12). Common predictors included age, C-reactive protein, albumin, hemoglobin, disease extent, and Mayo scores. The meta-analysis yielded a pooled AUC of 0.86 (95% confidence interval [CI]: 0.80-0.92). Most studies exhibited a high risk of bias (n=29), particularly in participant selection and statistical analysis. Applicability concerns were identified in 18 studies, primarily due to subgroup-specific designs that limited the generalizability of the findings. External validation data (n=16) were limited, and only a small number of studies (n=14) included calibration curves or decision curve analysis. Conclusions: This study demonstrates that prognostic models for UC have some potential in predictive performance and clinical application. However, most models are constrained by high bias risk, insufficient external validation, and limited generalizability due to small sample sizes and subgroup-specific designs. Future research should prioritize multi-center validations, refine model development approaches, and enhance model applicability to support broader clinical implementation. Clinical Trial: PROSPERO CRD42024609424; https://www.crd.york.ac.uk/PROSPERO/view/CRD42024609424