Risk prediction model based on blood biomarkers for predicting moderate to severe endoscopic activity in patients with ulcerative colitis

Abstract

ObjectWe explored developing an internal validation model to predict the moderate to severe endoscopic activity of ulcerative colitis (UC) patients based on non-invasive or minimally-invasive parameters.MethodsUlcerative Colitis Endoscopic Index of Severity (UCEIS) and Mayo endoscopic subscore were performed for UC patients who met the criteria from January 2017 to August 2021 through the electronic database of our center. Logistic regression and a least absolute shrinkage and selection operator (Lasso) regression model were performed to screen the risk factors of moderate to severe UC activity. The nomogram was established subsequently. Discrimination of the model was evaluated using the concordance index (c-index), and the calibration plot and 1,000 Bootstrap were used to evaluate the model’s performance and conduct internal validation.ResultsSixty-five UC patients were included in this study. According to UCEIS criteria,45 patients were moderate to severe endoscopic activity. 26 potential predictors of UC were analyzed by logistic and Lasso regression showed that vitamin D (Vit D), albumin (ALB), prealbumin (PAB), and fibrinogen (Fbg) were the best predictors of moderate to severe endoscopic activity of UC. We used these 4 variables to develop a dynamic nomogram prediction model. The c-index was 0.860, which means good discrimination. The calibration plot and Bootstrap analysis showed that the prediction model accurately distinguished the moderate to severe endoscopic activity in UC patients. The prediction model was verified using a cohort of UC patients with moderate to severe activity defined by the Mayo endoscopic subscore, and it was found that the model still had good discrimination and calibration (c-index = 0.891).ConclusionThe model containing Vit D, ALB, PAB, and Fbg was a good tool for evaluating UC activity. The model is simple, accessible, and user-friendly, which has broad application prospects in clinical practice.

Serum Amyloid A as a non-invasive predictive biomarker of mucosal healing in ulcerative colitis patients

“…25 Compared with Mayo score, UCEIS can distinguish the depth of ulcers, precisely depict the actual endoscopic manifestations of patients with severe UC, and more accurately reflect clinical outcomes. 26 In such patients SAA was statistically significantly higher in mild disease in comparison to endoscopic remission as determined by Mayo score and UCEIS. And, also higher in severe and moderate disease than in mild disease according to MES (p <0.001).…”

Utility of four machine learning approaches for identifying ulcerative colitis and Crohn's disease

“…Consequently, researchers are currently exploring cost-effective and non-invasive ML techniques that are based on the results of routine laboratory tests for each study participant. Vitamin D, albumin, prealbumin and fibrinogen were screened as good biomarkers for assessing evaluating UC activity using logistic regression and a least absolute shrinkage and selection operator regression models [ 62 ]. ML models (random forest, adaptive boosting, K-nearest neighbors, support vector machines, naïve Bayes, ridge regression, and extreme gradient boosting) based on 33 different laboratory variables were used to assess the level of activity in IBD.…”

Análisis de la asociación entre el fibrinógeno sérico y la severidad de la colitis ulcerosa crónica idiopática: relevancia clínica

“…Además, nuestros hallazgos coinciden con investigaciones previas que también respaldan el papel del fibrinógeno como un predictor de actividad en la CUCI. Varios estudios han señalado que los niveles de fibrinógeno se correlacionan positivamente con la severidad de la actividad endoscópica de la enfermedad 16,17,20,21 . Además, se ha observado una mayor severidad histológica en pacientes con CUCI en relación con el incremento de niveles de fibrinógeno 22 .…”