期刊
UNITED EUROPEAN GASTROENTEROLOGY JOURNAL
卷 10, 期 8, 页码 836-843出版社
JOHN WILEY & SONS LTD
DOI: 10.1002/ueg2.12268
关键词
algorithm; calprotectin; flare; inflammatory bowel disease; machine learning; relapse; ulcerative colitis
资金
- DiaSorin SpA
This study demonstrates that measuring FC levels with the LIAISON (R) Calprotectin assay before relapse can predict relapse in patients with quiescent UC. Furthermore, the accuracy of prediction can be improved using machine learning methods and including other variables in the algorithm.
Introduction: Fecal calprotectin (FC) is established as a diagnostic marker to differentiate between inflammatory bowel diseases and non-inflammatory conditions. Furthermore, it may be effective in monitoring response to treatment, and to predict relapse during maintenance therapy. Design: This was a prospective longitudinal study carried out in Italy, France and Spain. The primary objective was to correlate the LIAISON (R) Calprotectin assay measurements to quiescent ulcerative colitis (UC) or relapse as assessed by clinical data. Patients were assessed every 3 months for 12 months, and at 18 months. Results: The last FC measured prior to relapse was the variable that predicted relapse in a statistically significant manner. With a 62.3 mu g/g cut-off the area under the curve was 0.619, and the sensitivity was 62.9% (95% Confidence Interval [CI] 44.9%-78.5%) and specificity 63.0% (95% CI 53.1%-72.1%). Using machine learning methods, the last FC measurement was shown to have the largest impact in predicting relapse. An algorithm was developed that included other variables available following a clinician's visit, which resulted in an area under the curve of 0.754 for predicting relapse. Conclusion: In the present study FC measured by the LIAISON (R) Calprotectin assay on the visit before relapse is predictive of relapse in patients with quiescent UC. In a proof of concept, the accuracy of prediction can further be improved including other variables in an algorithm developed by machine learning.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据