Pugliese Daniela, Privitera Giuseppe, Cersullo Nicola, Bordekar Harsh, Crispino Federica, Mezzina Nicolò, Pellegrini Lucienne, Allocca Mariangela, Laterza Lucrezia, Viola Anna, Bertani Lorenzo, Soru Pietro, Scrivo Barbara, Barberio Brigida, Ricci Chiara, Balestrieri Paola, Daperno Marco, Pluchino Dario, Rizzello Fernando, Scribano Maria Lia, Sablich Renato, Pastorelli Luca, Manguso Francesco, Variola Angela, Di Sario Antonio, Grossi Laurino, Ribaldone Davide Giuseppe, Biscaglia Giuseppe, Buda Andrea, Mocci Giammarco, Viscido Angelo, Di Paolo Maria Carla, Onali Sara, Rodino' Stefano, Coletta Marina, Principi Mariabeatrice, Miranda Agnese, Amato Arnaldo, Bezzio Cristina, Petruzzellis Carlo, Mazzuoli Silvia, Festa Stefano, Sartini Alessandro, Checchin Davide, Fanigliulo Libera, Gallina Sara, Cesarini Monica, Bodini Giorgia, Stradella Davide, Spagnuolo Rocco, Guidi Luisa, Savarino Edoardo, Cappello Maria, Caprioli Flavio, Costa Francesco, Fries Walter, Scaldaferri Franco, Fiorino Gionata, Castiglione Fabiana, Massari Alessandro, Orlando Ambrogio, Armuzzi Alessandro
Dipartimento di Medicina e Chirurgia Traslazionale, Università Cattolica del Sacro Cuore, L. Go A. Gemelli 8, 00168 Rome, Italy; UOC Pronto Soccorso, Medicina d'Urgenza e Medicina Interna, Ospedale Isola Tiberina Gemelli Isola, 00186 Rome, Italy; UOS Gastroenterologia, Ospedale Isola Tiberina Gemelli Isola, 00186 Rome, Italy.
Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy.
Dig Liver Dis. 2025 Jul;57(7):1393-1402. doi: 10.1016/j.dld.2025.04.021. Epub 2025 May 12.
Real-world studies on vedolizumab in inflammatory bowel disease (IBD) are often limited by small sample size and short follow-up. In this study, we investigated the 2-year effectiveness and safety of vedolizumab in patients with IBD, and applied eXplainable Artificial Intelligence (XAI) to identify predictors of both.
The Long-term Italian Vedolizumab Effectiveness (LIVE) study is multicentric, ambispective, observational study enrolling 1111 IBD patients (563 Crohn's disease, CD, 542 ulcerative colitis, UC). Steroid-free clinical remission (SFCR) at 24 months was the primary endpoint. A XAI model (eXtreme Gradient Boosting, XGB) was applied to identify the main clinical predictors of SFCR and development of adverse events (AEs).
Rates of SFCR at 24 months were 31.6 % and 39.7 % in CD and UC patients, and 0.14 AEs per patient-year was recorded. On XGB analysis, previous exposure to anti-TNFα and older age were the most important drivers for the prediction of SFCR; lower baseline CRP levels and fewer comorbidities were the most important features associated with no development of AEs.
Vedolizumab is effective and safe in IBD patients. XAI yielded promising results in identifying the most important predictors of SFCR and development of AEs.
关于维多珠单抗治疗炎症性肠病（IBD）的真实世界研究往往受限于样本量小和随访时间短。在本研究中，我们调查了维多珠单抗治疗IBD患者的2年有效性和安全性，并应用可解释人工智能（XAI）来识别两者的预测因素。
意大利维多珠单抗长期有效性（LIVE）研究是一项多中心、双向、观察性研究，纳入了1111例IBD患者（563例克罗恩病，CD；542例溃疡性结肠炎，UC）。24个月时的无类固醇临床缓解（SFCR）是主要终点。应用XAI模型（极端梯度提升，XGB）来识别SFCR和不良事件（AE）发生的主要临床预测因素。
CD和UC患者24个月时的SFCR率分别为31.6%和39.7%，每位患者每年记录到0.14次AE。在XGB分析中，既往使用抗TNFα和年龄较大是预测SFCR的最重要因素；较低的基线CRP水平和较少的合并症是与未发生AE相关的最重要特征。
维多珠单抗治疗IBD患者有效且安全。XAI在识别SFCR和AE发生的最重要预测因素方面取得了有前景的结果。
