Precision medicine: Externally validated explainable AI support tool for predicting sustainability of infliximab and vedolizumab in ulcerative colitis.

OBJECTIVE: Drug sustainability (DS), a surrogate marker for drug efficacy, is important, especially when aiming for precision medicine. However, it lacks reliable prediction methods. AIMS: To develop and externally validate a web-based artificial intelligence(AI)-derived tool for predicting DS of infliximab and vedolizumab in patients with moderate-to-severe Ulcerative Colitis (UC). METHODS: Data from three Israeli centers included infliximab or vedolizumab patients treated for >54 weeks. Sustainability meant no corticosteroids, hospitalizations or surgeries. Machine learning techniques predicted >54-week and overall DS using baseline clinical data. RESULTS: The model was developed using data from 246 patients from Rabin Medical Center and externally validated on 67 patients from Rambam Health Care Campus and Sheba Medical Center. No significant difference in DS was observed across the datasets. Most patients were biologic-naïve and primarily treated with vedolizumab. The model performed well, with an area under the ROC curve of 0.86, and showed good accuracy (65.5 %-76.9 %) across the test sets. CONCLUSIONS: The study introduces a novel, AI-based tool for predicting >54-week DS of infliximab and vedolizumab in moderate-to-severe UC, using baseline parameters. This can aid clinical decision-making in the framework of precision medicine, promising to optimize disease management while maintaining physician autonomy.

Vedolizumab Is Associated with Longer Drug Sustainability Compared to Infliximab in Moderate-to-Severe Ulcerative Colitis: Long-Term Real-World Cohort Data.

BACKGROUND AND AIM: Drug sustainability (DS) is a surrogate marker for treatment efficacy. We aimed to compare the DS of two main biologics used to treat moderate-to-severe ulcerative colitis (UC), infliximab (IFX) and vedolizumab (VDZ), in a real-world setting. METHODS: We conducted a retrospective cohort study at a tertiary medical center in Israel. We included patients treated between 1 December 2017 and 1 May 2021, who were followed for up to 300 weeks. DS was defined as corticosteroid-, surgical-, and hospitalization-free treatment. RESULTS: 217 patients with UC were included. VDZ had a significantly longer median DS of 265.6 weeks compared to IFX's 106.5 weeks (p = 0.001) in treatment-naïve patients, even when adjusting for disease severity (HR 0.55 95 CI 0.3-0.98, p = 0.042). In treatment-experienced patients, DS was comparable between IFX and VDZ (p = 0.593). CONCLUSIONS: VDZ showed significantly longer DS in treatment-naïve patients with UC compared to IFX, also when adjusted for disease severity. There was no difference in DS between VDZ and IFX in treatment-experienced patients and patients switching from one drug to another. VDZ may be a suitable first-line treatment for biologic-naïve patients with moderate-to-severe UC.