ABSTRACT
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.
ABSTRACT
BACKGROUND: The field of artificial intelligence (AI) is poised to significantly influence the future of medicine. With the accumulation of vast databases and recent advancements in computer science methods, AI's capabilities have been demonstrated in numerous areas, from diagnosis and morbidity prediction to patient treatment. Establishing an AI research and development unit within a medical center offers multiple advantages, particularly in fostering research and tapping into the immediate potential of AI at the patient's bedside. OBJECTIVES: To outline the steps taken to establish a center for AI and big data within an innovation center at a tertiary hospital in Israel. METHODS: We conducted a retrospective analysis of projects developed in the field of AI at the Artificial Intelligence Center at the Rabin Medical Center, examining trends, clinical domains, and the predominant sectors over a specific period. RESULTS: Between 2019 and 2023, data from 49 AI projects were gathered. A substantial and consistent growth in the number of projects was observed. Following the inauguration of the Artificial Intelligence Center we observed an increase of over 150% in the volume of activity. Dominant sectors included cardiology, gastroenterology, and anesthesia. Most projects (79.6%) were spearheaded by physicians, with the remainder by other hospital sectors. Approximately 59.2% of the projects were applied research. The remainder were research-based or a mix of both. CONCLUSIONS: Developing technological projects based on in-hospital medical data, in collaboration with clinicians, is promising. We anticipate the establishment of more centers dedicated to medical innovation, particularly involving AI.
