1014 Is there a role for a multidisciplinary tumor board smart virtual assistant in locally advanced cervical carcinoma? A proof of concept

Introduction/Background* The first prototype of the “Multidisciplinary Tumor Board Smart Virtual Assistant” is presented. Methodology Data from patients affected by invasive carcinoma of the cervix (LACC), FIGO stage IB2-IVa, treated between 2015 and 2018 were extracted. Magnetic Resonance (MR), Gynecologic examination under general anesthesia (EAU), and Positron Emission Tomography–Computed Tomography (PET-CT) performed at the time of diagnosis were the items from the Electronic Health Records (eHRs) considered for analysis. An automated extraction of eHR that capture the patient’s data before the diagnosis and then, through Natural Language Processing (NLP), analysis and categorization of all data to transform source information into structured data has been performed. Thereafter, an Artificial Intelligence method was developed to support the clinical staff in their decision with regards to tumor staging and to help them identifying the most complex cases where deeper analysis and discussion were required (e. g. conflicting information from different exams). Result(s)* In the first round, the system has been used to retrieve all the eHR for the 96 patients with LACC. This was the training set of the study, with validated 2009 FIGO staging classification ranging from I B2 to IV A as output. For these patients, available eHR included MR, EUA, and PET-CT diagnostic reports. The system has been able to classify all patients belonging to the training set and - through the NLP procedures - the clinical features were analyzed and classified for each patient. A second important result was the setup of a predictive model to evaluate the patient’s staging. Our approach has led to predict patient’s staging within an accuracy of 94%. Lastly we created a user-oriented operational tool targeting the MTB who are confronted with the challenge of large volumes of patients to be diagnosed in the most accurate way. The resulting decision support system is summarized in figure 1. Furthermore, the MTB Smart DA was tested in a 13 LACC patients validation cohort showing an accuracy of 93%, in line with the training set performances. Conclusion* This is the first proof of concept concerning the possibility of creating a smart virtual assistant for the MTB. A significant benefit could come from the integration of these automated methods in the collaborative, crucial decision stages.