Multidisciplinary Tumor Board Smart Virtual Assistant in Locally Advanced Cervical Cancer: A Proof of Concept

AimThe first prototype of the “Multidisciplinary Tumor Board Smart Virtual Assistant” is presented, aimed to (i) Automated classification of clinical stage starting from different free-text diagnostic reports; (ii) Resolution of inconsistencies by identifying controversial cases drawing the clinician’s attention to particular cases worthy for multi-disciplinary discussion; (iii) Support environment for education and knowledge transfer to junior staff; (iv) Integrated data-driven decision making and standardized language and interpretation.Patients and MethodData from patients affected by Locally Advanced Cervical Cancer (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.ResultsIn the first round, the system has been used to retrieve all the eHR for the 96 patients with LACC. 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 (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.ConclusionThis 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.

INNV-16. CNS-TAP TOOL RECOMMENDATIONS OF TARGETED ANTI-CANCER AGENTS COMPARED TO THOSE SELECTED BY A MULTIDISCIPLINARY TUMOR BOARD IN A MOLECULARLY-DRIVEN DIPG CLINICAL TRIAL (PNOC003)

Genetic sequencing of diffuse intrinsic pontine gliomas (DIPG) has revealed genomic heterogeneity, sparking an interest in individualized and targeted treatment options for this particularly devastating disease. A feasibility study, PNOC003: Molecular Profiling for Individualized Treatment Plan for DIPG (NCT02274987), was completed within the Pacific Pediatric Neuro-Oncology Consortium. In this study, a multidisciplinary tumor board reviewed detailed molecular and genomic profiling of each participant’s tumor and made molecularly-targeted treatment recommendations. Separately, our team developed the Central Nervous System Targeted Agent Prediction (CNS-TAP) tool, which combines pre-clinical, clinical, and CNS penetration data with patient-specific genomic information to derive numeric scores for targeted anticancer agents, aimed to objectively evaluate these therapies for use in patients with CNS tumors. We hypothesized that highly-scored agents within CNS-TAP would overlap with the agents recommended by the tumor board in PNOC003. For each study participant, we used the genomic profiling report to identify actionable alterations and incorporated these data into CNS-TAP to identify the highest-scoring agents. We compared high-scoring agents within CNS-TAP with recommendations from the tumor board for each of the enrolled 28 participants. Overall, 93% of patients (26/28) had at least one agent recommended by both the tumor board and CNS-TAP. Additionally, 38% of all agents (36/95) recommended by the tumor board were also selected by CNS-TAP. We identified factors that likely contributed to the differences in therapy recommendations between these two methods: CNS-TAP requires additional clinician input to account for drug-drug interactions, includes only classically-defined anticancer agents, and cannot easily be updated in real-time as new data emerge. However, CNS-TAP provides an objective evaluation of targeted therapies, whereas tumor boards are inherently subjective. A prospective study incorporating both CNS-TAP and a molecular tumor board for targeted therapy selection in high-grade glioma is currently ongoing to further compare and objectively evaluate these methods.