BIO20-027: Comparison of Treatment Plans Feasible Through AI Enabled Multidisciplinary Online Tumor Board Solution vs. NCCN Based Clinical Decision Support System (CDSS)

Background: Multidisciplinary tumor boards at Academic Medical Centers (AMC) maximize cancer outcomes. Guidelines based CDSS are alternatives to determine care pathways. Since 2015, 300 AMC cancer experts in USA and India use an AI enabled online tumor board solution, “NAVYA,” to scale low cost access to multidisciplinary expertise, on 1-2 minutes of expert time per decision (ASCO 2017). Methods: This is a prospective cohort analysis of patients of all GI patients who used NAVYA between 5/1/15-8/31/19 were analyzed. Actionable treatment plans generated by NAVYA were compared to NCCN based CDSS. Actionable treatment plans include chemotherapy protocols (doses, frequencies), radiation protocols (sites, fractions), etc. Overarching modality and specialty level decisions (CT-RT vs. surgery) lack specificity, and were deemed inactionable. NAVYA recommendations that did not map with NCCN are reported in detail. Results: 1300 patients (4600 treatment decisions) were analyzed: 61% (792) male, 80% between age 45 to 75, mostly with Colon, Pancreas, Gallbladder, Rectum, or Stomach cancer; 49.7% non-metastatic. Cohort was comparable to GLOBOCAN estimates. In 82.2% (3781/4600) decisions, NAVYA added value beyond NCCN. First, in 4.57% (210/4600), NAVYA recommended a patient-specific treatment plan that was not part of NCCN. Specific substitutions such as Capecitabine for 5-FU, Carboplatin for Cisplatin, and Paclitaxel for Docetaxel that were not part of NCCN were made to for patient tolerance of therapy. Second, in 2.5% (115/4600), NAVYA recommended treatments plan for clinical scenarios not covered by NCCN such as 2nd line therapy for metastatic biliary tract tumors, 3rd line treatments for patients with good ECOG, lack of clarity in diagnosis or conflicting diagnostic reports. Third, in 75.85% (3489/4600), NAVYA used patient specific criteria including resource constraints and patient preference to choose a treatment plan amongst the multiple pathways provided by NCCN and added actionable treatment details. Only in 17.09% (786/4600) decisions was NCCN based CDSS directly actionable without further expert input through NAVYA. Conclusions: Guideline based CDSS alone are insufficient to make the vast majority of individualized treatment decisions. Scaling rapid access to multidisciplinary experts is critical. Leapfrogging existing guidelines based CDSS, NAVYA online tumor board makes actionable expert treatment plans possible at a large scale.