Abstract A63: Overcoming challenges in health care with machine learning: Innovation from retinoblastoma

Abstract

Abstract Introduction: As retinoblastoma is a rare pediatric cancer (1/17,000 live births) with little evidence to justify treatment choices, we built a cloud-based retinoblastoma-specific electronic health record database for point-of-care data to support clinical and research collaboration and provide a quantitative analysis of prescribed treatments. Methods: Disease-specific Electronic Patient Illustrated Clinical Timeline (DEPICT HEALTH) is online, cloud-based, interactive, with point-of-care timelines and corresponding retinal/tumor drawings, with standardized scoring of tumor number, size, and locations. Results: DEPICT HEALTH records are contributed by the entire care team and used in quantitative treatment analyses. DEPICT HEALTH effectively communicates disease and treatment information to the patients’ circle of care and their parents, independent of language. The Retinoblastoma Activity Index (RAI) quantifies the active tumor (colored yellow) by counting the yellow pixels in the DEPICT HEALTH digital drawings. The drawings represent tumor at every encounter based on the collective opinion of the care team, and the RAI will quantitate tumor response to treatment. Two clinical trials were initiated using DEPICT HEALTH and RAI for eligibility and short- and long-term outcomes. Conclusion: Using RAI to score tumor response provides RECIST (response evaluation criteria in solid tumors) for retinoblastoma research, a standard of measurement that has never before been available. Machine learning methods will ultimately analyze point-of-care data to predict patient outcomes and assist with clinical decision making. DEPICT HEALTH provides an unbiased view of the efficacy of treatments, with potential to allow global point-of-care data to be widely available for research, essentially an “n” of “ALL.” Citation Format: Isabella Janusonis, Tran Truong, Justin Liu, Mei Chen, Brenda Gallie. Overcoming challenges in health care with machine learning: Innovation from retinoblastoma [abstract]. In: Proceedings of the AACR Special Conference on the Advances in Pediatric Cancer Research; 2019 Sep 17-20; Montreal, QC, Canada. Philadelphia (PA): AACR; Cancer Res 2020;80(14 Suppl):Abstract nr A63.