Presenting “Creating Research Quality Cancer Genomic Data from Electronic Health Records” at AACR 2022

Venue: Ernest N. Morial Convention Center New Orleans, Louisiana, USA

Leading researchers and oncologists, Professor Larry Kessler, Dr. VK Gadi and Dr. Rachel Yung, have been invited to present our collaborated work “Creating Research Quality Cancer Genomic Data from Electronic Health Records” at the annual AACR meeting.

Understanding the impact of precision medicine on medical practice, patient care and clinical outcomes is a priority for advancing cancer care. However, extracting tumor genomic testing (TGT) results from electronic health records (EHRs) is challenging. Our pilot study is performed to assess the ability of Natural Language Processing (NLP) algorithms to convert unstructured text data and PDF-formatted TGT results into research-quality data. Pangaea adapted their existing NLP algorithm (PIES) that leverages pre-training, fine-tuning and rules to extract 26 variables and obtained an average accuracy of 97.3% with a standard deviation of 3.5% across all 26 variables. The output placed variables into relevant, standardized formats and produced a research quality data set. The expansion of our pilot study to other data health care systems will further enhance our ability to assess the scalability of these technologies to create research-quality data fit for use.

Read the full abstract here.

Request Publication

Presenters

Dr. VK Gadi

Director of Medical Oncology, UI Health;
Associate Director, University of Illinois Cancer Center

Professor Larry Kessler

Professor, Department of Health Systems & Population Health, University of Washington;
Director, Regulatory Oversight Center for Dialysis Innovation

Dr. Rachel Yung

Associate Professor, Medical Oncology, University of Washington;
Physician, Seattle Cancer Care Alliance

Attendees

Dr. Vibhor Gupta

Founder
Pangaea Data

Mr. Jingqing Zhang

Head of AI
Pangaea Data