Statement of the problem: Unconscious bias and systemic racism is evident in published reports that describe persistent asymmetric outcomes in our entire health care system including oncology. Framework of the solution: There already is a very large set of publications that describe the extent and outcomes of health disparities. An extensive data set also describes mitigation strategies. Changing the outcomes includes policy changes within the health care system but also with regulatory agencies and the legislative branch of government. It is critical that these different systems are armed with the totality of available information in a manner that can be leveraged to improve the health care of all. We have developed a system of describing large sets of data manually extracted from published articles. These results are aggregated together independent of the framework of the manuscript so that similar outcomes can be placed side by side. This system can provide the necessary comprehensive data that is available today to begin to implement changes. Results to date: We have used COVID-19 publications as a prototype topic that has so many articles no single person can comprehend or manage. We extracted data from 1000 COVID-19 manuscripts that presented new data. This rendered 26,000 note fields arranged in a parent child relationship. The data base described 12,000 individual observations. A read only version is available at COVIDpublications.org. We are now applying this system to bias and stigma of the health care profession to persons who use drugs, and a demo of this project is available at (https://app.refbin.com/app/embed?m=1188). We have now established the rules to manually extract data from any clinical article that presents new data. This involves 4 types of note fields per observation arranged in parent child relationships. 1) The observation, 2) description of the observation, 3) the population, and 4) the topic. This system allows the observations from an unlimited number of studies to share parents. This results in about a 5-fold reduction in the total number of note fields. It also allows grouping of information so that a user can scan the data base and access the entirety of information without specifically knowing what they are looking for. Conclusions: We are expanding this data base bias and systemic racism of the health care system on persons with substance use disorder to include the broader range of patients. By capturing all of the data that is known we hope to influence implementation of improved health care to patients including those with cancer. These results will be presented in October. Citation Format: Shania Lunna, Samuel Gauthier, Stacia Richard, Rachel M Bombardier, David N Krag. Extraction and organization of all published results on impact of systemic racism on treatment of cancer patients [abstract]. In: Proceedings of the AACR Virtual Conference: 14th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2021 Oct 6-8. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2022;31(1 Suppl):Abstract nr PO-047.