Machine Learning And Prioritizing Incoming Tissue Potential
At the end of 2018, New England Donor Services (NEDS) renewed its focus on two areas: 1) increasing the total recoverable tissues amongst its referred tissue donor potential and 2) reducing the frequency of cases ruled out for tissue donation just before recovery could take place. By utilizing machine learning, a model algorithm was built to prioritize incoming tissue potential referrals in consideration of these two areas. Machine learning, the model algorithm, and its implementation into NEDS' Tissue Operations will be discussed and explored.
Mark DeFilippis, MBA, CTBS
Director, Tissue Operations Center, New England Donor Services
Mark is the Director of the Tissue Operations Center at New England Donor Services and is responsible for the 24-hour operations center. Mark has been with New England Donor Services for over fifteen years, he has served in the Quality Department as well as in the Operations Center determining donor eligibility and working with families to obtain authorization. Mark is the co-chair of the Membership Committee, he is currently the Secretary of the RADE Council as well a member of The AOPO Tissue Council. Mark is a Certified Tissue Banking Specialist.
Brandon McKown, MBA
Brandon McKown is a Business Intelligence Analyst with New England Donor Services. He began his career with NEDS in 2010. Prior to this, he worked in the financial software industry in Albuquerque, New Mexico after attaining his MBA in 2007 at the State University of New York at Albany. He has presented previously at AATB's QDEW in 2018, discussing "Electronic Tissue Allocation in Real Time"