Advanced search
Start date
Betweenand

Automated method and system for on demand acquisition of blood donors using machine learning to mitigate blood stockout and wastage

Grant number: 19/08819-5
Support type:Research Grants - Innovative Research in Small Business - PIPE
Duration: October 01, 2020 - June 30, 2021
Field of knowledge:Health Sciences - Collective Health - Public Health
Principal researcher:Rafael Yassushi Oki
Grantee:Rafael Yassushi Oki
Company:Savelivez Tecnologia para a Saúde Ltda. (Filial)
CNAE: Desenvolvimento e licenciamento de programas de computador não-customizáveis
City: São Paulo
Assoc. researchers: Luis Felipe Melo de Miranda ; Marcos Rodrigues de Matos
Associated scholarship(s):20/16794-0 - Automated method and system for on demand acquisition of blood donors using machine learning to mitigate blood stockout and wastage, BP.TT
20/14677-6 - Automated method and system for on demand acquisition of blood donors using machine learning to mitigate blood stockout and wastage, BP.TT

Abstract

Data from the World Health Organization (WHO) indicates an increasing demand for blood transfusions and shows the number of donors does not scale with this growth. This is a global problem in which more than 70 countries have a donation rate of less than 1% of the total population, with a WHO recommended value of 3%. Approximately 50% of the total 112.5 million blood donations occur in developed countries, serving only 19% of the world's population. In this context, both public and private blood banks are the organizations responsible for supplying hospital stocks. However, blood is a living tissue that has no substitutes, and each blood component has a different shelf-life. Platelets, for example, last for a maximum of seven days. Since this demand is volatile and, currently, campaigns to bring in donors do not account for blood type or current stock levels, this misalignment between supply and demand generates lack of some blood components and, at the same time, waste of others. In addition to the damage to public health, there is financial loss. The problem of wastage comes to cost more than R$ 500 per blood bag, according to data from the Ministry of Health, which generates waste amounting to millions of reais per year in Brazil due to the expiration of donated blood. The purpose of this project is to use machine learning to develop a system to help blood banks avoid stockouts and wastage through personalized and automated communication that can engage donors by blood type, accounting for desired volume, location, and timing according to the specific demand of each location. To address the problem, machine learning will be used in conjunction with statistical methods and digital marketing concepts for on-demand donor engagement. The project is expected to develop a platform and validate its effectiveness in reducing blood bank costs and helping blood banks in keeping to the appropriate stock levels. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)