AI-based identification of plasma donors with Covid-19 antibodies

Grant number: 2020-02232

Grant search

Key facts

  • Disease

    COVID-19
  • Start & end year

    2020
    2021
  • Known Financial Commitments (USD)

    $116,000
  • Funder

    Vinnova
  • Principal Investigator

    Unspecified Unspecified Unspecified
  • Research Location

    Sweden
  • Lead Research Institution

    Prometa Technologies AB
  • Research Priority Alignment

    N/A
  • Research Category

    Clinical characterisation and management

  • Research Subcategory

    Supportive care, processes of care and management

  • Special Interest Tags

    Digital Health

  • Study Type

    Non-Clinical

  • Clinical Trial Details

    Not applicable

  • Broad Policy Alignment

    Pending

  • Age Group

    Not Applicable

  • Vulnerable Population

    Not applicable

  • Occupations of Interest

    Not applicable

Abstract

Purpose and goal ** Denna text är maskinöversatt ** The goal has been to develop an AI model to identify a large number of potential plasma donors, to make good Covid-19 care available to as many people as possible. This model was developed in the project and that goal was thus achieved. A possible further development in the future is to make the model available for practical use, through testing and fine-tuning. Expected results and effects ** Denna text är maskinöversatt ** The project has strengthened the participants´ knowledge and skills regarding modeling and development of AI tools for clinical applications and developed the AI models that were the goal. Due to the pandemic, testing and fine-tuning could not be done to the extent that was the ambition, but there are great development opportunities here in the future. Planned approach and implementation ** Denna text är maskinöversatt ** The project has been implemented by Prometa, VizzDAT and Karolinska Institutet during the summer and autumn of 2020 in five different activities / work packages under the leadership of three project manager managers, one from each organization.