Development of medical applications based on AI models and register data – regulatory considerations

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Artificial intelligence based methods, especially machine learning (ML), are increasingly used in healthcare for automatic medical image analysis and clinical decision support systems. Development and validation of ML models involve processing of large volumes of personal data. We analysed regulatory impacts on ML based application development especially from the perspective of privacy protection and usage of ML models as a basis for software under medical device regulation (MDR). We present best practices for ML application development and personal data usage in a use case of predicting elderly individuals’ future need for healthcare and social welfare services.
Original languageEnglish
Title of host publicationProceedings of the 18th Scandinavian Conference on Health Informatics (SHI 2022)
EditorsAndré Henriksen, Elia Gabarron, Vivian Vimarlund
PublisherLinköping University Electronic Press
Pages141-146
Number of pages6
ISBN (Electronic)978-91-7929-344-4
Publication statusPublished - 24 Aug 2022
MoE publication typeA4 Article in a conference publication
Event18th Scandinavian Conference on Health Informatics, SHI 2022 - Tromsø, Norway
Duration: 22 Aug 202224 Aug 2022
Conference number: 18
https://uit.no/tavla/artikkel/764177/scandinavian_conference_on_health_informatics

Publication series

SeriesLinköping Electronic Conference Proceedings
Number187
ISSN1650-3686

Conference

Conference18th Scandinavian Conference on Health Informatics, SHI 2022
Abbreviated titleSHI 2022
Country/TerritoryNorway
CityTromsø
Period22/08/2224/08/22
Internet address

Keywords

  • artificial intelligence
  • machine learning
  • medical device regulation
  • MDR
  • privacy protection

Fingerprint

Dive into the research topics of 'Development of medical applications based on AI models and register data – regulatory considerations'. Together they form a unique fingerprint.

Cite this