[en] The ever increasing use of artificial intelligence (AI) methods in biomedical sciences calls for closer inter-disciplinary collaborations that transfer the domain knowledge from life scientists to computer science researchers and vice-versa. We highlight two general areas where the use of AI-based solutions designed for clinical and laboratory settings has proven problematic. These are used to demonstrate common sources of translational challenges that often stem from the differences in data interpretation between the clinical and research view, and the unmatched expectations and requirements on the result quality metrics. We outline how explicit interpretable inference reporting might be used as a guide to overcome such translational challenges. We conclude with several recommendations for safer translation of machine learning solutions into real-world settings.
Disciplines :
Computer science
Author, co-author :
Vega Moreno, Carlos Gonzalo ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core
Kratochvil, Miroslav ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core
Satagopam, Venkata ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core
Schneider, Reinhard ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Bioinformatics Core
External co-authors :
no
Language :
English
Title :
Translational Challenges of Biomedical Machine Learning Solutions in Clinical and Laboratory Settings
Publication date :
2022
Event name :
International Work-Conference on Bioinformatics and Biomedical Engineering
Event place :
Meloneras, Spain
Event date :
from 27-06-2022 to 30-06-2022
Audience :
International
Main work title :
Bioinformatics and Biomedical Engineering
Publisher :
Springer International Publishing, Cham, Unknown/unspecified