Artificial intelligence aided serum protein electrophoresis analysis of Finnish patient samples: Retrospective validation.

Journal: Clinica chimica acta; international journal of clinical chemistry
PMID: 39662719

Abstract

BACKGROUND AND AIMS: Serum protein electrophoresis interpretation requires a substantial amount of manual work. In 2020, Chabrun et al. created a machine learning method called SPECTR for the task. We aimed to validate and test the SPECTR method against our results of more precise immunofixation electrophoresis.

Authors

  • Tapio Lahtiharju
    Department of Clinical Chemistry, HUS Diagnostic Centre, Helsinki University Hospital and University of Helsinki, P.O. Box 720, FI-00029 HUS, Finland. Electronic address: tapio.lahtiharju@hus.fi.
  • Lassi Paavolainen
    Institute for Molecular Medicine Finland (FIMM), University of Helsinki, Tukholmankatu 8, Helsinki 00014, Finland.
  • Janne Suvisaari
    Department of Clinical Chemistry, HUS Diagnostic Centre, Helsinki University Hospital and University of Helsinki, P.O. Box 720, FI-00029 HUS, Finland. Electronic address: janne.suvisaari@hus.fi.
  • Pasi Nokelainen
    Department of Clinical Chemistry, HUS Diagnostic Centre, Helsinki University Hospital and University of Helsinki, P.O. Box 720, FI-00029 HUS, Finland. Electronic address: pasi.nokelainen@hus.fi.
  • Emmi Rotgers
    Fimlab Laboratories Oy Ltd, P.O. Box 66, FI-33013, Finland. Electronic address: emmi.rotgers@fimlab.fi.
  • Mikko Anttonen
    Department of Clinical Chemistry, HUS Diagnostic Centre, Helsinki University Hospital and University of Helsinki, P.O. Box 720, FI-00029 HUS, Finland. Electronic address: mikko.anttonen@hus.fi.
  • Outi Itkonen
    Department of Clinical Chemistry, HUS Diagnostic Centre, Helsinki University Hospital and University of Helsinki, P.O. Box 720, FI-00029 HUS, Finland. Electronic address: outi.itkonen@hus.fi.

Keywords

External Resources

Popular Topics
Recent Journals