Clinical validation of autoSCORE: A human-in-the-loop AI tool for interpretation of long-term EEG recordings

 

Jesper Tveit, Harald Aurlien, Aatif M. Husain, Apameh Tarazi, Beate Diehl, William Gallentine, William Tatum, Cecil D. Hahn, Daniel Gregor Schulze, Daniella Terney, Don Schomer, Eivind Aanestad, Elena Gardell, Erik Westhall, Ernesto Gonzalez-Giraldo, Eva Catenaccio, Fieke Cox, Firas Fahoum, Hatice Tankisi, Ina Hjelland, Jan Brøgger, Julien Hébert, Katherine Xiong, Kristian Bernhard Nilsen, Lilach Goldstein, Line Ulvin, Oliver Johannes Henning, Peter W. Kaplan, Petter Omland, Phillip L. Pearl, Ravindra Arya, Richard Wennberg, Rune Markhus, Shavonne L Massey, Stephan Schuele, Sudha Kessler, Trudy Pang, Birgit Frauscher, Sándor Beniczky

Clinical Neurophysiology

2026

 

Highlights:

  • We report validation of an AI model for analysis of long-term EEG.
  • AI agreement with experts was comparable to agreement between experts.
  • AI outperformed experts in focal non-epileptiform detection.