Your browser doesn't support javascript.
loading
Federated machine learning for a facilitated implementation of Artificial Intelligence in healthcare - a proof of concept study for the prediction of coronary artery calcification scores.
Wolff, Justus; Matschinske, Julian; Baumgart, Dietrich; Pytlik, Anne; Keck, Andreas; Natarajan, Arunakiry; von Schacky, Claudio E; Pauling, Josch K; Baumbach, Jan.
Afiliação
  • Wolff J; Chair of Experimental Bioinformatics, TUM School of Life Sciences Weihenstephan, Technical University of Munich, Maximus-von-Imhof-Forum 3, 85354 Freising, Germany.
  • Matschinske J; Syte - Strategy Institute for Digital Health, Hohe Bleichen 8, 20354 Hamburg, Germany.
  • Baumgart D; Chair of Computational Systems Biology, University of Hamburg, Notkestreet 9-11, 22607 Hamburg, Germany.
  • Pytlik A; Preventicum Essen, Theodor-Althoff-Str. 47 45133 Essen, Germany.
  • Keck A; Preventicum Duesseldorf, Koenigsallee 11, 40212 Duesseldorf, Germany.
  • Natarajan A; Preventicum Essen, Theodor-Althoff-Str. 47 45133 Essen, Germany.
  • von Schacky CE; Preventicum Duesseldorf, Koenigsallee 11, 40212 Duesseldorf, Germany.
  • Pauling JK; Syte - Strategy Institute for Digital Health, Hohe Bleichen 8, 20354 Hamburg, Germany.
  • Baumbach J; Independent Researcher, Digital Health, Informatics and Data Science, Lower Saxony, Germany.
J Integr Bioinform ; 19(4)2022 Dec 01.
Article em En | MEDLINE | ID: mdl-36054833
ABSTRACT
The implementation of Artificial Intelligence (AI) still faces significant hurdles and one key factor is the access to data. One approach that could support that is federated machine learning (FL) since it allows for privacy preserving data access. For this proof of concept, a prediction model for coronary artery calcification scores (CACS) has been applied. The FL was trained based on the data in the different institutions, while the centralized machine learning model was trained on one allocation of data. Both algorithms predict patients with risk scores ≥5 based on age, biological sex, waist circumference, dyslipidemia and HbA1c. The centralized model yields a sensitivity of c. 66% and a specificity of c. 70%. The FL slightly outperforms that with a sensitivity of 67% while slightly underperforming it with a specificity of 69%. It could be demonstrated that CACS prediction is feasible via both, a centralized and an FL approach, and that both show very comparable accuracy. In order to increase accuracy, additional and a higher volume of patient data is required and for that FL is utterly necessary. The developed "CACulator" serves as proof of concept, is available as research tool and shall support future research to facilitate AI implementation.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Inteligência Artificial / Vasos Coronários Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Ano de publicação: 2022 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Inteligência Artificial / Vasos Coronários Tipo de estudo: Prognostic_studies / Risk_factors_studies Limite: Humans Idioma: En Ano de publicação: 2022 Tipo de documento: Article