%0 Journal Article
%A Makarious, Mary B.
%A Leonard, Hampton L.
%A Vitale, Dan
%A Iwaki, Hirotaka
%A Sargent, Lana
%A Dadu, Anant
%A Violich, Ivo
%A Hutchins, Elizabeth
%A Saffo, David
%A Bandres-Ciga, Sara
%A Kim, Jonggeol Jeff
%A Song, Yeajin
%A Maleknia, Melina
%A Bookman, Matt
%A Nojopranoto, Willy
%A Campbell, Roy H.
%A Hashemi, Sayed Hadi
%A Botia, Juan A.
%A Carter, John F.
%A Craig, David W.
%A Van Keuren-Jensen, Kendall
%A Morris, Huw R.
%A Hardy, John A.
%A Blauwendraat, Cornelis
%A Singleton, Andrew B.
%A Faghri, Faraz
%A Nalls, Mike A.
%T Multi-modality machine learning predicting Parkinson’s disease
%J npj Parkinson's Disease
%V 8
%N 1
%@ 2373-8057
%C London [u.a.]
%I Nature Publ. Group
%M DZNE-2022-00445
%P 35
%D 2022
%X Personalized medicine promises individualized disease prediction and treatment. The convergence of machine learning (ML) and available multimodal data is key moving forward. We build upon previous work to deliver multimodal predictions of Parkinson’s disease (PD) risk and systematically develop a model using GenoML, an automated ML package, to make improved multi-omic predictions of PD, validated in an external cohort. We investigated top features, constructed hypothesis-free disease-relevant networks, and investigated drug–gene interactions. We performed automated ML on multimodal data from the Parkinson’s progression marker initiative (PPMI). After selecting the best performing algorithm, all PPMI data was used to tune the selected model. The model was validated in the Parkinson’s Disease Biomarker Program (PDBP) dataset. Our initial model showed an area under the curve (AUC) of 89.72
%F PUB:(DE-HGF)16
%9 Journal Article
%2 pmc:PMC8975993
%$ pmid:35365675
%R 10.1038/s41531-022-00288-w
%U https://pub.dzne.de/record/163706