PuSH - Publikationsserver des Helmholtz Zentrums München

Nguyen, B.H.P. ; Garger, D. ; Lu, D. ; Maalmi, H.* ; Prokisch, H. ; Thorand, B. ; Adamski, J. ; Kastenmüller, G. ; Waldenberger, M. ; Gieger, C. ; Peters, A. ; Suhre, K.* ; Bönhof, G.J.* ; Rathmann, W.* ; Roden, M.* ; Grallert, H. ; Ziegler, D.* ; Herder, C.* ; Menden, M.P.

Interpretable multimodal machine learning (IMML) framework reveals pathological signatures of distal sensorimotor polyneuropathy.

Commun. Med. 4:265 (2024)
Verlagsversion DOI PMC
Free journal
Creative Commons Lizenzvertrag
BACKGROUND: Distal sensorimotor polyneuropathy (DSPN) is a common neurological disorder in elderly adults and people with obesity, prediabetes and diabetes and is associated with high morbidity and premature mortality. DSPN is a multifactorial disease and not fully understood yet. METHODS: Here, we developed the Interpretable Multimodal Machine Learning (IMML) framework for predicting DSPN prevalence and incidence based on sparse multimodal data. Exploiting IMMLs interpretability further empowered biomarker identification. We leveraged the population-based KORA F4/FF4 cohort including 1091 participants and their deep multimodal characterisation, i.e. clinical data, genomics, methylomics, transcriptomics, proteomics, inflammatory proteins and metabolomics. RESULTS: Clinical data alone is sufficient to stratify individuals with and without DSPN (AUROC = 0.752), whilst predicting DSPN incidence 6.5 ± 0.2 years later strongly benefits from clinical data complemented with two or more molecular modalities (improved ΔAUROC > 0.1, achieved AUROC of 0.714). Important and interpretable features of incident DSPN prediction include up-regulation of proinflammatory cytokines, down-regulation of SUMOylation pathway and essential fatty acids, thus yielding novel insights in the disease pathophysiology. CONCLUSIONS: These may become biomarkers for incident DSPN, guide prevention strategies and serve as proof of concept for the utility of IMML in studying complex diseases.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Korrespondenzautor
ISSN (print) / ISBN 2730-664X
e-ISSN 2730-664X
Zeitschrift Communications Medicine
Quellenangaben Band: 4, Heft: 1, Seiten: , Artikelnummer: 265 Supplement: ,
Verlag Springer
Nichtpatentliteratur Publikationen
Begutachtungsstatus Peer reviewed
Institut(e) Institute of Computational Biology (ICB)
Institute of Neurogenomics (ING)
Institute of Epidemiology II (EPI2)
Institute of Experimental Genetics (IEG)