Contribution to a conference proceedings

FZJ-2020-03219

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Evolving complex yet interpretable representations: application to Alzheimer’s diagnosis and prognosis

Kroll, J.-P. (Corresponding author)FZJ* ; Eickhoff, S. B.FZJ* ; Hoffstaedter, F.FZJ* ; Patil, K. R.FZJ*

2020
IEEE

This record in other databases:

Please use a persistent id in citations: doi:10.1109/CEC48606.2020.9185843

Abstract: With increasing accuracy and availability of moredata, the potential of using machine learning (ML) methods inmedical and clinical applications has gained considerableinterest. However, the main hurdle in translational use of MLmethods is the lack of explainability, especially when non-linearmethods are used. Explainable (i.e. human-interpretable)methods can provide insights into disease mechanisms but canequally importantly promote clinician-patient trust, in turnhelping wider social acceptance of ML methods. Here, weempirically test a method to engineer complex, yet interpretable,representations of base features via evolution of context-freegrammar (CFG). We show that together with a simple MLalgorithm evolved features provide higher accuracy on severalbenchmark datasets and then apply it to a real word problem ofdiagnosing Alzheimer’s disease (AD) based on magneticresonance imaging (MRI) data. We further demonstrate highperformance on a hold-out dataset for the prognosis of AD.Keywords — grammar evolution, feature representation,interpretability, Alzheimer’s disease, machine learning

Note: This study was supported by the European Union‘sHorizon 2020 Research and Innovation Programme underGrant Agreement No. 785907 (HBP SGA2) and GrantAgreement No. 7202070 (HBP SGA1). Data collection andsharing for this project was funded by the Alzheimer's DiseaseNeuroimaging Initiative (ADNI) (National Institutes of HealthGrant U01 AG024904) and DOD ADNI (Department ofDefense award number W81XWH-12-2-0012). ADNI isfunded by the National Institute on Aging, the NationalInstitute of Biomedical Imaging and Bioengineering, andthrough generous contributions from the following: AbbVie,Alzheimer’s Association; Alzheimer’s Drug DiscoveryFoundation; Araclon Biotech; BioClinica, Inc.; Biogen;Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate;Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company;EuroImmun; F. Hoffmann-La Roche Ltd and its affiliatedcompany Genentech, Inc.; Fujirebio; GE Healthcare; IXICOLtd.; Janssen Alzheimer Immunotherapy Research &Development, LLC.; Johnson & Johnson PharmaceuticalResearch & Development LLC.; Lumosity; Lundbeck; Merck& Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRxResearch; Neurotrack Technologies; NovartisPharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging;Servier; Takeda Pharmaceutical Company; and TransitionTherapeutics. The Canadian Institutes of Health Research isproviding funds to support ADNI clinical sites in Canada.Private sector contributions are facilitated by the Foundationfor the National Institutes of Health (www.fnih.org). Thegrantee organization is the Northern California Institute forResearch and Education, and the study is coordinated by theAlzheimer’s Therapeutic Research Institute at the Universityof Southern California. ADNI data are disseminated by theLaboratory for Neuro Imaging at the University of SouthernCalifornia.

---

Contributing Institute(s):

1. Gehirn & Verhalten (INM-7)

Research Program(s):

1. 572 - (Dys-)function and Plasticity (POF3-572) (POF3-572)
2. 574 - Theory, modelling and simulation (POF3-574) (POF3-574)
3. HBP SGA1 - Human Brain Project Specific Grant Agreement 1 (720270) (720270)
4. HBP SGA2 - Human Brain Project Specific Grant Agreement 2 (785907) (785907)

Appears in the scientific report 2020

---