TY  - JOUR
A1  - Lampe, Leonie
A1  - Niehaus, Sebastian
A1  - Huppertz, Hans-Jürgen
A1  - Merola, Alberto
A1  - Reinelt, Janis Dominik
A1  - Mueller, Karsten
A1  - Straub, Sarah
A1  - Fassbender, Klaus
A1  - Fliessbach, Klaus
A1  - Jahn, Holger
A1  - Kornhuber, Johannes
A1  - Lauer, Martin Konrad
A1  - Prudlo, Johannes
A1  - Schneider, Anja
A1  - Synofzik, Matthis
A1  - Danek, Adrian
A1  - Diehl-Schmid, Janine
A1  - Otto, Markus
A1  - Villringer, Arno
A1  - Egger, Karl
A1  - Hattingen, Elke
A1  - Hilker-Roggendorf, Rüdiger
A1  - Schnitzler, Alfons
A1  - Südmeyer, Martin
A1  - Oertel, Wolfgang H.
A1  - Kassubek, Jan Rainer
A1  - Höglinger, Günter
A1  - Schroeter, Matthias
T1  - Comparative analysis of machine learning algorithms for multi-syndrome classification of neurodegenerative syndromes
T2  - Alzheimer's research & therapy
N2  - Importance: The entry of artificial intelligence into medicine is pending. Several methods have been used for the predictions of structured neuroimaging data, yet nobody compared them in this context.
Objective: Multi-class prediction is key for building computational aid systems for differential diagnosis. We compared support vector machine, random forest, gradient boosting, and deep feed-forward neural networks for the classification of different neurodegenerative syndromes based on structural magnetic resonance imaging.
Design, setting, and participants: Atlas-based volumetry was performed on multi-centric T1-weighted MRI data from 940 subjects, i.e., 124 healthy controls and 816 patients with ten different neurodegenerative diseases, leading to a multi-diagnostic multi-class classification task with eleven different classes.
Interventions: N.A.
Main outcomes and measures: Cohen’s kappa, accuracy, and F1-score to assess model performance.
Results: Overall, the neural network produced both the best performance measures and the most robust results. The smaller classes however were better classified by either the ensemble learning methods or the support vector machine, while performance measures for small classes were comparatively low, as expected. Diseases with regionally specific and pronounced atrophy patterns were generally better classified than diseases with widespread and rather weak atrophy.
Conclusions and relevance: Our study furthermore underlines the necessity of larger data sets but also calls for a careful consideration of different machine learning methods that can handle the type of data and the classification task best.
KW  - Comparative analysis
KW  - Deep neural network
KW  - Gradient boosting
KW  - Multi-syndrome classification
KW  - Neurodegenerative syndromes
KW  - Random forest
KW  - Support vector machine
Y1  - 2022
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/83634
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-836347
SN  - 1758-9193
N1  - This work was supported by the German Federal Ministry of Education and Research (BMBF) by a grant given to the German FTLD Consortium (FKZ O1GI1007A), by the German Research Foundation DFG (SCHR 774/5-1), by the Parkinson’s Disease Foundation (PDF-IRG-1307), and by the Michael J. Fox Foundation (MJFF-11362).
N1  - Project repository: https://github.com/Leoniela/Comparison-ML-Algorithms-Neurodegen
VL  - 14.2022
IS  - art. 62
SP  - 1
EP  - 13
PB  - BioMed Central
CY  - London
ER  -