Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloEvaluation of machine learning algorithms performance for the prediction of early multiple sclerosis from resting-state FMRI connectivity data.
Anno di pubblicazione2019
Autore/iValeria Saccà 1, Alessia Sarica 2, Fabiana Novellino 2, Stefania Barone 3, Tiziana Tallarico 3, Enrica Filippelli 3, Alfredo Granata 3, Carmelina Chiriaco 2, Roberto Bruno Bossio 4, Paola Valentino 3, Aldo Quattrone 2,3
Affiliazioni autori1. Department of Medical and Surgical Sciences, University "Magna Graecia", Catanzaro, Italy. 2. National Research Council, Institute of Bioimaging and Molecular Physiology (IBFM), Catanzaro, Italy. 3. Institute of Neurology, University Magna Graecia, Catanzaro, Italy. 4. Neurology Operating Unit Serraspiga, Provincial Health Authority, Cosenza, Italy.
Autori CNR e affiliazioni
  • inglese
AbstractMachine Learning application on clinical data in order to support diagnosis and prognostic evaluation arouses growing interest in scientific community. However, choice of right algorithm to use was fundamental to perform reliable and robust classification. Our study aimed to explore if different kinds of Machine Learning technique could be effective to support early diagnosis of Multiple Sclerosis and which of them presented best performance in distinguishing Multiple Sclerosis patients from control subjects. We selected following algorithms: Random Forest, Support Vector Machine, Naïve-Bayes, K-nearest-neighbor and Artificial Neural Network. We applied the Independent Component Analysis to resting-state functional-MRI sequence to identify brain networks. We found 15 networks, from which we extracted the mean signals used into classification. We performed feature selection tasks in all algorithms to obtain the most important variables. We showed that best discriminant network between controls and early Multiple Sclerosis, was the sensori-motor I, according to early manifestation of motor/sensorial deficits in Multiple Sclerosis. Moreover, in classification performance, Random Forest and Support Vector Machine showed same 5-fold cross-validation accuracies (85.7%) using only this network, resulting to be best approaches. We believe that these findings could represent encouraging step toward the translation to clinical diagnosis and prognosis.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da1103
Pagine a1114
Pagine totali12
RivistaBrain imaging and behavior (Print)
Attiva dal 2007
Editore: Springer - New York, NY
Paese di pubblicazione: Stati Uniti d'America
Lingua: inglese
ISSN: 1931-7557
Titolo chiave: Brain imaging and behavior (Print)
Titolo proprio: Brain imaging and behavior. (Print)
Titolo abbreviato: Brain imaging behav. (Print)
Numero volume della rivista13
Fascicolo della rivista-
Verificato da referee-
Stato della pubblicazionePostprint
Indicizzazione (in banche dati controllate)
  • PubMed (Codice:29992392)
Parole chiaveArtificial neural network; K-nearest-neighbor; Naïve Bayes; Random Forest; Resting state fMRI; Support vector machine
Link (URL, URI)-
Titolo parallelo-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • IBFM — Istituto di bioimmagini e fisiologia molecolare
Moduli/Attività/Sottoprogetti CNR
Progetti Europei-