Author:
De Francesco Silvia,Crema Claudio,Archetti Damiano,Muscio Cristina,Reid Robert I.,Nigri Anna,Bruzzone Maria Grazia,Tagliavini Fabrizio,Lodi Raffaele,D’Angelo Egidio,Boeve Brad,Kantarci Kejal,Firbank Michael,Taylor John-Paul,Tiraboschi Pietro,Redolfi Alberto,Bruzzone Maria Grazia,Tiraboschi Pietro,Gandini Wheeler-Kingshott Claudia A. M.,Tosetti Michela,Forloni Gianluigi,Redolfi Alberto,D’Angelo Egidio,Tagliavini Fabrizio,Lodi Raffaele,Agati Raffaele,Aiello Marco,Alberici Elisa,Amato Carmelo,Aquino Domenico,Arrigoni Filippo,Baglio Francesca,Biagi Laura,Bonanno Lilla,Bosco Paolo,Bottino Francesca,Bozzali Marco,Canessa Nicola,Carducci Chiara,Carne Irene,Carnevale Lorenzo,Castellano Antonella,Cavaliere Carlo,Colnaghi Mattia,Contarino Valeria Elisa,Conte Giorgio,Costagli Mauro,Demichelis Greta,De Francesco Silvia,Falini Andrea,Ferraro Stefania,Ferrazzi Giulio,Figà Talamanca Lorenzo,Fundarò Cira,Gaudino Simona,Ghielmetti Francesco,Gianeri Ruben,Giulietti Giovanni,Grimaldi Marco,Iadanza Antonella,Inglese Matilde,Laganà Maria Marcella,Lancione Marta,Levrero Fabrizio,Longo Daniela,Lucignani Giulia,Lucignani Martina,Malosio Maria Luisa,Manzo Vittorio,Marino Silvia,Medina Jean Paul,Micotti Edoardo,Morelli Claudia,Muscio Cristina,Napolitano Antonio,Nigri Anna,Padelli Francesco,Palesi Fulvia,Pantano Patrizia,Parrillo Chiara,Pavone Luigi,Peruzzo Denis,Petsas Nikolaos,Pichiecchio Anna,Pirastru Alice,Politi Letterio S.,Roccatagliata Luca,Rognone Elisa,Rossi Andrea,Rossi-Espagnet Maria Camilla,Ruvolo Claudia,Salvatore Marco,Savini Giovanni,Tagliente Emanuela,Testa Claudia,Tonon Caterina,Tortora Domenico,Triulzi Fabio Maria,
Abstract
AbstractBiomarker-based differential diagnosis of the most common forms of dementia is becoming increasingly important. Machine learning (ML) may be able to address this challenge. The aim of this study was to develop and interpret a ML algorithm capable of differentiating Alzheimer’s dementia, frontotemporal dementia, dementia with Lewy bodies and cognitively normal control subjects based on sociodemographic, clinical, and magnetic resonance imaging (MRI) variables. 506 subjects from 5 databases were included. MRI images were processed with FreeSurfer, LPA, and TRACULA to obtain brain volumes and thicknesses, white matter lesions and diffusion metrics. MRI metrics were used in conjunction with clinical and demographic data to perform differential diagnosis based on a Support Vector Machine model called MUQUBIA (Multimodal Quantification of Brain whIte matter biomArkers). Age, gender, Clinical Dementia Rating (CDR) Dementia Staging Instrument, and 19 imaging features formed the best set of discriminative features. The predictive model performed with an overall Area Under the Curve of 98%, high overall precision (88%), recall (88%), and F1 scores (88%) in the test group, and good Label Ranking Average Precision score (0.95) in a subset of neuropathologically assessed patients. The results of MUQUBIA were explained by the SHapley Additive exPlanations (SHAP) method. The MUQUBIA algorithm successfully classified various dementias with good performance using cost-effective clinical and MRI information, and with independent validation, has the potential to assist physicians in their clinical diagnosis.
Funder
Italian Ministry of Economy and Finance
Italian Ministry of Health
Publisher
Springer Science and Business Media LLC