Your browser doesn't support javascript.
loading
Machine learning-driven diagnosis of multiple sclerosis from whole blood transcriptomics.
Omrani, Maryam; Chiarelli, Rosaria Rita; Acquaviva, Massimo; Bassani, Claudia; Dalla Costa, Gloria; Montini, Federico; Preziosa, Paolo; Pagani, Lucia; Grassivaro, Francesca; Guerrieri, Simone; Romeo, Marzia; Sangalli, Francesca; Colombo, Bruno; Moiola, Lucia; Zaffaroni, Mauro; Pietroboni, Anna; Protti, Alessandra; Puthenparampil, Marco; Bergamaschi, Roberto; Comi, Giancarlo; Rocca, Maria A; Martinelli, Vittorio; Filippi, Massimo; Farina, Cinthia.
Afiliação
  • Omrani M; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Chiarelli RR; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Acquaviva M; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Bassani C; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Dalla Costa G; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
  • Montini F; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
  • Preziosa P; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
  • Pagani L; IQVIA, Analytics Center of Excellence, Milano.
  • Grassivaro F; Dipartimento di Neuroscienze, Azienda Ospedale - Università di Padova, Padova, Italy.
  • Guerrieri S; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Romeo M; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Sangalli F; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Colombo B; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Moiola L; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Zaffaroni M; Centro Sclerosi Multipla, ASST della Valle Olona, Ospedale di Gallarate, Gallarate, Italy.
  • Pietroboni A; Fondazione IRCCS Cà Granda Ospedale Maggiore Policlinico, Milan, Italy.
  • Protti A; ASST Grande Ospedale Metropolitano Niguarda, Milan, Italy.
  • Puthenparampil M; Dipartimento di Neuroscienze, Azienda Ospedale - Università di Padova, Padova, Italy.
  • Bergamaschi R; IRCCS Fondazione Mondino, Pavia, Italy.
  • Comi G; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
  • Rocca MA; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
  • Martinelli V; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy.
  • Filippi M; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy; Unit of Neurology, IRCCS San Raffaele Scientific Institute, Milan, Italy; Vita-Salute San Raffaele University, Milan, Italy.
  • Farina C; Institute of Experimental Neurology and Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy. Electronic address: farina.cinthia@hsr.it.
Brain Behav Immun ; 121: 269-277, 2024 Oct.
Article em En | MEDLINE | ID: mdl-39097200
ABSTRACT
Multiple sclerosis (MS) is a neurological disorder characterized by immune dysregulation. It begins with a first clinical manifestation, a clinically isolated syndrome (CIS), which evolves to definite MS in case of further clinical and/or neuroradiological episodes. Here we evaluated the diagnostic value of transcriptional alterations in MS and CIS blood by machine learning (ML). Deep sequencing of more than 200 blood RNA samples comprising CIS, MS and healthy subjects, generated transcriptomes that were analyzed by the binary classification workflow to distinguish MS from healthy subjects and the Time-To-Event pipeline to predict CIS conversion to MS along time. To identify optimal classifiers, we performed algorithm benchmarking by nested cross-validation with the train set in both pipelines and then tested models generated with the train set on an independent dataset for final validation. The binary classification model identified a blood transcriptional signature classifying definite MS from healthy subjects with 97% accuracy, indicating that MS is associated with a clear predictive transcriptional signature in blood cells. When analyzing CIS data with ML survival models, prediction power of CIS conversion to MS was about 72% when using paraclinical data and 74.3% when using blood transcriptomes, indicating that blood-based classifiers obtained at the first clinical event can efficiently predict risk of developing MS. Coupling blood transcriptomics with ML approaches enables retrieval of predictive signatures of CIS conversion and MS state, thus introducing early non-invasive approaches to MS diagnosis.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Transcriptoma / Aprendizado de Máquina / Esclerose Múltipla Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Transcriptoma / Aprendizado de Máquina / Esclerose Múltipla Idioma: En Ano de publicação: 2024 Tipo de documento: Article