BACKGROUND: An early diagnosis together with an accurate disease progression monitoring of multiple sclerosis is an important component of successful disease management. Prior studies have established that multiple sclerosis is correlated with speech discrepancies. Early research using objective acoustic measurements has discovered measurable dysarthria. METHOD: The objective was to determine the potential clinical utility of machine learning and deep learning/AI approaches for the aiding of diagnosis, biomarker extraction and progression monitoring of multiple sclerosis using speech recordings. A corpus of 65 MS-positive and 66 healthy individuals reading the same text aloud was used for targeted acoustic feature extraction utilizing automatic phoneme segmentation. A series of binary classification models was trained, tuned, and evaluated regarding their Accuracy and area-under-the-curve. RESULTS: The Random Forest model performed best, achieving an Accuracy of 0.82 on the validation dataset and an area-under-the-curve of 0.76 across 5 k-fold cycles on the training dataset. 5 out of 7 acoustic features were statistically significant. CONCLUSION: Machine learning and artificial intelligence in automatic analyses of voice recordings for aiding multiple sclerosis diagnosis and progression tracking seems promising. Further clinical validation of these methods and their mapping onto multiple sclerosis progression is needed, as well as a validating utility for English-speaking populations.

• Klíčová slova
• Biomedical, Dysarthria, Machine learning, Multiple sclerosis, Phonetics, Speech acoustics, Technology assessment,
• MeSH
• lidé MeSH
• pilotní projekty MeSH
• řeč * MeSH
• roztroušená skleróza * MeSH
• strojové učení MeSH
• umělá inteligence MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

It has not yet been established whether genetic predictors of multiple sclerosis (MS) susceptibility also influence disease severity and accumulation of disability. Our aim was to evaluate associations between 16 previously validated genetic susceptibility markers and MS phenotype. Patients with clinically isolated syndrome verified by positive magnetic resonance imaging (MRI) and cerebrospinal fluid findings (n=179) were treated with interferon-β. Disability and volumetric MRI parameters were evaluated regularly for 2 years. Sixteen single-nucleotide polymorphisms (SNPs) previously validated as predictors of MS susceptibility in our cohort and their combined weighted genetic risk score (wGRS) were tested for associations with clinical (conversion to MS, relapses and disability) and MRI disease outcomes (whole brain, grey matter and white matter volumes, corpus callosum cross-sectional area, brain parenchymal fraction, T2 and T1 lesion volumes) 2 years from disease onset using mixed-effect models. We have found no associations between the tested SNPs and the clinical or MRI outcomes. Neither the combined wGRS predicted MS activity and progression over 2-year follow-up period. Power analyses confirmed 90% power to identify clinically relevant changes in all outcome variables. We conclude that the most important MS susceptibility loci do not determine MS phenotype and disease outcomes.

• MeSH
• biologické markery mozkomíšní mok   MeSH
• dospělí MeSH
• fenotyp MeSH
• genetická predispozice k nemoci * MeSH
• genetické asociační studie MeSH
• genetické lokusy * MeSH
• jednonukleotidový polymorfismus MeSH
• lidé středního věku MeSH
• lidé MeSH
• magnetická rezonanční tomografie MeSH
• mladiství MeSH
• mozek patologie   MeSH
• roztroušená skleróza diagnóza   genetika   MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mladiství MeSH
• mužské pohlaví MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Názvy látek
• biologické markery MeSH