Machine learning classifier to identify clinical and radiological features relevant to disability progression in multiple sclerosis

Objectives To evaluate the accuracy of a data-driven approach, such as machine learning classification, in predicting disability progression in MS. Methods We analyzed structural brain images of 163 subjects diagnosed with MS acquired at two different sites. Participants were followed up for 2–6 yea...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of neurology Ročník 268; číslo 12; s. 4834 - 4845
Hlavní autoři: Tommasin, Silvia, Cocozza, Sirio, Taloni, Alessandro, Giannì, Costanza, Petsas, Nikolaos, Pontillo, Giuseppe, Petracca, Maria, Ruggieri, Serena, De Giglio, Laura, Pozzilli, Carlo, Brunetti, Arturo, Pantano, Patrizia
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2021
Springer Nature B.V
Témata:
Accuracy
Anisotropy
Brain - diagnostic imaging
Cerebellum
Disability Evaluation
Disease Progression
Gray Matter - diagnostic imaging
Humans
Learning algorithms
Machine Learning
Magnetic Resonance Imaging
Medicine
Medicine & Public Health
Multiple sclerosis
Multiple Sclerosis - diagnostic imaging
Neurology
Neuroradiology
Neurosciences
Original Communication
Patients
Phenotypes
Substantia alba
Substantia grisea
Thalamus
Multiple sclerosis
Disability progression
Magnetic resonance imaging
Machine learning
ISSN:0340-5354, 1432-1459, 1432-1459
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Objectives To evaluate the accuracy of a data-driven approach, such as machine learning classification, in predicting disability progression in MS. Methods We analyzed structural brain images of 163 subjects diagnosed with MS acquired at two different sites. Participants were followed up for 2–6 years, with disability progression defined according to the expanded disability status scale (EDSS) increment at follow-up. T2-weighted lesion load (T2LL), thalamic and cerebellar gray matter (GM) volumes, fractional anisotropy of the normal appearing white matter were calculated at baseline and included in supervised machine learning classifiers. Age, sex, phenotype, EDSS at baseline, therapy and time to follow-up period were also included. Classes were labeled as stable or progressed disability. Participants were randomly chosen from both sites to build a sample including 50% patients showing disability progression and 50% patients being stable. One-thousand machine learning classifiers were applied to the resulting sample, and after testing for overfitting, classifier confusion matrix, relative metrics and feature importance were evaluated. Results At follow-up, 36% of participants showed disability progression. The classifier with the highest resulting metrics had accuracy of 0.79, area under the true positive versus false positive rates curve of 0.81, sensitivity of 0.90 and specificity of 0.71. T2LL, thalamic volume, disability at baseline and administered therapy were identified as important features in predicting disability progression. Classifiers built on radiological features had higher accuracy than those built on clinical features. Conclusions Disability progression in MS may be predicted via machine learning classifiers, mostly evaluating neuroradiological features.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0340-5354
1432-1459
1432-1459
DOI:10.1007/s00415-021-10605-7