Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients
Composite MRI scales of central nervous system tissue destruction correlate stronger with clinical outcomes than their individual components in multiple sclerosis (MS) patients. Using machine learning (ML), we previously developed Combinatorial MRI scale (COMRISv1) solely from semi-quantitative (sem...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-11-01
|
| Series: | Frontiers in Radiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fradi.2022.1026442/full |
| _version_ | 1828297557873262592 |
|---|---|
| author | Erin Kelly Mihael Varosanec Peter Kosa Vesna Prchkovska David Moreno-Dominguez Bibiana Bielekova |
| author_facet | Erin Kelly Mihael Varosanec Peter Kosa Vesna Prchkovska David Moreno-Dominguez Bibiana Bielekova |
| author_sort | Erin Kelly |
| collection | DOAJ |
| description | Composite MRI scales of central nervous system tissue destruction correlate stronger with clinical outcomes than their individual components in multiple sclerosis (MS) patients. Using machine learning (ML), we previously developed Combinatorial MRI scale (COMRISv1) solely from semi-quantitative (semi-qMRI) biomarkers. Here, we asked how much better COMRISv2 might become with the inclusion of quantitative (qMRI) volumetric features and employment of more powerful ML algorithm. The prospectively acquired MS patients, divided into training (n = 172) and validation (n = 83) cohorts underwent brain MRI imaging and clinical evaluation. Neurological examination was transcribed to NeurEx™ App that automatically computes disability scales. qMRI features were computed by lesion-TOADS algorithm. Modified random forest pipeline selected biomarkers for optimal model(s) in the training cohort. COMRISv2 models validated moderate correlation with cognitive disability [Spearman Rho = 0.674; Lin's concordance coefficient (CCC) = 0.458; p < 0.001] and strong correlations with physical disability (Spearman Rho = 0.830–0.852; CCC = 0.789–0.823; p < 0.001). The NeurEx led to the strongest COMRISv2 model. Addition of qMRI features enhanced performance only of cognitive disability model, likely because semi-qMRI biomarkers measure infratentorial injury with greater accuracy. COMRISv2 models predict most granular clinical scales in MS with remarkable criterion validity, expanding scientific utilization of cohorts with missing clinical data. |
| first_indexed | 2024-04-13T12:27:40Z |
| format | Article |
| id | doaj.art-14079176d997486699c60cae8348cbbc |
| institution | Directory Open Access Journal |
| issn | 2673-8740 |
| language | English |
| last_indexed | 2024-04-13T12:27:40Z |
| publishDate | 2022-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Radiology |
| spelling | doaj.art-14079176d997486699c60cae8348cbbc2022-12-22T02:46:58ZengFrontiers Media S.A.Frontiers in Radiology2673-87402022-11-01210.3389/fradi.2022.10264421026442Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patientsErin Kelly0Mihael Varosanec1Peter Kosa2Vesna Prchkovska3David Moreno-Dominguez4Bibiana Bielekova5Neuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United StatesNeuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United StatesNeuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United StatesQMENTA, Boston,MA, United StatesQMENTA, Boston,MA, United StatesNeuroimmunological Diseases Section, Laboratory of Clinical Immunology and Microbiology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD, United StatesComposite MRI scales of central nervous system tissue destruction correlate stronger with clinical outcomes than their individual components in multiple sclerosis (MS) patients. Using machine learning (ML), we previously developed Combinatorial MRI scale (COMRISv1) solely from semi-quantitative (semi-qMRI) biomarkers. Here, we asked how much better COMRISv2 might become with the inclusion of quantitative (qMRI) volumetric features and employment of more powerful ML algorithm. The prospectively acquired MS patients, divided into training (n = 172) and validation (n = 83) cohorts underwent brain MRI imaging and clinical evaluation. Neurological examination was transcribed to NeurEx™ App that automatically computes disability scales. qMRI features were computed by lesion-TOADS algorithm. Modified random forest pipeline selected biomarkers for optimal model(s) in the training cohort. COMRISv2 models validated moderate correlation with cognitive disability [Spearman Rho = 0.674; Lin's concordance coefficient (CCC) = 0.458; p < 0.001] and strong correlations with physical disability (Spearman Rho = 0.830–0.852; CCC = 0.789–0.823; p < 0.001). The NeurEx led to the strongest COMRISv2 model. Addition of qMRI features enhanced performance only of cognitive disability model, likely because semi-qMRI biomarkers measure infratentorial injury with greater accuracy. COMRISv2 models predict most granular clinical scales in MS with remarkable criterion validity, expanding scientific utilization of cohorts with missing clinical data.https://www.frontiersin.org/articles/10.3389/fradi.2022.1026442/fullmachine learning (ML)multiple sclerosisMRI biomarkersdisability outcomespredictive models |
| spellingShingle | Erin Kelly Mihael Varosanec Peter Kosa Vesna Prchkovska David Moreno-Dominguez Bibiana Bielekova Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients Frontiers in Radiology machine learning (ML) multiple sclerosis MRI biomarkers disability outcomes predictive models |
| title | Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients |
| title_full | Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients |
| title_fullStr | Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients |
| title_full_unstemmed | Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients |
| title_short | Machine learning-optimized Combinatorial MRI scale (COMRISv2) correlates highly with cognitive and physical disability scales in Multiple Sclerosis patients |
| title_sort | machine learning optimized combinatorial mri scale comrisv2 correlates highly with cognitive and physical disability scales in multiple sclerosis patients |
| topic | machine learning (ML) multiple sclerosis MRI biomarkers disability outcomes predictive models |
| url | https://www.frontiersin.org/articles/10.3389/fradi.2022.1026442/full |
| work_keys_str_mv | AT erinkelly machinelearningoptimizedcombinatorialmriscalecomrisv2correlateshighlywithcognitiveandphysicaldisabilityscalesinmultiplesclerosispatients AT mihaelvarosanec machinelearningoptimizedcombinatorialmriscalecomrisv2correlateshighlywithcognitiveandphysicaldisabilityscalesinmultiplesclerosispatients AT peterkosa machinelearningoptimizedcombinatorialmriscalecomrisv2correlateshighlywithcognitiveandphysicaldisabilityscalesinmultiplesclerosispatients AT vesnaprchkovska machinelearningoptimizedcombinatorialmriscalecomrisv2correlateshighlywithcognitiveandphysicaldisabilityscalesinmultiplesclerosispatients AT davidmorenodominguez machinelearningoptimizedcombinatorialmriscalecomrisv2correlateshighlywithcognitiveandphysicaldisabilityscalesinmultiplesclerosispatients AT bibianabielekova machinelearningoptimizedcombinatorialmriscalecomrisv2correlateshighlywithcognitiveandphysicaldisabilityscalesinmultiplesclerosispatients |