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 (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.

Confounder-adjusted MRI-based predictors of multiple sclerosis disability

Introduction

Both aging and multiple sclerosis (MS) cause central nervous system (CNS) atrophy. Excess brain atrophy in MS has been interpreted as "accelerated aging." Current paper tests an alternative hypothesis: MS causes CNS atrophy by mechanism(s) different from physiological aging. Thus, subtracting effects of physiological confounders on CNS structures would isolate MS-specific effects.

Methods

Standardized brain MRI and neurological examination were acquired prospectively in 646 participants enrolled in ClinicalTrials.gov Identifier: NCT00794352 protocol. CNS volumes were measured retrospectively, by automated Lesion-TOADS algorithm and by Spinal Cord Toolbox, in a blinded fashion. Physiological confounders identified in 80 healthy volunteers were regressed out by stepwise multiple linear regression. MS specificity of confounder-adjusted MRI features was assessed in non-MS cohort (n = 158). MS patients were randomly split into training (n = 277) and validation (n = 131) cohorts. Gradient boosting machine (GBM) models were generated in MS training cohort from unadjusted and confounder-adjusted CNS volumes against four disability scales.

Results

Confounder adjustment highlighted MS-specific progressive loss of CNS white matter. GBM model performance decreased substantially from training to cross-validation, to independent validation cohorts, but all models predicted cognitive and physical disability with low p-values and effect sizes that outperform published literature based on recent meta-analysis. Models built from confounder-adjusted MRI predictors outperformed models from unadjusted predictors in the validation cohort.

Conclusion

GBM models from confounder-adjusted volumetric MRI features reflect MS-specific CNS injury, and due to stronger correlation with clinical outcomes compared to brain atrophy these models should be explored in future MS clinical trials.

Disease biomarkers in multiple sclerosis: current serum neurofilament light chain perspectives

The continuous neuroinflammatory and neurodegenerative pathology in multiple sclerosis (MS) results in irreversible accumulation of physical and cognitive disability. Reliable early detection of MS disease processes can aid in the diagnosis, monitoring and treatment management of MS patients. Recent assay technological advancements now allow reliable quantification of serum-based neurofilament light chain (sNfL) levels, which provide temporal information regarding the degree of neuroaxonal damage. The relationship and predictive value of sNfL with clinical and cognitive outcomes, other paraclinical measures and treatment response is reviewed. sNfL measurement is an emerging, noninvasive and disease-responsive MS biomarker that is currently utilized in research and clinical trial settings. Understanding sNfL confounders and further assay standardization will allow clinical implementation of this biomarker.

Comparison of measures of comorbidity for predicting disability 12-months post-injury

BACKGROUND

Understanding the factors that impact on disability is necessary to inform trauma care and enable adequate risk adjustment for benchmarking and monitoring. A key consideration is how to adjust for pre-existing conditions when assessing injury outcomes, and whether the inclusion of comorbidity is needed in addition to adjustment for age. This study compared different approaches to modelling the impact of comorbidity, collected as part of the routine hospital episode data, on disability outcomes following orthopaedic injury.

METHODS

12-month Glasgow Outcome Scale - Extended (GOS-E) outcomes for 13,519 survivors to discharge were drawn from the Victorian Orthopaedic Trauma Outcomes Registry, a prospective cohort study of admitted orthopaedic injury patients. ICD-10-AM comorbidity codes were mapped to four comorbidity indices. Cases with a GOS-E score of 7-8 were considered "recovered". A split dataset approach was used with cases randomly assigned to development or test datasets. Logistic regression models were fitted with "recovery" as the outcome and the performance of the models based on each comorbidity index (adjusted for injury and age) measured using calibration (Hosmer-Lemshow (H-L) statistics and calibration curves) and discrimination (Area under the Receiver Operating Characteristic (AUC)) statistics.

RESULTS

All comorbidity indices improved model fit over models with age and injuries sustained alone. None of the models demonstrated acceptable model calibration (H-L statistic p < 0.05 for all models). There was little difference between the discrimination of the indices for predicting recovery: Charlson Comorbidity Index (AUC 0.70, 95% CI: 0.68, 0.71); number of ICD-10 chapters represented (AUC 0.70, 95% CI: 0.69, 0.72); number of six frequent chronic conditions represented (AUC 0.70, 95% CI: 0.69, 0.71); and the Functional Comorbidity Index (AUC 0.69, 95% CI: 0.68, 0.71).

CONCLUSIONS

The presence of ICD-10 recorded comorbid conditions is an important predictor of long term functional outcome following orthopaedic injury and adjustment for comorbidity is indicated when assessing risk-adjusted functional outcomes over time or across jurisdictions.