Pnd97 Factors Influencing Health-Related Quality of Life in Patients With Secondary Progressive Multiple Sclerosis Using Expand Trial Data

Abstract

0%. Percentage change in accuracy when validated on dataset with transformations was: RF=6.59%, GBL=0.31%, GLM=0.1%, GBT=0.1%, SVM=-0.1%. Conclusions: (1) All algorithms can extract data patterns and maintain their predictive performance under extreme transformations. (2) Boosting and treebased algorithms drastically outperform SVM and LASSO algorithms in noise-free data (3) SVM and LASSO face no decrease in performance, while Tree-based algorithms can be rendered unusable by heavy noise. (4) Ability to identify the source and degree of noise in the validation dataset is necessary to select appropriate classification algorithm. (5) Data-specific tuning is critical to assure high performance even under heavy noise.

Disutility of Cognitive Processing Speed (CPS) Impairment in the Context of Multiple Sclerosis: A Time Trade-Off (TTO) Elicitation Study

“…12-18 However, health state utility values collected by alternative methods may be accepted if sufficiently justified and documented. Taken alongside the relatively low sensitivity of the EQ-5D and EDSS measures across domains of cognitive impairment, 6,9 these results suggest that the values elicited in the current study, for states defined using the sensitive and validated SDMT measure of cognitive speed and efficiency, may form a valuable resource for future submissions.…”

“… 7 The SDMT is a performance measure that discriminates individuals with MS versus healthy controls. 8 Most studies show only a weak correlation between SDMT and the EDSS, 9 and recently the sensitivity of the EDSS to relapses was enhanced by augmenting the EDSS score with SDMT results. 10 …”

“…7 The SDMT is a performance measure that discriminates individuals with MS versus healthy controls. 8 Most studies show only a weak correlation between SDMT and the EDSS, 9 and recently the sensitivity of the EDSS to relapses was enhanced by augmenting the EDSS score with SDMT results. 10 Cost-effectiveness models for new treatment options typically incorporate estimates of patient HRQoL in the form of health state utility values.…”

Cognitive decline may not be adequately captured in economic evaluations of multiple sclerosis: are new treatments being undervalued?

“…EDSS scores have been shown to correlate with measures of physical function, but not with neuropsychological assessments 11 , suggesting that the EDSS is influenced most heavily by the assessment of physical disability. Additionally, EDSS scores were found to only weakly correlate with cognitive function in a clinical trial of siponimod in patients with SPMS 12 . Therefore, cognitive function might not have much influence on EDSS scores.…”