The association between MRI brain volumes and computerized cognitive scores of people with multiple sclerosis

Exploring the relationship between manual dexterity and cognition in people with multiple sclerosis: 9-hole peg and multiple cognitive functions

AIM AND RATIONALE

Problems with manual dexterity and cognition impact the everyday performance of people with multiple sclerosis (PwMS). Accumulated findings point to the relationship between deficits in manual dexterity and auditory domains of cognition with a lack of evidence on visuospatial and verbal aspects of cognitive functioning. Therefore, this study explores the relationship between manual dexterity and cognition in a cohort of PwMS.

METHOD

This cross-sectional study collected data from 63 PwMS aged 22 to 55 through a convenient sampling method. Participants were diagnosed with relapsing-remitting multiple sclerosis (RRMS). Cognition was measured using a multi-domain computerized cognitive testing, NeuroTrax, and manual dexterity was measured using a 9-hole peg assessment. Spearman correlation was used to identify the correlation among cognition subtests as well as with manual dexterity. Linear regression analysis was also conducted to identify whether manual dexterity predicts cognitive functioning.

RESULTS

A significant negative correlation was found between 9-hole peg scores and global cognitive scores (GCS), r = -0.34, p = 006. The manual dexterity scores were also shown to predict GCS, R2= 0.165, p = 0.001.

CONCLUSION

Manual dexterity was found to not only predict cognitive dysfunction but was also associated with multiple cognitive domains. Understanding the relationship between manual dexterity and cognition and the inferred progression of deficits can assist clinicians to provide interventions at earlier stages of disease progression to potentially increase daily functioning and quality of life (QoL).

Gaining Biological Insights through Supervised Data Visualization

Dimensionality reduction-based data visualization is pivotal in comprehending complex biological data. The most common methods, such as PHATE, t-SNE, and UMAP, are unsupervised and therefore reflect the dominant structure in the data, which may be independent of expert-provided labels. Here we introduce a supervised data visualization method called RF-PHATE, which integrates expert knowledge for further exploration of the data. RF-PHATE leverages random forests to capture intricate featurelabel relationships. Extracting information from the forest, RF-PHATE generates low-dimensional visualizations that highlight relevant data relationships while disregarding extraneous features. This approach scales to large datasets and applies to classification and regression. We illustrate RF-PHATE's prowess through three case studies. In a multiple sclerosis study using longitudinal clinical and imaging data, RF-PHATE unveils a sub-group of patients with non-benign relapsingremitting Multiple Sclerosis, demonstrating its aptitude for time-series data. In the context of Raman spectral data, RF-PHATE effectively showcases the impact of antioxidants on diesel exhaust-exposed lung cells, highlighting its proficiency in noisy environments. Furthermore, RF-PHATE aligns established geometric structures with COVID-19 patient outcomes, enriching interpretability in a hierarchical manner. RF-PHATE bridges expert insights and visualizations, promising knowledge generation. Its adaptability, scalability, and noise tolerance underscore its potential for widespread adoption.

Multiple sclerosis and quality of life: The role of cognitive impairment on quality of life in people with multiple sclerosis

BACKGROUND

Multiple Sclerosis (MS), a chronic disease of the central nervous system (CNS), affects functional ability and quality of life (QoL). Depression, fatigue, and disability status are among the many factors that have been shown to impact QoL in people with MS, but the extent to which MS-related cognitive impairment is related to QoL is understudied in the literature.

OBJECTIVE

The purpose of this study was to determine relevant predictors of QoL from a wide list of symptoms including physical disability, and a multi-dimensional computerized cognitive assessment battery (CAB), depression, fatigue, and demographic variables (including employment status). In addition, the unique predictive power of cognitive impairment on QoL was explored in relation to other common factors of disease impact.

METHODS

171 people with MS (PwMS) were evaluated with a computerized assessment battery (CAB), EDSS examination, and validated Patient Reported Outcome (PRO) measures (Multiple Sclerosis Impact Scale, MSIS-29; Beck Depression Inventory - Second Edition BDI-2; and the Modified Fatigue Impact Scale, MFIS).

RESULTS

171 PwMS were included [Age: 46.02 years ± 9.85, 124 (72.5%) female]. Depression and fatigue scores were highly correlated with MSIS-29. EDSS, unemployment, memory, executive functioning, and motor skills were moderately correlated with MSIS-29. Predictors of QoL were EDSS, depression, fatigue, executive functioning, and attention. Attention and executive functioning were predictive of QoL even after controlling for demographic variables, fatigue, depression, and physical disability status.

CONCLUSION

Findings indicate the need for comprehensive and quantified evaluation of all factors associated with disease burden, which will ultimately serve to improve the QoL in PwMS through more targeted and patient-centered care.

Towards a more precise rating of neurological disability in multiple sclerosis: A new automatic and linear quantification of limbs function

INTRODUCTION

The Expanded Disability Status Scale (EDSS) is the gold standard for evaluating clinical disability in multiple sclerosis (MS) in daily practice. However, more precise clinical assessment tools are needed. We assessed a new, automated rating of the neurological examination obtained with a mobile application (Quantified Neurological Examination - QNE).

METHOD

Consecutive MS patients were assessed for EDSS score and QNE application that calculates, from the description of the examination, a global score and subscores (qFSS) corresponding to the EDSS functional system scores (FSS). Brain MRI was analysed to obtain automatic measures of brain atrophy.

RESULTS

We performed 200 examinations and included 78 patients in the MRI analysis. The global QNE score was strongly correlated with the EDSS. qFSS was statistically different according to the corresponding FSS for each function, except for the visual FSS. EDSS was predominantly correlated to the pyramidal function of the lower limbs. QNE score and qFSS had at least equivalent correlation to MRI measures than EDSS, particularly regarding the gray matter and cortical volumes.

DISCUSSION

We propose an automated method to rate neurological disability in MS. While QNE strongly correlates with EDSS, it may allow a more precise way to monitor the evolution of disability.

FDA-approved machine learning algorithms in neuroradiology: A systematic review of the current evidence for approval

Over the past decade, machine learning (ML) and artificial intelligence (AI) have become increasingly prevalent in the medical field. In the United States, the Food and Drug Administration (FDA) is responsible for regulating AI algorithms as "medical devices" to ensure patient safety. However, recent work has shown that the FDA approval process may be deficient. In this study, we evaluate the evidence supporting FDA-approved neuroalgorithms, the subset of machine learning algorithms with applications in the central nervous system (CNS), through a systematic review of the primary literature. Articles covering the 53 FDA-approved algorithms with applications in the CNS published in PubMed, EMBASE, Google Scholar and Scopus between database inception and January 25, 2022 were queried. Initial searches identified 1505 studies, of which 92 articles met the criteria for extraction and inclusion. Studies were identified for 26 of the 53 neuroalgorithms, of which 10 algorithms had only a single peer-reviewed publication. Performance metrics were available for 15 algorithms, external validation studies were available for 24 algorithms, and studies exploring the use of algorithms in clinical practice were available for 7 algorithms. Papers studying the clinical utility of these algorithms focused on three domains: workflow efficiency, cost savings, and clinical outcomes. Our analysis suggests that there is a meaningful gap between the FDA approval of machine learning algorithms and their clinical utilization. There appears to be room for process improvement by implementation of the following recommendations: the provision of compelling evidence that algorithms perform as intended, mandating minimum sample sizes, reporting of a predefined set of performance metrics for all algorithms and clinical application of algorithms prior to widespread use. This work will serve as a baseline for future research into the ideal regulatory framework for AI applications worldwide.

Cognitive impairment, fatigue and depression in multiple sclerosis: Is there a difference between benign and non-benign MS?

INTRODUCTION

Multiple Sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system (CNS). The severity of disability in people with MS (PwMS) is generally measured with the Expanded Disability Status Scale (EDSS). A variant of MS known as 'benign MS' (BMS) has been defined as an EDSS score of 3 or lower, combined with a disease duration of 10 years or longer; however, there is disagreement in the field about whether BMS really exists. Given that the EDSS does not capture cognitive issues, communication dysfunction, fatigue, depression, or anxiety properly, its ability to accurately represent disability in all PwMS, including BMS, remains questionable.

METHODS

In this study, 141 persons with BMS (PwBMS) were included, consisting of 115 females (82%) and 26 males (18%) with a mean age of 50.8 (±8.68). A computerized test battery (NeuroTrax®) was used to assess cognition, covering seven cognitive domains (memory, executive function, visual-spatial processing, verbal function, attention, information processing, and motor skills). Fatigue was measured using the Fatigue Severity Scale (FSS). The Beck Depression Inventory (BDI) was used to assess symptoms of depression. Cognitive impairment was defined for this study as when someone has a score lower than 85 in at least two subdomains of the cognitive test battery. Rates of impairment were compared to 158 persons with non-benign MS (PwNBMS; with a disease duration of 10 years and longer and an EDSS score higher than 3) and 487 PwMS with a disease duration of fewer than 10 years.

RESULTS

Cognitive impairment was found in 38% of PwBMS and in 66% of PwNBMS (p<0.001). In PwBMS, the lowest rate of impairment was found in the verbal function domain (18%) and the highest rate of impairment in the domain of information processing (32%). Fatigue and depression were found in 78% and 55% of all PwBMS, with no difference in these rates between PwBMS and PwNBMS (p = 0.787 and p = 0.316 resp.) CONCLUSION: Cognitive impairment, fatigue and depression are common among people with an EDSS-based definition of benign MS. These aspects should be incorporated into a new and better definition of truly benign MS.

The moderating roles of self-efficacy and depression in dual-task walking in multiple sclerosis: A test of self-awareness theory

OBJECTIVE

Multiple sclerosis (MS) is a debilitating neurological disease associated with a variety of psychological, cognitive, and motoric symptoms. Walking is among the most important functions compromised by MS. Dual-task walking (DTW), an everyday activity in which people walk and engage in a concurrent, discrete task, has been assessed in MS, but little is known about how it relates to other MS symptoms. Self-awareness theory suggests that DTW may be a function of the interactions among psychological, cognitive, and motor processes.

METHOD

Cognitive testing, self-report assessments for depression and falls self-efficacy (FSE), and walk evaluations [DTW and single-task walk (STW)] were assessed in seventy-three people with MS in a clinical care setting. Specifically, we assessed whether psychological factors (depression and FSE) that alter subjective evaluations regarding one's abilities would moderate the relationships between physical and cognitive abilities and DTW performance.

RESULTS

DTW speed is related to diverse physical and cognitive predictors. In support of self-awareness theory, FSE moderated the relationship between STW and DTW speeds such that lower FSE attenuated the strength of the relationship between them. DTW costs - the change in speed normalized by STW speed - did not relate to cognitive and motor predictors. DTW costs did relate to depressive symptoms, and depressive symptoms moderated the effect of information processing on DTW costs.

CONCLUSIONS

Findings indicate that an interplay of physical ability and psychological factors - like depression and FSE - may enhance understanding of walking performance under complex, real-world, DTW contexts.

"It's on the tip of my tongue!" exploring confrontation naming difficulties in patients with multiple sclerosis

BACKGROUND

Naming difficulty is commonly reported by patients with multiple sclerosis (pwMS). Though many cognitive batteries recommended for pwMS include fluency tasks, they do not include naming tasks. The aim of this study was to examine the prevalence of naming impairment in pwMS by using a measure of confrontation naming and to identify correlates with neuroimaging.

METHODS

One-hundred-eighty-five pwMS (M_age = 48.75 ± 11.23) completed neuropsychological testing and fifty had brain MRI scans within one year of neuropsychological testing. Controlling for demographic variables, partial correlations and hierarchical regressions with language tests as the outcome variables and neuroimaging variables as predictors were performed.

RESULTS

Performance on language tasks ranged within low average to average, with impairment most frequently found on a measure of confrontation naming (Boston Naming Test [BNT];27.6%), followed by a measure of phonemic fluency (Controlled Oral Word Association Test [COWAT]; 24.3%) and semantic fluency (animals [AF]; 18.3%). In the subset of patients with neuroimaging, thalamic volume had the strongest relationship with language variables, followed by white matter volume and T2 lesion volume. Language variables had no association with fractional gray matter volume. Of the language measures, BNT demonstrated the strongest relationship with MRI variables, followed by AF. There were no significant associations between neuroimaging variables and COWAT. Regression results revealed that fractional thalamic volume significantly contributed to BNT scores after adjusting for demographics, while T2 lesion volume predicted AF and no neuroimaging variables emerged as predictors for COWAT after controlling for demographics.

CONCLUSIONS

Objective naming impairment is common in pwMS and are more strongly associated with neuroimaging of MS brain pathology than verbal fluency tasks that are commonly used in cognitive batteries for pwMS. Continued research on language (especially naming) deficits and neuroimaging correlates (particularly thalamic involvement) in pwMS is needed.

Cognitive impairment in people with multiple sclerosis: Perception vs. performance - factors that drive perception of impairment differ for patients and clinicians

BACKGROUND

Neurologists' perceptions of the presence of cognitive impairment (CI) in people with multiple sclerosis (PwMS) may not always align with findings of objective cognitive assessment. The accuracy of self-reported CI in PwMS can also be highly variable across individuals, and may not align with objective measurement of cognitive disturbances. Research suggests that additional factors impact perceived cognitive ability, such as depression and fatigue. Objective cognitive screening regardless of patient or neurologist perception has been recommended but still is often limited in routine care. Moreover, comprehensive neuropsychological assessment is even less routinely done.

OBJECTIVE

To explore how neurologists' perceptions of PwMS' CI compare to the perception of the patient by determining whether PwMS and their clinicians are accurate in detecting the presence and degree of CI as defined by a multi-domain validated computerized test battery in PwMS, as well as investigate what factors influence perception of CI in each group.

METHODS

PwMS completed a computerized multi-domain cognitive testing battery, and self-reported measures of disease impact (MSIS-29), fatigue (MFIS), and depression (BDI-II). Disability was assessed by the clinician using the Expanded Disability Status Scale (EDSS). Clinicians and patients also provided an estimation of cognitive deficits along a Likert scale.

RESULTS

In this cohort of PwMS (N=202, age range: 20 to 88, gender: 71% female), their level of accuracy in detecting attention deficits (k = -.028, p = .010) was low but statistically significant. In contrast, clinicians' accuracy in detecting global CI (k = -.037, p < .001) and a number of specific domain deficits was moderate. Fatigue (p < .001) and cognitive performance (p = .012) significantly predicted patient perceived cognitive deficits. Clinician perceived cognitive performance was significantly predicted by multiple factors: cognitive scores (p < .001), physical disability (p = .011), age (p = .021), and depression (p = .038).

CONCLUSION

The need to objectively screen for CI in PwMS, regardless of perception, can be aided by a better understanding of the agreement and discrepancies between the patient and clinician regarding perceived cognitive disturbances and the presence of CI defined by a multi-dimensional objective screening battery.

Brain age as a surrogate marker for cognitive performance in multiple sclerosis

Background and purpose

Data from neuro‐imaging techniques allow us to estimate a brain's age. Brain age is easily interpretable as ‘how old the brain looks’ and could therefore be an attractive communication tool for brain health in clinical practice. This study aimed to investigate its clinical utility by investigating the relationship between brain age and cognitive performance in multiple sclerosis (MS).

Methods

A linear regression model was trained to predict age from brain magnetic resonance imaging volumetric features and sex in a healthy control dataset (HC_train, n = 1673). This model was used to predict brain age in two test sets: HC_test (n = 50) and MS_test (n = 201). Brain‐predicted age difference (BPAD) was calculated as BPAD = brain age minus chronological age. Cognitive performance was assessed by the Symbol Digit Modalities Test (SDMT).

Results

Brain age was significantly related to SDMT scores in the MS_test dataset (r = −0.46, p < 0.001) and contributed uniquely to variance in SDMT beyond chronological age, reflected by a significant correlation between BPAD and SDMT (r = −0.24, p < 0.001) and a significant weight (−0.25, p = 0.002) in a multivariate regression equation with age.

Conclusions

Brain age is a candidate biomarker for cognitive dysfunction in MS and an easy to grasp metric for brain health.

Visual evoked potential latency predicts cognitive function in people with multiple sclerosis

Prior studies have reported an association between visual evoked potentials (VEPs) and cognitive performance in people with multiple sclerosis (PwMS), but the specific mechanisms that account for this relationship remain unclear. We examined the relationship between VEP latency and cognitive performance in a large sample of PwMS, hypothesizing that VEP latency indexes not only visual system functioning but also general neural efficiency. Standardized performance index scores were obtained for the domains of memory, executive function, visual-spatial processing, verbal function, attention, information processing speed, and motor skills, as well as global cognitive performance (NeuroTrax battery). VEP P100 component latency was obtained using a standard checkerboard pattern-reversal paradigm. Prolonged VEP latency was significantly associated with poorer performance in multiple cognitive domains, and with the number of cognitive domains in which performance was ≥ 1 SD below the normative mean. Relationships between VEP latency and cognitive performance were significant for information processing speed, executive function, attention, motor skills, and global cognitive performance after controlling for disease duration, visual acuity, and inter-ocular latency differences. This study provides evidence that VEP latency delays index general neural inefficiency that is associated with cognitive disturbances in PwMS.