Author Of 2 Presentations
P0002 - Applying machine learning to multimodal neuroimaging data to predict visual episodic memory performance in multiple sclerosis (ID 1530)
Abstract
Background
Episodic memory (EM) impairment is common in MS. The thalamus, hippocampus, fornix and cingulum are important hubs in the Papez circuit involved in EM processing. The extent to which MS-related early structural and functional changes in these regions relate to visual EM is not known.
Objectives
To build a brain model which represents multimodal MRI measures mostly associated with visual EM processing in early MS using a machine learning approach (Elastic Net-EN).
Methods
A computerized nonverbal test of visual episodic memory (CANTAB Paired Associate Learning-PAL) was administered to 180 MS patients (RADIEMS cohort: 162 relapsing remitting, 18 clinically isolated syndrome, 123 female, mean age = 34.4 ± 7.5, mean years since diagnosis = 2.1 ± 1.4, mean premorbid intelligence = 108.3 ± 8.8). Raw scores of first trial memory were selected for statistical assessment. Neuroimaging data were acquired via a 3T MRI scanner. Lesion load over 12 regions across the brain, volume of bilateral 12 hippocampal subfields, 25 thalamic nuclei, functional and structural connectivity (assessed by fractional anisotropy and mean diffusivity) between bilateral subiculum of hippocampus and anterior thalamic nuclei and structural connectivity of fornix and cingulum were used to build a model predicting EM. Age, sex, IQ and EDSS scores were also included in the model. Five-fold cross-validation was used to train and test the model with 50 repetitions. Pearson’s correlation (r) was used to assess the univariate relationships between the continuous variables and model’s prediction accuracy.
Results
PAL test score was positively correlated with IQ (r = 0.24, p < 0.05), and negatively correlated with age and EDSS score (r = -0.25 and r = -0.23, p < 0.05). The correlation between the model’s predicted memory and actual memory scores was 0.26 ± 0.14, indicating moderate performance similar to pevious literature predicting cognitive scores from imaging variables. The most important MRI predictors of better memory were right hippocampus molecular layer and right thalamus parataenial nucleus volume, functional connectivity between left thalamus anteroventral nuclei and left hippocampus subiculum, left thalamus medial pulvinar and right hippocampus CA4 volume and lesion load in medulla and limbic lobe.
Conclusions
Atrophy and lesions in select regions of Papez Circuit are important imaging predictors of memory in early MS. A next essential step to understanding disease-specificity of these findings is comparison to matched health controls.
P0827 - Speed of Lexical Access Contributes to Verbal Memory Retrieval in MS. (ID 1060)
Abstract
Background
Verbal memory deficits are common in persons with multiple sclerosis (MS). Memory deficits associated with hippocampal pathology may contribute; however, the hippocampus encodes verbal memories by binding together semantic content present within the cortex. Recent evidence for early parietal cortical atrophy and subtle language-related deficits (i.e. speed of lexical access) in MS suggest that individual differences in language function may contribute to verbal memory.
Objectives
To investigate whether language ability independently contributes to verbal memory performance in persons with MS.
Methods
Analyses were performed on independent research and clinical samples of relapsing-remitting MS. In the research sample (n=185), word-list memory was assessed by the Selective Reminding Test (SRT), and in the clinical sample (n=227), word-list memory was assessed by the Hopkins Verbal Learning Test, Revised (HVLT-R). In both samples when controlling for age, sex, premorbid verbal IQ, and word-list Total Learning, stepwise regression (entry p<.05) predicted word-list delayed recall with Symbol Digit Modalities Test (SDMT), processing speed (Stroop, Pattern Comparison, Decision Speed in research sample; Wechsler Adult Intelligence Scale, Fourth Edition [WAIS-IV] Symbol Search subtest in clinical sample), nonverbal memory (CANTAB Paired Associate Learning [PAL]), and language tasks (rapid automatized naming [RAN], animal naming). The Brief Visuospatial Memory Test, Revised (BVMT-R) was also used in the research sample to assess nonverbal memory. Healthy controls (n=50) were assessed using the same battery as the research sample.
Results
In the research sample, SRT delayed recall was independently predicted by Total Learning (partial r (rp)=.658, p<.001), nonverbal memory (BVMT-R, rp=.204, p=.006), and language (RAN, rp=.204, p=.006). These findings were replicated in the clinical sample: HVLT-R delayed recall was independently predicted by Total Learning (rp=.659, p<.001), language (RAN, rp=.206, p=.002), and nonverbal memory (rp=.144, p=.032), but also SDMT (rp=.135, p=.044). Demonstrating specificity to MS, there was no relationship between word-list delayed recall and RAN among healthy controls (rp=.020, p=.894).
Conclusions
Results suggest that language ability (speed of lexical access assessed by RAN) contributes to delayed recall of word lists independent of initial total learning scores in both research and replication clinical samples. These findings highlight the need to consider language changes as a component of verbal memory in MS.