Artificial intelligence to predict clinical disability in patients with multiple sclerosis using FLAIR MRI.

PURPOSE: The purpose of this study was to create an algorithm that combines multiple machine-learning techniques to predict the expanded disability status scale (EDSS) score of patients with multiple sclerosis at two years solely based on age, sex and fluid attenuated inversion recovery (FLAIR) MRI data. MATERIALS AND METHODS: Our algorithm combined several complementary predictors: a pure deep learning predictor based on a convolutional neural network (CNN) that learns from the images, as well as classical machine-learning predictors based on random forest regressors and manifold learning trained using the location of lesion load with respect to white matter tracts. The aggregation of the predictors was done through a weighted average taking into account prediction errors for different EDSS ranges. The training dataset consisted of 971 multiple sclerosis patients from the "Observatoire français de la sclérose en plaques" (OFSEP) cohort with initial FLAIR MRI and corresponding EDSS score at two years. A test dataset (475 subjects) was provided without an EDSS score. Ten percent of the training dataset was used for validation. RESULTS: Our algorithm predicted EDSS score in patients with multiple sclerosis and achieved a MSE=2.2 with the validation dataset and a MSE=3 (mean EDSS error=1.7) with the test dataset. CONCLUSION: Our method predicts two-year clinical disability in patients with multiple sclerosis with a mean EDSS score error of 1.7, using FLAIR sequence and basic patient demographics. This supports the use of our model to predict EDSS score progression. These promising results should be further validated on an external validation cohort.

fMRI brain response during sentence reading comprehension in children with benign epilepsy with centro-temporal spikes.

INTRODUCTION: Children with benign epilepsy with centro-temporal spikes (BECTS) often have language problems. Abnormal epileptic activity is found in central and temporal brain regions, which are involved in reading and semantic and syntactic comprehension. Using functional magnetic resonance imaging (fMRI), we examined reading networks in BECTS children with a new sentence reading comprehension task involving semantic and syntactic processing. METHOD: Fifteen children with BECTS (age=11y 1m ± 16 m; 12 boys) and 18 healthy controls (age=11 y 8m ± 20 m; 11 boys) performed an fMRI reading comprehension task in which they read a pair of syntactically complex sentences and decided whether the target sentence (the second sentence in the pair) was true or false with respect to the first sentence. All children also underwent an exhaustive neuropsychological assessment. RESULTS: We demonstrated weaknesses in several cognitive domains in BECTS children. During the sentence reading fMRI task, left inferior frontal regions and bilateral temporal areas were activated in BECTS children and healthy controls. However, additional brain regions such as the left hippocampus and precuneus were activated in BECTS children. Moreover, specific activation was found in the left caudate and putamen in BECTS children but not in healthy controls. Cognitive results and accuracy during the fMRI task were associated with specific brain activation patterns. CONCLUSION: BECTS children recruited a wider network to perform the fMRI sentence reading comprehension task, with specific activation in the left dorsal striatum. BECTS cognitive performance differently predicted functional activation in frontal and temporal regions compared to controls, suggesting differences in brain network organisation that contribute to reading comprehension.

Nonlinear cerebral atrophy patterns across the Alzheimer's disease continuum: impact of APOE4 genotype.

The progression of Alzheimer's disease (AD) is characterized by complex trajectories of cerebral atrophy that are affected by interactions with age and apolipoprotein E allele ε4 (APOE4) status. In this article, we report the nonlinear volumetric changes in gray matter across the full biological spectrum of the disease, represented by the AD-cerebrospinal fluid (CSF) index. This index reflects the subject's level of pathology and position along the AD continuum. We also evaluated the associated impact of the APOE4 genotype. The atrophy pattern associated with the AD-CSF index was highly symmetrical and corresponded with the typical AD signature. Medial temporal structures showed different atrophy dynamics along the progression of the disease. The bilateral parahippocampal cortices and a parietotemporal region extending from the middle temporal to the supramarginal gyrus presented an initial increase in volume which later reverted. Similarly, a portion of the precuneus presented a rather linear inverse association with the AD-CSF index whereas some other clusters did not show significant atrophy until index values corresponded to positive CSF tau values. APOE4 carriers showed steeper hippocampal volume reductions with AD progression. Overall, the reported atrophy patterns are in close agreement with those mentioned in previous findings. However, the detected nonlinearities suggest that there may be different pathological processes taking place at specific moments during AD progression and reveal the impact of the APOE4 allele.

Balanced intraintestinal nutrition: comparison of absorption degree of selected fats and emulsions of fats.

The absorption of emulsion of soybean oil, soybean oil and molted butter was compared with that of the Intralipid preparation manufactured by Vitrum. The experiments were carried out on a dog and rats using the method of isolated intestinal fistulae. It was found that the emulsion of soybean oil prepared by the authors was absorbed in a degree similar to that of Intralipid fat emulsion and that it could be used as a component of a preparation intended for balanced non-residual intraintestinal nutrition.

[Dietary pattern of workers employed in a 3-shift system]. / Sposób zywienia robotników zatrudnionych w systemie trójzmianowym (badania pilotazowe).

The studies were performed among 105 workers aged 19 to 30 years, working in a 3-shift-system for at least one year. A questionnaire method of examination was used. Each worker was asked about his usual frequency of meals, sleep time and life routine while working on different shifts, as well as about the consumption of food in the last 24 hours. Usually, regardless of the period of working shift, workers consumed few number 57 meals. Meals during the working time were eaten mostly by morning-shift workers and very rarely by night-shift workers. Comparing calorific values of the meals consumed prior to the working hours at different time of shift work it has been shown that the meals consumed before night shift had the highest values, whereas the meals consumed prior to the morning shift had the lowest values. Generally, the meals consumed by shift workers did not vary and involved a large percentage of meat products, and fats, and too little percentage of vegetables, fruit, milk and dairy products. The food consumed by the workers under examinination contained mainly fats, protein and relatively little carbohydrates and ascorbic acid. Most of the workers preferred morning shift although sleep time was longest in case of afternoon shift. Complaints typical of the night shift included great fatigue and sleepiness. The sleep time was the shortest in case of this shift and sometimes it hardly amounted to 3 hours per day. The obtained results may be used for an elaboration of the lines of most suitably arranged meals schedule for shift and night workers.