The intricate neuroinflammatory diseases multiple sclerosis (MS) and neuromyelitis optica (NMO) often present similar clinical symptoms, creating challenges in their precise detection via magnetic resonance imaging (MRI). This challenge is further compounded when detecting the active and inactive states of MS. To address this diagnostic problem, we introduce an innovative framework that incorporates state-of-the-art machine learning algorithms applied to features culled from MRI scans by pre-trained deep learning models, VGG-NET and InceptionV3. To develop and test this methodology, we utilized a robust dataset obtained from the King Abdullah University Hospital in Jordan, encompassing cases diagnosed with both MS and NMO. We benchmarked thirteen distinct machine learning algorithms and discovered that support vector machine (SVM) and K-nearest neighbor (KNN) algorithms performed superiorly in our context. Our results demonstrated KNN’s exceptional performance in differentiating between MS and NMO, with precision, recall, F1-score, and accuracy values of 0.98, 0.99, 0.99, and 0.99, respectively, using leveraging features extracted from VGG16. In contrast, SVM excelled in classifying active versus inactive states of MS, achieving precision, recall, F1-score, and accuracy values of 0.99, 0.97, 0.98, and 0.98, respectively, using leveraging features extracted from VGG16 and VGG19. Our advanced methodology outshines previous studies, providing clinicians with a highly accurate, efficient tool for diagnosing these diseases. The immediate implication of our research is the potential to streamline treatment processes, thereby delivering timely, appropriate care to patients suffering from these complex diseases.

Background: Gait deficits are common among people with multiple sclerosis (PwMS). Therefore, investigating factors that may influence walking in PwMS is important. Previous studies in older adults and other neurological populations demonstrated the relationship between sleep quality and gait performance. Despite the fact that the prevalence of poor sleep quality is very high among PwMS, little is known about the effect of sleep quality on gait among PwMS. Objective: This study aimed to explore the relationship between sleep quality and gait performance in PwMS. Methods: Forty-one PwMS participated in the study between February 2019 and December 2019. Participants were asked to walk at a self-selected speed over 10$$ m with an inertial measurement unit (IMU) attached over the back. Walking speed, step length (left and right), and step time were calculated. Sleep was estimated objectively using a wrist-worn triaxle-accelerometer; the derived parameters were sleep efficiency (SE) and the number of awakening after sleep onset (NASO). Results: SE significantly correlated with step length ($p=0.02$ ). Furthermore, the NASO significantly correlated with gait speed ($p=0.03$ ), and step-time ($p=0.02$ ). These correlations remained significant even after adjusting for age and disease duration. Conclusion: We observed that when corrected for disease duration and age there were relationships between NASO and SE to gait parameters; these observations warrant further investigations.

Multiple sclerosis (MS) causes various impairments, affecting physical, psychological, and cognitive functions. While stress is common in patients with MS (PwMS), its impact on balance and gait speed has not yet been explored. This study aimed to examine the impact of stress on balance and gait speed in PwMS while also assessing its prevalence in this population. A total of 125 individuals diagnosed with MS based on the 2017 McDonald criteria participated. Outcome measures included a socio-demographic questionnaire, the Patient Determined Disease Step (PDDS) to assess disability level, the Perceived Stress Scale (PSS) to measure stress levels, the Modified Fatigue Impact Scale (MFIS) for fatigue assessment, the Montreal Cognitive Assessment (MoCA) and Symbol Digit Modalities Test (SDMT) for cognitive function, the Berg Balance Scale (BBS) for balance, and the 10-Meter Walking Test (10-MWT) for gait speed evaluation. A significant negative correlation was found between stress and balance (r = -0.373, p = 0.0001), and a significant positive correlation was observed between stress and time taken to complete the 10-MWT (r = 0.216, p = 0.01). However, after controlling for confounders (age, BMI, PDDS, disease duration, and disease onset), these correlations were no longer significant. The findings suggest a high prevalence of stress in PwMS, with potential effects on balance and gait speed. Stress management interventions may play a crucial role in enhancing mobility and stability in PwMS. Further research is warranted to investigate additional factors influencing this relationship.