Multiple sclerosis (MS) is a chronic autoimmune disease of the central nervous system that prominently affects young adults due to its debilitating nature. The pathogenesis of the disease is focused on the inflammation and neurodegeneration processes. Inflammation is associated with relapses, while neurodegeneration emerges in the progressive stages of the disease. Magnetic resonance imaging (MRI) is commonly used for the diagnosis of MS, and guidelines such as the McDonald criteria are available. MRI is an essential tool to demonstrate the spatial distribution and changes over time in the disease. This study discusses the use of image processing techniques for the diagnosis of MS and specifically combines the MobileNetV2 network with exemplar-based learning, IMrMr feature selection, and K-Nearest Neighbors (KNN) classification methods. Experiments conducted on two different datasets (Dataset 1 and Dataset 2) demonstrate that these methods provide high accuracy in diagnosing MS. Dataset 1 comprises 128 patients with 706 MRI images, 131 MS patients with 667 MRI images, and 150 healthy control subjects with 1373 MRI images. Dataset 2 includes an MS group with 650 MRI images and a healthy control group with 676 MRI images. The results of the study include 10-fold cross-validation results performed on different image sections (Axial, Sagittal, and Hybrid) for Dataset 1. Accuracy rates of 99.76% for Axial, 99.48% for Sagittal, and 98.02% for Hybrid sections were achieved. Furthermore, 100% accuracy was achieved on Dataset 2. In conclusion, this study demonstrates the effective use of powerful image processing methods such as the MobileNetV2 network and exemplar-based learning for the diagnosis of MS. These findings suggest that these methods can be further developed in future research and offer significant potential for clinical applications in the diagnosis and monitoring of MS.

Alzheimer's disease (AD) is a common cause of dementia. We aimed to develop a computationally efficient yet accurate feature engineering model for AD detection based on electroencephalography (EEG) signal inputs. New method: We retrospectively analyzed the EEG records of 134 AD and 113 non-AD patients. To generate multilevel features, a multilevel discrete wavelet transform was used to decompose the input EEG-signals. We devised a novel quantum-inspired EEG-signal feature extraction function based on 7-distinct different subgraphs of the Goldner-Harary pattern (GHPat), and selectively assigned a specific subgraph, using a forward-forward distance-based fitness function, to each input EEG signal block for textural feature extraction. We extracted statistical features using standard statistical moments, which we then merged with the extracted textural features. Other model components were iterative neighborhood component analysis feature selection, standard shallow k-nearest neighbors, as well as iterative majority voting and greedy algorithm to generate additional voted prediction vectors and select the best overall model results. With leave-one-subject-out cross-validation (LOSO CV), our model attained 88.17% accuracy. Accuracy results stratified by channel lead placement and brain regions suggested P4 and the parietal region to be the most impactful. Comparison with existing methods: The proposed model outperforms existing methods by achieving higher accuracy with a computationally efficient quantum-inspired approach, ensuring robustness and generalizability. Cortex maps were generated that allowed visual correlation of channel-wise results with various brain regions, enhancing model explainability.

Background/Objectives: Stroke is an acute condition in which impaired cerebral perfusion causes focal or global neurological dysfunction. Serious complications are a major contributor to morbidity and mortality in patients with stroke. Malnutrition is common in this population, and nutritional markers, including the prognostic nutritional index (PNI), may be useful for early risk assessment of stroke-associated infections. Insulin resistance (IR) is also an emerging risk factor for stroke and has been associated with poor prognosis through various metabolic and inflammatory pathways. The triglyceride–glucose (TyG) index has been proposed as a reliable surrogate marker of IR. Various biochemical and clinical parameters are used to assess prognosis in patients with stroke. We investigated the prognostic value of the TyG index and PNI for mortality and early mortality, defined as death within the first 30 days, in these patients. Methods: After application of the exclusion criteria, 415 patients with stroke were included. Demographic characteristics, including age and sex, and comorbidities were reviewed. Complete blood count, biochemical parameters, C-reactive protein, blood gas measurements, and lactate levels were recorded. Brain computed tomography and diffusion-weighted magnetic resonance imaging findings were reviewed to classify patients into ischemic and hemorrhagic stroke subgroups. Patients were grouped as survivors or nonsurvivors, and deaths within the first 30 days were classified as early mortality. PNI and TyG index values were calculated using the following formulas: PNI = 10 × serum albumin (g/dL) + 0.005 × total lymphocyte count (cells/mm³); TyG index = ln [fasting triglycerides (mg/dL) × fasting blood glucose (mg/dL)/2]. Results: Of the 415 patients included, 389 (93.7%) had ischemic stroke and 26 (6.3%) had hemorrhagic stroke. The median age was 74 years (IQR, 65.0–81.0), and the sex distribution was balanced: 207 patients (49.9%) were women and 208 (50.1%) were men. The PNI was lower in nonsurvivors than in survivors in the overall stroke cohort (ischemic and hemorrhagic stroke combined; 40.86 ± 8.02 vs. 46.88 ± 6.85, p < 0.001), the ischemic stroke subgroup (41.12 ± 8.77 vs. 46.82 ± 6.83, p = 0.001), and the hemorrhagic stroke subgroup (39.79 ± 3.79 vs. 48.17 ± 7.32, p = 0.006). The PNI was also lower in patients who died within the first 30 days than in survivors in the overall cohort (41.86 ± 8.42 vs. 46.88 ± 6.85, p < 0.001), the ischemic stroke subgroup (42.46 ± 8.90 vs. 46.82 ± 6.83, p = 0.002), and the hemorrhagic stroke subgroup (38.60 ± 4.35 vs. 48.17 ± 7.32, p = 0.012). Conclusions: Biomarkers calculated using simple hematological parameters have a significant impact on mortality and early mortality in stroke patients (both ischemic and hemorrhagic stroke). When we examined the effects of these TyG and PNI markers on mortality in stroke patients in our study, we observed that the PNI had a significant impact on mortality. Although our findings suggest that the PNI independently predicts mortality or could guide risk assessment in the emergency department, we consider this an exploratory observation, as stroke severity measures—such as the NIHSS—and relevant treatment data were not included in our analyses. However, we believe that single-point TyG values do not carry sufficient significance regarding mortality; therefore, future research should take into account cumulative, repeated TyG measurements obtained during patient follow-up.