AI and Neurological Rare & Neuroimmune Diseases ── 2026-10-09
New papers on neurological rare and neuroimmune diseases and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 9 disease groups, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.
Read by disease: Basic research（1） · ALS（0） · Parkinson's（0） · Hereditary neurodegeneration（0） · Neuromuscular（0） · Multiple sclerosis（1） · NMOSD/MOGAD（0） · Myasthenia gravis（0） · Autoimmune encephalitis/CIDP/GBS（0）
Neurodegeneration and neuroimmunology research and AI
- Abstract
Assistive technologies for individuals with disabilities are crucial in promoting social inclusion and enabling them to participate more fully in daily life. This article focuses on designing and developing a cost-effective head-mounted eye-tracking system aimed at enhancing the quality of life for individuals with severe mobility impairments (locked-in syndrome, amyotrophic lateral sclerosis). This system allows patients to communicate with caregivers, send messages, and operate various devices, including wheelchairs, using only their natural eye movements. The proposed head-mounted smart control system consists of two subsystems: real-time image recording and eye state recognition. The eye state recognition system identifies faces using the Histogram of Oriented Gradients algorithm and Support Vector Machine. In the first step, the raw eye area is extracted using the Haar Cascade Classifier and facial landmark detection algorithms. The extracted eye area is analyzed in the second step to determine gaze direction by employing the YOLOv3 (You Only Look Once, Version 3) algorithm and the LeNet deep learning model. The proposed method was tested using the Columbia Gaze Data Set, part of the Columbia Vision and Graphics Center (CAVE) database maintained by Columbia University’s Computer Vision Laboratory. The results showed an impressive 98.94% accuracy in classifying eye states using the YOLOv3 deep learning model combined with facial landmark detection, demonstrating the system’s high precision. The operational evaluation of the proposed assistive solution yielded promising and encouraging results.
Journal IF-equivalent: 0.9 (OpenAlex 2-year mean citedness, value as of 2026-10-08, retrieved 2026-10-09; not the official Clarivate IF)Reference: Deif MA, Attar H, Elhoseny M, Alomoush W, Alsaqoor S, Chodakowska E, et al. Artificial Intelligence–Powered Eye-Tracking Assistive System with You Only Look Once, Version 3 for Individuals with Disabilities. ELECT. 2026 Oct 7;26. doi:10.5152/electrica.2026.25090.Checked: Abstract only
See all 1 Basic research papers →
ALS: treatment, trials and AI
No new qualifying paper for this issue.
Parkinson's disease and parkinsonism: treatment, trials and AI
No new qualifying paper for this issue.
Hereditary neurodegenerative diseases: treatment, trials and AI
No new qualifying paper for this issue.
Neuromuscular diseases (muscular dystrophy, SMA): treatment, trials and AI
No new qualifying paper for this issue.
Multiple sclerosis: treatment, trials and AI
- Abstract
INTRODUCTION: Accurate segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) is fundamental for robust disease monitoring and for the evaluation of therapeutic efficacy. Within Internet of Medical Things (IoMT)-based diagnostic infrastructures, where deep learning models serve as autonomous computational nodes embedded in interconnected clinical workflows, ensuring reliable lesion detection without continuous human supervision is a critical operational and clinical requirement. A persistent methodological challenge is the pronounced class imbalance characteristic of MS neuroimaging datasets. This imbalance causes conventional loss functions to systematically miss small lesions, thereby directly compromising the utility of automated image analysis as an instrument for precision medicine. METHODS: This work proposes the Regularization via Gradient Attribution (RGA) framework, a module that leverages gradient-based eXplainable Artificial Intelligence (XAI) attribution maps as active supervisory signals during training. Instead of constraining the learning process exclusively at the prediction-output level, RGA imposes additional penalties on the network when false-negative lesion regions have low internal attribution and when false-positive healthy-tissue regions exhibit elevated attribution. The framework is architecturally agnostic, compatible with both convolutional and transformer-based backbone networks, and accommodating arbitrary spatial attribution techniques. RGA was evaluated on two public MS lesion segmentation datasets, MSLesSeg and 3D-MR-MS, using three backbones (nnU-Net, UNETR, TransBTS) and two XAI methods (LayerCAM, Integrated Gradients) in 5-fold cross-validation. RESULTS: On both datasets, RGA consistently improved DSC, TPR, and LTPR over the baselines. The best configuration, nnU-Net + RGA achieved a DSC of 0.7056 on MSLesSeg and 0.7466 on 3D-MR-MS, with RGA yielding the highest DSC for all backbones. Qualitative analyses further substantiate these findings by demonstrating a marked reduction in missed-lesion regions across all model architectures, without a corresponding substantial increase in false-positive predictions. DISCUSSION: By jointly providing high lesion-level detection completeness, model interpretability, and zero additional inference-time computational cost, RGA represents a methodologically grounded approach compatible with IoMT-oriented precision-medicine pipelines, while requiring dedicated deployment validation before clinical or edge-device implementation.
Journal IF-equivalent: 2.6 (OpenAlex 2-year mean citedness, value as of 2026-10-08, retrieved 2026-10-09; not the official Clarivate IF)Reference: Giugliano S, Sannino G. Regularization via gradient attribution for multiple sclerosis lesion segmentation. Front Med (Lausanne). 2026 Sep 23;13:1907567. doi:10.3389/fmed.2026.1907567; PMCID: PMC13642209.Checked: Full text checked
See all 1 Multiple sclerosis papers →
NMOSD and MOGAD: treatment, trials and AI
No new qualifying paper for this issue.
Myasthenia gravis: treatment, trials and AI
No new qualifying paper for this issue.
Autoimmune encephalitis, CIDP and Guillain-Barre syndrome: treatment, trials and AI
No new qualifying paper for this issue.