Search Results (142)

Parkinson’s Disease (PD) is a progressive neurodegenerative disorder for which early and reliable diagnosis remains challenging. To address this challenge, the key innovation of this work is a confidence-gated fusion mechanism that dynamically weights classifier outputs based on per-sample prediction certainty, overcoming the limitations of static ensemble strategies. Building on this idea, we propose a Confidence-Gated Hybrid CNN Ensemble that integrates CNN-based acoustic feature extraction with heterogeneous classifiers, including XGBoost, Support Vector Machines, and Random Forest. By adaptively modulating the contribution of each classifier at the sample level, the proposed framework enhances robustness against data imbalance, inter-speaker variability, and feature complexity. The method is evaluated on two benchmark PD speech datasets, where it consistently outperforms conventional machine learning and ensemble approaches, achieving a best classification accuracy of up to 97.9% while maintaining computational efficiency compatible with real-time deployment. These results highlight the effectiveness and clinical potential of confidence-aware ensemble learning for non-invasive PD detection. Full article

Background/Objectives: In recent years, MRI-based diffusion-weighted tractography techniques have uncovered additional white matter pathways that have significant roles in language processing and production. In this review, we aim to outline the major language centers of the brain and major language pathways along with association tracts that serve dual roles in both the language and limbic systems. According to the current dual-stream model of language processing, the brain’s language network is organized into a dorsal stream, responsible for mapping sound to articulation, and a ventral stream, which maps sound to meaning. Materials and Methods: The literature cited in this manuscript was identified through targeted searches of the PubMed database. Priority was given to peer-reviewed human studies, including original neuroimaging, cadaveric validation, and intraoperative stimulation studies. Non-peer-reviewed sources and publications lacking clear anatomical or functional correlation to language pathways were excluded. Results: Advances in functional MRI and diffusion weighted imaging techniques have revealed a more interconnected network, expanding our understanding beyond the classical dual-stream model of language processing. The Kamali limbic model proposed distinct ventral and dorsal limbic networks. Notably, several fiber pathways within the ventral limbic network may subserve both language and limbic functions. The association tracts with dual limbic-language functions form a critical basis for understanding the pathophysiology of language disorders accompanied by cognitive and emotional comorbidities observed in dyslexia, speech apraxia, aphasia, autism spectrum disorder, schizophrenia and post-traumatic stress disorder. Conclusions: Visualizing the language center and interconnected dual language and limbic fiber tracts highlights the importance of integrating language, executive function, and emotion in developing disease models and designing effective, targeted treatments for patients. Full article

Prader–Willi (PWS) and Angelman (AS) syndromes were the first examples in humans with errors in genomic imprinting, usually from de novo 15q11-q13 deletions of different parent origin (paternal in PWS and maternal in AS). Dozens of genes and transcripts are found in the 15q11-q13 region, and may play a role in PWS, specifically paternally expressed SNURF-SNRPN and MAGEL2 genes, while AS is due to the maternally expressed UBE3A gene. These three causative genes, including their encoding proteins, were targeted. This review article summarizes and illustrates the current understanding and cause of both PWS and AS using strategies to include the literature sources of key words and searchable web-based programs with databases for integrated gene and protein interactions, biological processes, and molecular mechanisms available for the two imprinting disorders. The SNURF-SNRPN gene is key in developing complex spliceosomal snRNP assemblies required for mRNA processing, cellular events, splicing, and binding required for detailed protein production and variation, neurodevelopment, immunodeficiency, and cell migration. The MAGEL2 gene is involved with the regulation of retrograde transport and promotion of endosomal assembly, oxytocin and reproduction, as well as circadian rhythm, transcriptional activity control, and appetite. The UBE3A gene encodes a key enzyme for the ubiquitin protein degradation system, apoptosis, tumor suppression, cell adhesion, and targeting proteins for degradation, autophagy, signaling pathways, and circadian rhythm. PWS is characterized early with infantile hypotonia, a poor suck, and failure to thrive with hypogenitalism/hypogonadism. Later, growth and other hormone deficiencies, developmental delays, and behavioral problems are noted with hyperphagia and morbid obesity, if not externally controlled. AS is characterized by seizures, lack of speech, severe learning disabilities, inappropriate laughter, and ataxia. This review captures the clinical presentation, natural history, causes with genetics, mechanisms, and description of established laboratory testing for genetic confirmation of each disorder. Three separate searchable web-based programs and databases that included information from the updated literature and other sources were used to identify and examine integrated genetic findings with predicted gene and protein interactions, molecular mechanisms and functions, biological processes, pathways, and gene-disease associations for candidate or causative genes per disorder. The natural history, review of pathophysiology, clinical presentation, genetics, and genetic-phenotypic findings were described along with computational biology, molecular mechanisms, genetic testing approaches, and status for each disorder, management and treatment options, clinical trial experiences, and future strategies. Conclusions and limitations were discussed to improve understanding, clinical care, genetics, diagnostic protocols, therapeutic agents, and genetic counseling for those with these genomic imprinting disorders. Full article

Background/Objectives: Super-selective intra-arterial chemoradiotherapy (SSIACRT) is an alternatively effective treatment for locally advanced oral cavity cancer although no comparative studies on prognosis between SSIACRT and surgical resection with or without post-operative radiotherapy (S+R) have been reported. This study aimed to compare the 5-year survival rate and Quality of Life (QoL) between S+R and SSIACRT for locally advanced oral cavity cancer. Methods: From a total of 326 patients with stage III and IV oral cavity cancer treated between 2000–2020 at a single institution, 149 patients treated with S+R and SSIACRT were analyzed by using Propensity Score Matching (PSM) method, a pseudo-randomized controlled trial, and the matched cases were retrospectively evaluated. The 5-year survival rate and QoL were evaluated using the Kaplan–Meier method and the University of Washington QoL questionnaire, respectively. Log-rank test and Cox proportional hazards model were used to compare 5-year survival rate and to assess factors affecting survival rates, respectively. Paired t-test was used to compare QoL. Results: To compare the 5-year survival rate and QoL between S+R and SSIACRT, 48 and 15 cases were matched after PSM. The 149 cases were further evaluated for covariates affecting survival rates. The 5-year disease-specific survival rate and 5-year crude survival rate were 52.4% and 44.3% for S+R and 71.3%, and 62.9% for SSIACRT, respectively. There was no statistical difference in survival rates between both treatments, based on Log-rank test analysis. Treatment method was the only independent variable that influenced survival rates. SSIACRT showed better statistical difference in QoL evaluation, specifically in appearance, activity, recreation, swallowing, speech, shoulder, taste, mood, and total score. Conclusions: Propensity score-matched analysis demonstrated survival outcomes that were comparable to, and not inferior to, S+R. However, SSIACRT was associated with superior quality-of-life outcomes compared with S+R, as shown by Cox proportional hazards modeling. These findings suggest that SSIACRT is an effective treatment option and, from a quality-of-life perspective, may be considered a preferable approach in the management of locally advanced oral cavity cancer. Full article

Dysphagia and dysarthria are common, co-occurring manifestations in neurodegenerative diseases, resulting from damage to distributed neural networks involving cortical, subcortical, cerebellar, and brainstem regions. These disorders profoundly affect patient health and quality of life through complex sensorimotor impairments. Objective: The aims was to provide a comprehensive, evidence-based review of the neuroanatomical substrates, pathophysiology, diagnostic approaches, and management strategies for dysphagia and dysarthria in neurodegenerative diseases with emphasis on their multisystem nature and integrated treatment approaches. Methods: A narrative literature review was conducted using PubMed, Scopus, and Web of Science databases (2000–2024), focusing on Parkinson’s disease (PD), amyotrophic lateral sclerosis (ALS), progressive supranuclear palsy (PSP), and multiple system atrophy (MSA). Search terms included “dysphagia”, “dysarthria”, “neurodegenerative diseases”, “neural networks”, “swallowing control” and “speech production.” Studies on neuroanatomy, pathophysiology, diagnostic tools, and therapeutic interventions were included. Results: Contemporary neuroscience demonstrates that swallowing and speech control involve extensive neural networks beyond the brainstem, including bilateral sensorimotor cortex, insula, cingulate gyrus, basal ganglia, and cerebellum. Disease-specific patterns reflect multisystem involvement: PD affects basal ganglia and multiple brainstem nuclei; ALS involves cortical and brainstem motor neurons; MSA causes widespread autonomic and motor degeneration; PSP produces tau-related damage across multiple brain regions. Diagnostic approaches combining fiberoptic endoscopic evaluation, videofluoroscopy, acoustic analysis, and neuroimaging enable precise characterization. Management requires multidisciplinary Integrated teams implementing coordinated speech-swallowing therapy, pharmacological interventions, and assistive technologies. Conclusions: Dysphagia and dysarthria in neurodegenerative diseases result from multifocal brain damage affecting distributed neural networks. Understanding this multisystem pathophysiology enables more effective integrated assessment and treatment approaches, enhancing patient outcomes and quality of life. Full article

Background: Early diagnosis of Alzheimer’s disease (AD) is essential for slowing disease progression and mitigating cognitive decline. However, conventional diagnostic methods are often invasive, time-consuming, and costly, limiting their utility in large-scale screening. There is an urgent need for scalable, non-invasive, and accessible screening tools. Methods: We propose a novel screening framework combining a pre-trained multimodal large language model with structured MMSE speech tasks. An artificial intelligence-assisted multilingual Mini-Mental State Examination system (AAM-MMSE) was utilized to collect voice data from 1098 participants in Sichuan and Chongqing. CosyVoice2 was used to extract speaker embeddings, speech labels, and acoustic features, which were converted into statistical representations. Fourteen machine learning models were developed for subject classification into three diagnostic categories: Healthy Control (HC), Mild Cognitive Impairment (MCI), and Alzheimer’s Disease (AD). SHAP analysis was employed to assess the importance of the extracted speech features. Results: Among the evaluated models, LightGBM and Gradient Boosting classifiers exhibited the highest performance, achieving an average AUC of 0.9501 across classification tasks. SHAP-based analysis revealed that spectral complexity, energy dynamics, and temporal features were the most influential in distinguishing cognitive states, aligning with known speech impairments in early-stage AD. Conclusions: This framework offers a non-invasive, interpretable, and scalable solution for cognitive screening. It is suitable for both clinical and telemedicine applications, demonstrating the potential of speech-based AI models in early AD detection. Full article

This review integrates molecular, clinical, and translational data to provide an updated understanding of GJB2-related deafness and its emerging treatment landscape. Truncating mutations in GJB2 typically cause severe-profound hearing loss (HL) phenotypes, whereas non-truncating alleles are often associated with milder or progressive phenotypes. Geographic variation in variant prevalence contributes to regional differences in disease burden. Beyond the coding region, deletions and cis-regulatory mutations within the DFNB1 locus, including GJB6 and CRYL1, can influence HL severity when compounded with other pathogenic GJB2 variants. DFNB1 hearing loss generally presents as symmetric, bilateral, and flat to gently sloping across frequencies, with preserved cochlear neurons that support excellent cochlear implant (CI) outcomes. Early implantation CI in GJB2-positive children yields superior speech and language development compared with non-GJB2 etiologies. Emerging therapies include dual-AAV (AAV1 + AAV-ie/ScPro) delivery, achieving cell-specific Cx26 restoration, adenine base-editing for dominant-negative variants, and allele-specific suppression using RNA interference or antisense oligonucleotides. Concurrent progress in human iPSC-derived cochlear organoids provides a physiologic model to advance toward clinical trials. By integrating genotype-phenotype correlations, natural history insights, and advances in molecular therapeutics, this review presents a comprehensive update on GJB2-related HL and highlights how gene-based strategies are poised to change the treatment of this condition. Full article

Parkinson’s disease (PD) alters both speech and movement, yet most automated assessments still treat these signals separately. We examined whether combining voice with head motion improves discrimination between patients and healthy controls (HC). Synchronous measurements of acoustic and inertial signals were collected using a HoloLens 2 headset. Data were obtained from 165 participants (72 PD/93 HC), following a standardized mixed-reality (MR) protocol. We benchmarked single-modality models against fusion strategies under 5-fold stratified cross-validation. Voice alone was robust (pooled AUC ≈ 0.865), while the inertial channel alone was near chance (AUC ≈ 0.497). Fusion provided a modest but repeatable improvement: gated early-fusion achieved the highest AUC (≈0.875), cross-attention fusion was comparable (≈0.873). Gains were task-dependent. While speech-dominated tasks were already well captured by audio, tasks that embed movement benefited from complementary inertial data. Proposed MR capture proved feasible within a single session and showed that motion acts as a conditional improvement factor rather than a sole predictor. The results outline a practical path to multimodal screening and monitoring for PD, preserving the reliability of acoustic biomarkers while integrating kinematic features when they matter. Full article

Speech is one of the earliest-affected modalities in Parkinson’s disease (PD). For more reliable PD evaluation, speech-based telediagnosis studies often use multiple samples from the same subject to capture variability in speech recordings. However, many existing studies split samples—rather than subjects—between training and testing, creating a biased experimental setup that allows data (samples) from the same subject to appear in both sets. This raises concerns for reliable PD evaluation due to data leakage, which results in over-optimistic performance (often close to 100%). In addition, detecting subtle vocal impairments from speech recordings using multiple feature extraction techniques often increases data dimensionality, although only some features are discriminative while others are redundant or non-informative. To address this and build a reliable speech-based PD telediagnosis system, the key contributions of this work are two-fold: (1) a uniform (fair) experimental setup employing subject-wise symmetric (stratified) splitting in 5-fold cross-validation to ensure better generalization in PD prediction, and (2) a novel hybrid data complexity-aware (HDC) feature selection method that improves class separability. This work further contributes to the research community by releasing a publicly accessible five-fold benchmark version of the Parkinson’s speech dataset for consistent and reproducible evaluation. The proposed HDC method analyzes multiple aspects of class separability to select discriminative features, resulting in reduced data complexity in the feature space. In particular, it uses data complexity measures (F4, F1, F3) to assess minimal feature overlap and ReliefF to evaluate the separation of borderline points. Experimental results show that the top-50 discriminative features selected by the proposed HDC outperform existing feature selection algorithms on five out of six classifiers, achieving the highest performance with 0.86 accuracy, 0.70 G-mean, 0.91 F1-score, and 0.58 MCC using an SVM (RBF) classifier. Full article

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative condition characterized by the degeneration of upper and lower motor neurons. This degeneration leads to a gradual muscle weakness, dysarthria, dysphagia, respiratory insufficiency, and, in some patients, alterations in cognitive and behavioral performance. Regardless of advancements made in pharmacological and gene-targeted interventions, a definitive curative treatment remains elusive. Consequently, rehabilitation plays a pivotal role in preserving autonomy, participation, and overall quality of life. This review outlines the current evidence and clinical approaches related to multidisciplinary rehabilitation in ALS. It covers physical and occupational therapy, respiratory, speech and language, psychological, and palliative care domains. Evidence supports moderate tailored exercise programs, early respiratory therapy, and structured management of mobility deficits, spasticity, pain, dysphagia, and communication impairments as key elements of symptomatic treatment. Psychological and social support, which includes the involvement of caregivers and relatives, enhances emotional well-being and coping resilience. Even with progressive development of gene-targeted and disease-modifying therapies, rehabilitation will stay relevant for maintaining long-term motor function. This review highlights the need for standardized, evidence-based rehabilitation protocols and intensified neurorehabilitation research to strengthen clinical outcomes and quality of life as key therapeutic goals in ALS management. Full article

Background/Objectives: The Mediator (MED) complex is an essential regulator of RNA polymerase II transcription. There is increasing evidence that pathogenic variants in several MED subunits are the cause of neurodegenerative and neurodevelopmental phenotypes, collectively referred to as “MEDopathies”. This review aims to summarize current knowledge on the genetic basis, clinical manifestations, and neuroradiological features of MED-related disorders. Methods: We undertook a narrative synthesis of the literature focusing on the MED subunits most commonly associated with neurological disorders, including MED1, MED8, MED11, MED12/MED12L, MED13/MED13L, MED14, MED17, MED20, MED23, MED25, MED27, and CDK8. Sources included peer-reviewed genetic, clinical, and imaging studies, supplemented by relevant case reports and cohort analyses. In addition, representative facial phenotypes associated with selected MED variants (MED11, MED12, MED13, MED13L, MED25) were visualized for educational purposes using artificial intelligence-based image generation derived from standardized clinical descriptors. Results: All MEDopathies show converging clinical patterns: global developmental delay/intellectual disability, hypotonia, epilepsy, speech disorders, and behavioral comorbidity. Non-neurological involvement, such as craniofacial or cardiac anomalies, is subunit-specific. Neuroradiological features include callosal abnormalities (agenesis, thinning, dysmorphia), delayed or hypomyelination, progressive cerebral and cerebellar atrophy, basal ganglia signaling changes, pontine hypoplasia, and, in MED27 deficiency, a “hot cross bun” sign. Gene-specific constellations emphasize catastrophic infantile progression (MED11), X-linked syndromes with callosal defects (MED12/MED12L), language-dominant phenotypes (MED13), and syndromic intellectual disability with systemic features (MED13L). Conclusions: The growing spectrum of MEDopathies argues for their recognition as a unified nosological group with overlapping clinical and radiological signatures. Characteristic MRI constellations may serve as diagnostic clues and guide targeted molecular testing. Future directions include longitudinal imaging to describe disease progression and the integration of genomic data with curated clinical radiological datasets to refine genotype-phenotype correlations. Full article

Background: Despite life-saving newborn screening programs and a life-long galactose-restricted diet, many patients with classic galactosemia continue to develop long-term debilitating neurological deficits, speech dyspraxia, and primary ovarian insufficiency (POI). In an earlier study, we showed that administration of an experimental human GALT mRNA predominantly expressed in the liver of the GalT gene-trapped mouse model augmented the expression of hepatic GALT activity, which reduced build-up of galactose and its toxic metabolites not only in the liver but also in the peripheral tissues. Moreover, we showed that the administration of GALT mRNA in the mutant mice restored whole-body galactose oxidation (WBGO), which is a functional biomarker. Methods: In this pilot study, we extended our proof-of-concept efficacy studies to a disease-relevant phenotype: motor impairment. GalT-KO mice aged 3 and 6 weeks old administered biweekly intravenous injections of 100 µL GALT mRNA at a dose of 2 mg/kg for 2 months. Motor performance was assessed using rotarod testing and composite phenotype scoring, 3 and 9 weeks following the dosing regimen. Results: Preliminary results showed that a biweekly dosing at 2 mg/kg for 2 months improved the motor performance of the animals in rotarod and composite phenotype scoring tests in a short-term experiment. Conclusions: Despite being a small-scale study, our findings suggest that when treated early in life, the experimental GALT mRNA is effective in improving the motor-related phenotypes in GalT-KO mice using the specified dosing regimen. These findings highlight the potential of mRNA-based therapies for mitigating neurological symptoms in Classic galactosemia. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor and non-motor symptoms, among which vocal impairment is one of the earliest and most prevalent. In recent years, voice analysis supported by machine learning (ML) and deep learning (DL) has emerged as a promising non-invasive method for early PD detection. We conducted a systematic review searching PubMed, Scopus, IEEE Xplore, and Web of Science databases for studies published between 2020 and September 2025. A total of 69 studies met the inclusion criteria and were analyzed in terms of dataset characteristics, speech tasks, feature extraction techniques, model architectures, validation strategies, and performance outcomes. Classical ML models such as Support Vector Machines (SVMs) and Random Forests (RFs) achieved high accuracy on small, homogeneous datasets, while DL architectures, particularly Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer-based foundation models, demonstrated greater robustness and scalability across languages and recording conditions. Despite these advances, persistent challenges such as dataset heterogeneity, class imbalance, and inconsistent validation practices continue to hinder reproducibility and clinical translation. Overall, the field is transitioning from handcrafted feature-based pipelines toward self-supervised, representation-learning frameworks that promise improved generalizability. Future progress will depend on the development of large, multilingual, and openly accessible datasets, standardized evaluation protocols, and interpretable AI frameworks to ensure clinically reliable and equitable voice-based PD diagnostics. Full article

Millions worldwide are affected by Parkinson’s disease, with the World Health Organization highlighting its growing prevalence. Early neuromotor speech impairments make voice analysis a promising tool for detecting Parkinson’s, aided by advances in deep speech embeddings. However, existing approaches often rely on either handcrafted acoustic features or opaque deep representations, limiting diagnostic performance and interoperability. To address this, we propose a multi-modal decentralized hybrid learning framework that combines structured voice biomarkers from the UCI Parkinson’s dataset (195 sustained-phonation samples from 31 subjects) with contrastive speech embeddings derived from the DAIC-WOZ corpus (189 interview recordings originally collected for depression detection) using Wav2Vec 2.0. This system employs an early fusion strategy followed by a dense neural classifier optimized for binary classification. By integrating both clinically interpretable and semantically rich features, the model captures complementary phonatory and affective patterns relevant to early-stage Parkinson’s detection. Extensive evaluation demonstrates that the proposed method achieves an accuracy of 96.2% and an AUC of 97.1%, outperforming unimodal and baseline fusion models. SHAP-based analysis confirms that a subset of features have disproportionately high discriminative value, enhancing interpretability. Overall, the proposed framework establishes a promising pathway toward data-driven, non-invasive screening for neurodegenerative conditions through voice analysis. Full article

Background: Neurological disorders are the leading cause of disability, affecting over three billion people worldwide. Amyotrophic lateral sclerosis (ALS) is among the most feared and uniformly fatal neurodegenerative diseases, with no therapy capable of restoring lost function. Methods: We report the first application of therapeutic fever to ALS using Computerized Brain-Guided Intelligent Thermofebrile Therapy (CBIT²). This fully noninvasive treatment, delivered through an FDA-approved computerized platform, digitally reengineers the 1927 Nobel Prize-recognized malarial fever therapy into a modern treatment guided by the Brain–Eyelid Thermoregulatory Tunnel. CBIT² induces therapeutic fever through synchronized hypothalamic feedback, activating heat shock proteins, which are known to restore proteostasis and neuronal function. Case presentation: A 56-year-old woman was diagnosed with progressive ALS at the Mayo Clinic, with electromyography (EMG) demonstrating fibrillation and fasciculation indicative of denervation corroborated by neurological and MRI findings; the patient was informed that she had an expected survival of three to five years. A neurologist from Northwestern University confirmed the diagnosis and thus maintained the patient on FDA-approved ALS drugs (riluzole and edaravone). Her condition rapidly worsened despite pharmacological treatment, and she underwent CBIT², resulting in (i) electrophysiological reversal with complete disappearance of denervation; (ii) biomarker correction, including reductions in neurofilament and homocysteine, IL-10 normalization (previously linked to mortality), and robust HSP70 induction; (iii) restoration of gait, swallowing, respiration, speech, and cognition; (iv) reconstitution of tongue structure; and (v) return to complex motor tasks, including golf, pickleball, and swimming. Discussion: This case provides the first documented evidence that ALS can be reversed through digitally reengineered fever therapy aligned with thermoregulation, which induces heat shock response and upregulates heat shock proteins, resulting in the patient no longer meeting diagnostic criteria for ALS and discontinuation of ALS-specific medications. Beyond ALS, shared protein-misfolding pathology suggests that CBIT² may extend to Alzheimer’s, Parkinson’s, and related disorders. By modernizing this Nobel Prize-recognized therapeutic principle with computerized precision, CBIT² establishes a framework for large-scale clinical trials. A century after fever therapy restored lost brain function and so decisively reversed dementia paralytica such that it earned the 1927 Nobel Prize in Medicine, CBIT² now safely harnesses the therapeutic power of fever through noninvasive, intelligent, brain-guided thermal modulation. Amid a global brain health crisis, fever-based therapies may offer a path to preserve thought, memory, movement, and independence for the more than one-third of humanity currently affected by neurological disorders. Full article