196 papers
This cohort study integrates neuroimaging data from 40 CADASIL patients with an AI-driven pipeline combining AlphaFold3, Foldseek, and molecular dynamics simulations to characterize how specific NOTCH3 domain mutations disrupt protein structure and function, ultimately suggesting that targeting POGLUT1 and stabilizing the NRR-Fab complex could be promising therapeutic strategies.
This study utilizes a Bayesian Partially Ordered Set (POSET) model on PPMI data to demonstrate that this framework offers a more granular and sophisticated characterization of Parkinson's disease cognitive dysfunction trajectories and predictors compared to traditional binary classifications.
In a controlled sleep lab study involving 31 participants, personalized transcranial alternating current stimulation (tACS) targeting individual theta and alpha brain frequencies significantly improved sleep quality by increasing efficiency by 13.4%, reducing sleep onset latency by 54%, and extending sleep duration by 26.3 minutes, suggesting a promising non-invasive treatment for insomnia.
This study demonstrates that structured prompting (specifically the CARDS framework) significantly enhances the safety, guideline adherence, and clinical reasoning of both closed-source and open-source large language models for acute stroke thrombolysis decision support, though performance gains vary by model architecture.
This study demonstrates that an intracortical brain-computer interface can successfully restore brain-to-text communication for a person with pontine stroke-induced dysarthria, achieving word error rates comparable to those in ALS patients and significantly outperforming previous electrocorticography-based systems.
This study identifies elevated expression of the TRKβ-SHC isoform in peripheral blood as a neuroprotective factor associated with preserved memory outcomes in post-stroke patients, suggesting that DNA methylation-regulated alternative splicing of NTRK2 could serve as a novel therapeutic target for post-stroke cognitive impairment.
This study demonstrates that olfactory perceptual fingerprints, which capture distinct changes in odor perception and sniffing behavior, serve as a disease-specific marker capable of accurately distinguishing Parkinson's disease from other causes of olfactory dysfunction, unlike standard clinical olfactory tests.
This study demonstrates that a novel AI-based system (SSDM-L) can accurately distinguish between nonfluent and logopenic variants of Primary Progressive Aphasia by detecting specific speech dysfluencies in brief reading tasks, offering a scalable tool to support clinical diagnosis.
This study of 630 adults with autism spectrum disorder reveals that genetic testing is significantly underutilized, with only 41% having documented testing history and just 28% of those tested receiving a positive genetic diagnosis, highlighting a critical need for increased screening and adherence to recommended testing protocols in adult ASD care.
This observational study demonstrates the feasibility and validity of a comprehensive telehealth assessment battery for characterizing Rapid-Onset Dystonia-Parkinsonism and other ATP1A3-related disorders, showing high completion rates for remote motor, speech, and neuropsychological evaluations among 59 participants.
This study demonstrates that stronger structural connectivity between the centromedian nucleus of the thalamus and the nucleus of the solitary tract (NTS) in the brainstem serves as a key predictor of seizure reduction in patients with drug-resistant epilepsy undergoing neuromodulation, suggesting a shared therapeutic mechanism with vagus nerve stimulation.
This study validates a multimodal integrative framework that combines MRI, cardiovascular, and plasma biomarkers into three distinct latent constructs, demonstrating that a composite of brain and vascular health is the strongest predictor of cognitive performance and Alzheimer's disease dementia diagnosis compared to individual measures.
This multi-center study utilized voxel-wise sweetspot mapping to identify that optimal deep brain stimulation sites for reducing tics in Gilles de la Tourette Syndrome align with specific anatomical fiber bundles connecting the pallidum and thalamus, explaining a significant portion of clinical variance across different brain targets.
This study demonstrates that a fine-tuned large language model (DeepSeek-R1) can accurately extract expert-level epilepsy and seizure phenotypes from unstructured clinical notes at scale, effectively transforming electronic health records into a valuable resource for longitudinal population research and improved patient care.
This study presents the largest single-site CSF proteogenomic analysis to date, identifying nearly 2,000 genetic variants that regulate cerebrospinal fluid proteins and using Mendelian randomization to prioritize causal targets for Alzheimer's, Parkinson's, and other neurodegenerative diseases.
In a 16-year prospective population-based study of 4,055 individuals, researchers found that while overall gut microbiome diversity was not linked to dementia risk, specific microbial compositions, including the genus *Dorea* and taxa associated with the *APOE ε4* genotype, showed modest associations with future dementia and Alzheimer's disease.