Biology subjects

Mohammad, U.

Publications and source records attributed to Mohammad, U..

3 recordsLinked to original sources

bioRxiv2025

Transcranial Magnetic Stimulation Reduces Non-Decision Time in Perceptual Decisions

Perceptual decision-making enables humans to process sensory information and translate it into goal-directed actions. A critical component of this process is response time, which declines with age due to the slowing of both non-decision processes and evidence accumulation. While perceptual learning has been shown to counteract these declines, it remains unclear whether non-decision processes can be accelerated through direct neural stimulation, bypassing the need for long training sessions. Here, we propose that Transcranial Magnetic Stimulation (TMS) can enhance perceptual decision-making by specifically reducing non-decision time. To test this hypothesis, we tracked response times during a perceptual learning task while recording brain activity. Using the Drift Diffusion Model, we quantified the effects of TMS on mental speed and non-decision time. Our findings reveal that perceptual learning decreases response time by simultaneously increasing mental speed and reducing non-decision time. Crucially, TMS application to brain regions associated with perceptual learning further shortened non-decision time without altering mental speed. These results demonstrate that TMS can selectively accelerate non-decision processes, offering a promising intervention for mitigating age-related cognitive slowing and enhancing decision efficiency. Significance StatementPerceptual decision-making is a fundamental cognitive process that slows with age due to declines in both non-decision processes and mental speed. While perceptual learning can mitigate these declines through practice, we propose that non-decision time can also be reduced by directly stimulating neural ensembles using Transcranial Magnetic Stimulation (TMS). Our study demonstrates that TMS applied to task-relevant brain areas decreases non-decision time, thereby accelerating response speed without affecting mental speed. These findings reveal a novel mechanism for enhancing perceptual decision-making efficiency and highlight TMS as a potential tool for counteracting age-related cognitive slowing.

neuroscience↗

bioRxiv2024

Utilizing Pretrained Vision Transformers and LargeLanguage Models for Epileptic Seizure Prediction

Repeated unprovoked seizures is a major source of concern for patients suffering from epilepsy. Predicting seizures before they occur is of interest to both machine-learning scientists as well as clinicians, and is an active area of research. The variability of EEG sensors, type of seizures, and specialized knowledge required for annotating the data complicates the large-scale annotation process essential for supervised predictive models. To address these challenges, we propose the use of Vision Transformers (ViTs) and Large Language Models (LLMs) that were originally trained on publicly available image or text data. Our work leverages these pre-trained models by refining the input, embedding, and classification layers in a minimalistic fashion to predict seizures. Our results demonstrate that LLMs outperforms the ViTs in patient-independent seizure prediction achieving a sensitivity of 79.02% which is 8% higher compared to ViTs and about 12% higher compared to a custom-designed ResNet-based model. Our work demonstrates the successful feasibility of pre-trained models for seizure prediction with its potential for improving the quality of life of people with epilepsy. Our code and related materials are available open-source at: https://github.com/pcdslab/UtilLLM_EPS/

bioinformatics↗

bioRxiv2024

MLSPred-Bench: ML-Ready Benchmark LeveragingSeizure Detection EEG data for Predictive Models

Predicting epileptic seizures is a significantly challenging task as compared to detection. While electroen-cephalography (EEG) data annotated for detection is available from multiple repositories, they cannot readily be used for predictive modeling. In this paper, we designed and developed a strategy that can be used for converting any EEG big data annotated for detection into ML-ready data suitable for prediction. The generalizability of our strategy is demonstrated by executing it on Temple University Seizure (TUSZ) corpus which is annotated for seizure detection. This execution results in 12 ML-ready datasets, collectively called MLSPred-Bench benchmark, which constitutes data for training, validating and testing seizure prediction models. Our strategy uses different variations of seizure prediction horizon (SPH) and the seizure occurrence period (SOP) to make more than 150GB of ML-ready data. To illustrate that the generated data can be used for predictive modeling, we executed an ML model on all the benchmarks which resulted in variable performances when compared with the original model and its performance. We expect that our strategy can be used as a general method to transform seizure detection EEG big data into ML-ready datasets useful for seizure prediction. Our code and related materials will be made available at https://github.com/pcdslab/MLSPred-Bench.

bioinformatics↗