Neurotechnology, AI, and Computational Neuroscience: From Theory to Clinical Application
- Artificial Intelligence in Neurology and Neuroscience
- Brain-Computer Interfaces (BCI) and Neural Prosthetics
- Wearable and Implantable Technology for Brain Monitoring
- Modeling Neural Networks and Brain Dynamics
- Artificial Intelligence and Machine Learning in Neuroscience
- Neuroinformatics and Big Data Approaches in Brain Research
- Computational Neuroscience and Neural Network Modeling
- Neuroimaging Innovations and AI Integration
- AI and Neurotechnology in Disease Prediction
- Future Directions
This session is about the layer of neuroscience that sits between the raw signal and the clinical decision — the decoders, the models, the devices and the data infrastructure that turn electrical activity and images into something a clinician can act on. Where other tracks at the Neurology Conference examine what the nervous system does or how it fails, this one examines how we measure it, compute on it, and intervene in it.
Three threads run through the programme. The first is measurement and interface: recording from cortex, scalp, blood vessel or wrist, and writing signals back through stimulation. The second is computation: statistical learning applied to neural and clinical data, and mechanistic simulation of the circuits themselves. The third is translation — the work of getting an algorithm past validation, past regulators, into a workflow, and in front of a patient without harming them. Contributions across Brain-Computer Interface research, Machine Learning in Neuroscience, and Neuroinformatics are all in scope.
A note on boundaries, so that authors submit to the right place: image acquisition — scanner physics, sequence design, contrast agents, modality comparison — belongs in the Neuroimaging and Diagnostic Techniques session. This session takes the acquired data as its starting point and concerns itself with what is computed from it. Likewise, therapeutic mechanism belongs in the therapeutics track; here we discuss the closed loop that decides when a therapy fires.
What This Session Covers
Machine learning applied to neurological data
- Deep learning for lesion segmentation, EEG screening, stroke triage and movement quantification
- Self-supervised and foundation models for neural time series
- External validation, dataset shift and site-to-site generalisation
- Calibration, label noise and honest reporting of failure cases
- Negative and null results in AI for Brain Disease Diagnosis
Brain–computer interfaces and neural prosthetics
- Invasiveness gradient: intracortical arrays, ECoG, endovascular electrodes, scalp EEG, fNIRS
- Speech restoration, cursor and robotic-arm control, communication in motor neuron disease
- Long-term signal stability and electrode–tissue interface change
- Recalibration burden and post-trial continuity of care
- Sensory feedback and bidirectional Neuroprosthetics
Decoding and neural signal analysis
- Artefact rejection, source separation and dimensionality reduction
- Latent state estimation and adaptive decoders that track signal drift
- Benchmarking studies and reusable, open pipelines
- Methods work in Neural Signal Processing and Brain Signal Decoding
Computational modelling and brain simulation
- Multi-scale models: single-neuron, spiking network, neural mass, whole-brain
- Connectome-constrained and patient-specific digital twin models
- In silico testing of interventions, including virtual epileptic patient approaches to surgical planning
- Network dynamics, oscillations and criticality
- Protein-spread models of neurodegeneration under Brain Simulation Models
Continuous monitoring: wearable and implantable systems
- Subscalp and long-term ambulatory EEG
- Responsive neurostimulation systems that log electrographic events
- Wrist-worn seizure detection; inertial sensing of tremor and bradykinesia
- Artefact burden, adherence and false-alarm tolerance in free-living conditions
- Battery and telemetry constraints; validation of digital endpoints
Data infrastructure, sharing and reproducibility
- Consortium and biobank resources for neurological data
- Standardised data organisation (BIDS) and containerised pipelines
- Cross-site harmonisation and batch-effect correction
- Federated learning that trains without moving patient data
- Data quality, provenance and the real cost of reproducibility
From model output to clinical decision
- Prodromal and preclinical detection; prognostic modelling
- Data-driven disease subtyping and treatment-response prediction
- Trial enrichment and patient selection
- Workflow integration, accountability and alert fatigue
- Health-economic case for adoption in Precision Neurology
Ethics, governance and neural data rights
- Privacy and ownership of neural data; emerging neurorights legislation
- Algorithmic bias and equity of access
- Explainability and clinician trust
- Informed consent for implanted devices; autonomy and identity in closed-loop stimulation
- Regulatory pathways and post-market surveillance of adaptive software, with Neuroethics and Society
Why Attend This Session
Explore AI and Neuroscience Synergy
Learn how artificial intelligence is revolutionizing brain research.
Hands-On Insights
Experience live demonstrations of neurotechnology tools.
Collaborate with Tech Innovators
Connect with leaders in both healthcare and technology sectors.
Prepare for Future Challenges
Address ethical and practical issues in AI-driven neurological care.
Related Sessions You May Like
Join the Global Neurology & Neuroscience Community
Connect with leading neurologists, neuroscientists, and healthcare professionals from across the globe. Share your groundbreaking research and gain insights into the latest advancements in brain science, neurological disorders, and innovative therapies shaping the future of neuroscience.
