Webinars
Case Studies in Neurocritical Care AI
Explore how AI has been used to solve real clinical and data challenges in neurocritical care.
Webinars
Case Studies in Neurocritical Care AI
Free, Monthly, No Experience Necessary
This webinar series explores real-world applications of AI in neuromonitoring through case studies, shared datasets, and practical examples of how clinicians and researchers have experimented with AI tools in specific analytical workflows. Each session explores how neuro ICU data is analyzed using different approaches and what this reveals about brain injury, monitoring, and clinical decision-making. Rather than theory alone, the sessions focus on real implementations and how results should be interpreted in context.
You can register for upcoming sessions using the button below. You can also revisit past webinars and explore related educational content across our YouTube channel.
Foster a deep understanding of data handling techniques.
Engage with a collaborative learning environment.
Feel empowered to address your own data challenges.
Get access to sample code, Jupyter notebooks, and data
Interested in Being a Speaker?
Would you like to be our webinar speaker for the month? We’d love to host you and bring attention to your research!
- All
- ICP
- EEG
- Spreading Depolarizations
- Cerebral Autoregulation
- AI / Machine Learning
Characterizing the Physiology of Circulatory Arrest in Humans
Dr. Mypinder Sekhon presents a multi-pronged approach for the physiology of the circulatory arrest in humans, to understand the processes that underpin death determination and cerebral ischemia.
Personalizing the Pressure Reactivity Index for Quantifying Cerebral Autoregulation in Neurocritical Care
Jennifer Briggs presents a personalized approach to the Pressure Reactivity Index (PRx) for quantifying cerebral autoregulation. Her work improves the accuracy and reliability of PRx by accounting for patient-specific variability and algorithmic sensitivity, advancing clinical decision-making in neurocritical care.
A Novel Methodology for Intracranial Pressure Subpeak Identification
Xu Han, in collaboration with mentors at the University of Cincinnati, presents a new method for identifying subpeaks in intracranial pressure (ICP) waveforms in traumatic brain injury patients. His work improves visualization and computational efficiency, enabling real-time analysis and better patient monitoring.
Automated Detection of Spreading Depolarizations in Electrocorticography
Jed Hartings and Sreekar Puchala explore real-time, automated detection of spreading depolarizations in electrocorticography, highlighting the potential of algorithmic monitoring to enhance clinical adoption, reduce reliance on manual review, and offer new insights into SD waveforms through systematic, cloud-based analysis.
Body, Brain, Behavior: Non-Invasive Neurotechnologies for Peak Performance and Cerebral Health
Jana Kainerstorfer explores non-invasive neurotechnologies for brain health, highlighting near-infrared optical imaging with EEG for disease monitoring, performance optimization, and applications in clinical and extreme environments.
EEG Signal Processing and Machine Learning for Coma Recovery Prediction in Critical Care
Dr. Morteza Zabihi examines recent approaches developed for EEG analysis in critical care, discusses key challenges of applying machine learning in healthcare, and explores strategies for building trustworthy, robust AI models.
WAVEFRONT: Noninvasive, Automated Detection of Cortical Spreading Depolarizations Using Scalp EEG
Dr. Alireza Chamanzar & John McNamee from Precision Neuroscopics discuss WAVEFRONT, allowing users to review detections, temporal and spatial signal patterns, propagation speed, and CSD frequency over time.
Predicting the Trajectory of ICP in TBI Patients: Evaluation of a Foundation Model for Time Series
Florian van Leeuwen explores whether pre-trained (foundation) models, leveraging the power of transfer learning, hold the key to predicting intracranial pressure changes in TBI patients.
Automated Artifact Detection for ABP Data From Heuristics to Deep Neural Networks
Tony Okeke explores innovative approaches to identifying artifacts in arterial blood pressure (ABP) data using a variety of machine learning techniques.
NCC Big Data Analysis: Is Unsupervised Clustering a Solution?
Jeanette Tas provides an overview of how unsupervised clustering, which uncovers new data patterns, has been applied to the field of neurocritical care.
Using Deep Learning to Analyze the Intracranial Pressure Signal in Traumatic Brain Injury Patients
Dr. Agnieszka Kazimierska and Cyprian Mataczyński showcase their deep learning-based approach for analyzing intracranial pressure (ICP) pulse waveform morphology and predicting potentially life-threatening episodes of elevated ICP.
COIN: A Novel qEEG Index to Detect Stroke and Cerebral Ischemia
Dr. Caffarelli discusses barriers to broad use of EEG for stroke screening and introduces the COIN index, providing an intuitive threshold-based readout of focal power suppression associated with stroke.
An Approach to Visualize and Detect Features of Brain Injury Progression
Dr. Balança & Dr. Ghibaudo explore how to visualize and analyze the interplay between markers of cortical injury such as cortical spreading depolarization and subcortical impairment such as heart rate and respiratory rate variability.
Multicenter ICU EEG Collaboration: Opportunities & Pitfalls
Dr. Amorim discusses his experience developing the International Cardiac Arrest Research (I-CARE) consortium, a multicenter EEG database of 1,000+ patients with coma post-cardiac arrest. He reviews challenges in EEG data harmonization and algorithm deployment as well as discuss the experience of releasing this dataset to the 2023 George B. Moody Physionet Challenge.
A Data-Driven Disease Course of TBI: Mining Prognostic Trajectories from ICU Data
Shubhayu speaks on integrating heterogeneous medical record data to model how clinical course influences 6-month GOSE outcomes. Using a prospective TBI cohort, he trains recurrent neural networks to predict ordinal GOSE scores every 2 hours from a token-embedded time series, incorporating missing values. His approach converts large patient records into interpretable time series with minimal processing.
Beta Oscillations & Traveling Waves With Recovery From TBI
Dr. Vaz covers the return of intracranial beta oscillations and traveling waves with recovery from traumatic brain injury.
Predicting 6-Month GOS-E from ICP and Brain Oxygenation
Ethan Moyer demonstrates a few techniques for predicting GOS-E outcomes on the BOOST II patients using Python.
Data Exploration through Multimodal Animation
Dr. Ramon Diaz-Arrastia speaks on his experience as a leader in TBI research and how analytics and big data can advance his work into the future.
Structuring Unstructured Data
Professor Ed Kim from Drexel University’s College of Computing and Informatics brings us up to speed on the background to modern AI, machine learning, and deep learning methods.
The Groundwork for Multimodal Machine Learning
Professor Ed Kim from Drexel University’s College of Computing and Informatics brings us up to speed on the background to modern AI, machine learning, and deep learning methods.