AI Doubles Medical Professionals’ Accuracy in Reading EEG Charts of ICU Patients
By HospiMedica International staff writers Posted on 30 May 2024 |

Electroencephalography (EEG) readings are crucial for detecting when unconscious patients may be experiencing or are at risk of seizures. EEGs involve placing small sensors on the scalp to measure the brain’s electrical signals, which are visualized as lines that fluctuate on a chart. During a seizure, these lines exhibit dramatic spikes similar to a seismograph during an earthquake, making them easy to recognize. However, other significant but subtler abnormalities, known as seizure-like events are more challenging to identify. Now, an assistive machine learning model can significantly enhance how medical professionals interpret EEG charts of patients in intensive care settings.
Researchers at Duke University (Durham, N.C., USA) utilized “interpretable” machine learning algorithms to develop this computational tool. Unlike typical machine learning models, which are often "black boxes" that make it impossible to understand how the conclusions have been arrived at, interpretable models are designed to reveal the processes behind their conclusions. The team began by analyzing EEG samples from over 2,700 patients, with more than 120 experts identifying key features in the graphs, categorizing them as seizures, one of four types of seizure-like events, or 'other.' These events appear on EEG charts as distinct shapes or patterns, but the variability of these charts means signals can be obscured by noise or blend into confusing charts.
Due to the ambiguity in these charts, the model was trained to place its decisions within a continuum rather than well-defined separate bins. Visually, this continuum can be likened to a multicolored starfish evading a predator, with each color representing a different type of seizure-like event. Each differently colored arm represents a type of seizure-like event the EEG could represent. The closer the algorithm puts a specific chart toward the tip of an arm, the more confident it is of its decision, while those placed closer to the central body are less sure. Moreover, the algorithm highlights the specific brainwave patterns it analyzed to reach its conclusions and compares the chart in question to three professionally diagnosed examples.
This approach allows medical professionals to quickly focus on relevant sections of the EEG, assess whether the identified patterns are accurate, or determine if the model's analysis is incorrect. This tool can greatly assist even those with limited experience in reading EEGs to make more informed decisions. To validate the effectiveness of this technology, a team of eight medical professionals with relevant experience categorized 100 EEG samples into six categories, both with and without AI assistance. Their accuracy improved significantly with the AI, jumping from 47% to 71%, and outperforming those who used a more opaque "black box" algorithm in prior studies. The findings were published in the journal NEJM AI on May 23, 2024
“Usually, people think that black box machine learning models are more accurate, but for many important applications, like this one, it's just not true,” said Cynthia Rudin, the Earl D. McLean, Jr. Professor of Computer Science and Electrical and Computer Engineering at Duke. “It's much easier to troubleshoot models when they are interpretable. And in this case, the interpretable model was actually more accurate. It also provides a bird's eye view of the types of anomalous electrical signals that occur in the brain, which is really useful for care of critically ill patients.”
Related Links:
Duke University
Channels
Artificial Intelligence
view channel
Innovative Risk Score Predicts Heart Attack or Stroke in Kidney Transplant Candidates
Heart researchers have utilized an innovative risk assessment score to accurately predict whether patients being evaluated for kidney transplants are at risk for future major cardiac events, such as a... Read more
AI Algorithm Detects Early-Stage Metabolic-Associated Steatotic Liver Disease Using EHRs
Liver disease, which is treatable when detected early, often goes unnoticed until it reaches advanced stages. Metabolic-associated steatotic liver disease (MASLD), the most prevalent form of liver disease,... Read moreSurgical Techniques
view channel
Easy-To-Apply Gel Could Prevent Formation of Post-Surgical Abdominal Adhesions
Surgical adhesions are a frequent and often life-threatening complication following open or laparoscopic abdominal surgery. These adhesions develop in the weeks following surgery as the body heals.... Read more
Groundbreaking Leadless Pacemaker to Prevent Invasive Surgeries for Children
Leadless pacemakers marked a significant advancement in cardiac care, primarily because traditional pacemakers are dependent on leads, which are prone to breakage over time. Currently, two FDA-approved... Read morePatient Care
view channel
Portable Biosensor Platform to Reduce Hospital-Acquired Infections
Approximately 4 million patients in the European Union acquire healthcare-associated infections (HAIs) or nosocomial infections each year, with around 37,000 deaths directly resulting from these infections,... Read more
First-Of-Its-Kind Portable Germicidal Light Technology Disinfects High-Touch Clinical Surfaces in Seconds
Reducing healthcare-acquired infections (HAIs) remains a pressing issue within global healthcare systems. In the United States alone, 1.7 million patients contract HAIs annually, leading to approximately... Read more
Surgical Capacity Optimization Solution Helps Hospitals Boost OR Utilization
An innovative solution has the capability to transform surgical capacity utilization by targeting the root cause of surgical block time inefficiencies. Fujitsu Limited’s (Tokyo, Japan) Surgical Capacity... Read more
Game-Changing Innovation in Surgical Instrument Sterilization Significantly Improves OR Throughput
A groundbreaking innovation enables hospitals to significantly improve instrument processing time and throughput in operating rooms (ORs) and sterile processing departments. Turbett Surgical, Inc.... Read moreHealth IT
view channel
Printable Molecule-Selective Nanoparticles Enable Mass Production of Wearable Biosensors
The future of medicine is likely to focus on the personalization of healthcare—understanding exactly what an individual requires and delivering the appropriate combination of nutrients, metabolites, and... Read more
Smartwatches Could Detect Congestive Heart Failure
Diagnosing congestive heart failure (CHF) typically requires expensive and time-consuming imaging techniques like echocardiography, also known as cardiac ultrasound. Previously, detecting CHF by analyzing... Read morePoint of Care
view channel
Handheld, Sound-Based Diagnostic System Delivers Bedside Blood Test Results in An Hour
Patients who go to a doctor for a blood test often have to contend with a needle and syringe, followed by a long wait—sometimes hours or even days—for lab results. Scientists have been working hard to... Read more
Smartphone-Enabled, Paper-Based Quantitative Diagnostic Platform Transforms POC Testing
Point-of-care diagnostics are crucial for public health, offering rapid, on-site testing that enables prompt diagnosis and treatment. This is especially valuable in remote or underserved regions where... Read moreBusiness
view channel
Becton Dickinson to Spin Out Biosciences and Diagnostic Solutions Business
Becton, Dickinson and Company (BD, Franklin Lakes, NJ, USA), has announced that its board of directors has unanimously authorized BD management to pursue a plan to separate BD's Biosciences and Diagnostic... Read more