A method for AI assisted human interpretation of neonatal EEG

Abstract

The study proposes a novel method to empower healthcare professionals to interact and leverage AI decision support in an intuitive manner using auditory senses. The method’s suitability is assessed through acoustic detection of the presence of neonatal seizures in electroencephalography (EEG). Neurophysiologists use EEG recordings to identify seizures visually. However, neurophysiological expertise is expensive and not available 24/7, even in tertiary hospitals. Other neonatal and pediatric medical professionals (nurses, doctors, etc.) can make erroneous interpretations of highly complex EEG signals. While artificial intelligence (AI) has been widely used to provide objective decision support for EEG analysis, AI decisions are not always explainable. This work developed a solution to combine AI algorithms with a human-centric intuitive EEG interpretation method. Specifically, EEG is converted to sound using an AI-driven attention mechanism. The perceptual characteristics of seizure events can be heard using this method, and an hour of EEG can be analysed in five seconds. A survey that has been conducted among targeted end-users on a publicly available dataset has demonstrated that not only does it drastically reduce the burden of reviewing the EEG data, but also the obtained accuracy is on par with experienced neurophysiologists trained to interpret neonatal EEG. It is also shown that the proposed communion of a medical professional and AI outperforms AI alone by empowering the human with little or no experience to leverage AI attention mechanisms to enhance the perceptual characteristics of seizure events.

Applications of artificial intelligence and cognitive science in design

“…In addition, the advancements in AI have continuously promoted the results of brain encoding and decoding, interpreting brain signals into text, vocal language, and images. For instance, the acoustic interpretation of EEG brain signals, converting EEG to sound using an AI-driven attention mechanism (Gomez-Quintana et al, 2022); the interpretation of human thoughts, captured via fMRI, into words by using GPT (Tang et al, 2023); and the reconstruction from EEG signals to corresponding images based on diffusion model (Zeng et al, 2023). Bringing together AI and cognitive science has thereby offered methods and approaches to study design from new perspectives.…”

Application of Convolutional Neural Network for Decoding of 12-Lead Electrocardiogram from a Frequency-Modulated Audio Stream (Sonified ECG)

“…The authors demonstrated a significant correlation between positron emission tomography scan images and sonification spectrograms in healthy controls vs. patients with Alzheimer’s and frontotemporal dementia. Effective detection of critical events (neonatal seizures) was achieved by listening to an audio EEG signal generated by an AI-driven sonification algorithm [ 17 ]. This study showed that an hour of EEG could be analyzed in a very short time on the order of a few seconds.…”