Key result
Quantified EEG-based machine learning detects ICU seizures with ~75% sensitivity.
Why the study?
Seizure diagnosis in ICU patients is challenging due to visual detection limitations and requires diverse, extensive EEG data for effective automated detection methods.
Can machine learning algorithms based on quantified EEG data accurately detect seizures in ICU patients?
Observational (n=71)
No
Can machine learning algorithms based on quantified EEG data accurately detect seizures in ICU patients?
Effect estimate: Average F1 score of 0.76
Machine learning models based on quantified EEG data show promise for automated seizure detection in ICU patients, with optimal model choice depending on the underlying pathology.
May aid automated ICU seizure detection; leaves open prospective validation and pathology-specific optimization.
Developing interfaces for seizure diagnosis, often challenging to detect visually, is rising. However, their effectiveness is constrained by the need for diverse and extensive databases. This study aimed to create a seizure detection methodology incorporating detailed information from each EEG channel and accounts for frequency band variations linked to the primary brain pathology leading to ICU admission, enhancing our ability to identify epilepsy onset. This study involved 460 video-electroencephalography recordings from 71 patients under monitoring. We applied signal preprocessing and conducted a numerical quantitative analysis in the frequency domain. Various machine learning algorithms were assessed for their efficacy. The k-nearest neighbours (KNN) model was the most effective in our overall sample, achieving an average F1 score of 0.76. For specific subgroups, different models showed superior performance: Decision Tree for ‘Epilepsy’ (average F1 score of 0.80) and ‘Craniencephalic Trauma’ (average F1 score of 0.84), Random Forest for ‘Cardiorespiratory Arrest’ (average F1 score of 0.89) and ‘Brain Haemorrhage’ (average F1 score of 0.84). In the categorisation of seizure types, Linear Discriminant Analysis was most effective for focal seizures (average F1 score of 0.87), KNN for generalised (average F1 score of 0.84) and convulsive seizures (average F1 score of 0.88), and logistic regression for non-convulsive seizures (average F1 score of 0.83). Our study demonstrates the potential of using classifier models based on quantified EEG data for diagnosing seizures in ICU patients. The performance of these models varies significantly depending on the underlying cause of the seizure, highlighting the importance of tailored approaches. The automation of these diagnostic tools could facilitate early seizure detection.
No takes yet. Share an insight, caveat, or question.
López-Viñas et al. (2024) conducted an observational in Suspected seizures in Intensive Care Unit (ICU) patients (n=71). Machine learning algorithms (e.g., k-nearest neighbors, Random Forest, Decision Tree) using quantified EEG data vs. Visual inspection by experienced neurophysiologists (reference standard) was evaluated on Seizure detection performance (F1 score, sensitivity, and specificity) in the overall sample (Average F1 score of 0.76). A k-nearest neighbors machine learning model utilizing quantified EEG data achieved an average F1 score of 0.76, with 75% sensitivity and 78.8% specificity, for detecting seizures in the overall ICU patient sample.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: