Multimodal deep learning approach to predicting neurological recovery from coma after cardiac arrest (2403.06027v1)
Abstract: This work showcases our team's (The BEEGees) contributions to the 2023 George B. Moody PhysioNet Challenge. The aim was to predict neurological recovery from coma following cardiac arrest using clinical data and time-series such as multi-channel EEG and ECG signals. Our modelling approach is multimodal, based on two-dimensional spectrogram representations derived from numerous EEG channels, alongside the integration of clinical data and features extracted directly from EEG recordings. Our submitted model achieved a Challenge score of $0.53$ on the hidden test set for predictions made $72$ hours after return of spontaneous circulation. Our study shows the efficacy and limitations of employing transfer learning in medical classification. With regard to prospective implementation, our analysis reveals that the performance of the model is strongly linked to the selection of a decision threshold and exhibits strong variability across data splits.
- Predicting Neurological Recovery from Coma After Cardiac Arrest: The George B. Moody PhysioNet Challenge 2023. Computing in Cardiology 2023;50:1–4.
- Independent functional outcomes after prolonged coma following cardiac arrest: a mechanistic hypothesis. Annals of Neurology 2020;87(4):618–632.
- PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2000;101(23):e215–e220.
- The International Cardiac Arrest Research (I-CARE) Consortium Electroencephalography Database. In Critical Care Medicine 2023; (in press).
- Dual Bayesian ResNet: A deep learning approach to heart murmur detection. In 2022 Computing in Cardiology (CinC). 2022; 1–4.
- Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017; 4700–4708.
- ROCKET: exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery 2020;34:1454–1495.
- Deep learning classification of cardiomegaly using combined imaging and non-imaging ICU data. In Medical Image Understanding and Analysis. Springer, 2021; 547–558.
- Multimodal Cardiomegaly Classification with Image-Derived Digital Biomarkers. In Medical Image Understanding and Analysis. 2022; 13–27.
- EEG-based outcome prediction after cardiac arrest with convolutional neural networks: performance and visualization of discriminative features. Human Brain Mapping 2019;40(16):4606–4617.
- Predicting neurological outcome in comatose patients after cardiac arrest with multiscale deep neural networks. Resuscitation 2021;169:86–94.
- Outcome prediction in postanoxic coma with deep learning. Critical Care Medicine 2019;47(10):1424–1432.
- Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG. In 2017 Computing in Cardiology (CinC). 2017; 1–4.
- HyperEnsemble learning from multimodal biosignals to robustly predict functional outcome after cardiac arrest. 2023 Computing in Cardiology 2023;1–4.