Continental generalization of a human-in-the-loop AI system for clinical seizure recognition

Yang, Yikai; Truong, Nhan Duy; Maher, Christina; Nikpour, Armin; Kavehei, Omid

doi:10.1016/j.eswa.2022.118083

Cited by 14 publications

(29 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All pre-training takes place offline, where the seizure detection model is trained using the TUH dataset (see §3.1) and the prediction model using the EPILEPSIAE dataset (see §3.2). The detection and prediction models both consist of convolutional long short-term memory modules [ 92 ] combined with a pair of fully connected layers, based on our previous work on seizure detection [ 48 ]. A summary of the architecture is provided in table 4 .…”

Section: Methodsmentioning

confidence: 99%

“…The seizure detection model is trained on the TUH seizure corpus [ 82 ] from the USA, while the prediction model is pre-trained using the European EPILEPSIAE dataset [ 83 ]. The AURA self-learning process is applied to the Australian test set from the RPAH where all human-annotated labels have been censored [ 48 ], and each patient starts with the same pre-trained prediction model that adapts over the course of their multiple monitoring sessions. Upon completion of all sessions, the sequence of predictions generated by the forecasting network is compared to the uncensored ground truth to provide a performance measure of sensitivity and the number of false alarms.…”

Section: Datasetsmentioning

confidence: 99%

“… Note: Training the detection model follows the same procedure as in [ 48 ]. The TUH seizure corpus provides dedicated validation and test sets, although the labels from the test set are unreleased.…”

Section: Datasetsmentioning

confidence: 99%

“…Detecting a seizure at the time of or immediately after onset has had far more success over forecasting seizures in advance [ 47 ]. Several machine learning techniques have been used to augment neurologist readings, leading to faster conclusions while maintaining specialist-level EEG-reading performance for the identification of seizures as they happen [ 48 – 51 ]. Unfortunately, seizure aversion is no longer an option when relying on detection mechanisms alone.…”

Section: Introductionmentioning

confidence: 99%

“…Our approach can be distinguished as we wholly do away with manual annotations, and instead use a detection model shown to perform similarly to neurologists [ 48 , 60 ]. These machine-generated detection labels are then used as targets for the prediction model.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Weak self-supervised learning for seizure forecasting: a feasibility study

et al. 2022

Self Cite

View full text Add to dashboard Cite

This paper proposes an artificial intelligence system that continuously improves over time at event prediction using initially unlabelled data by using self-supervised learning. Time-series data are inherently autocorrelated. By using a detection model to generate weak labels on the fly, which are concurrently used as targets to train a prediction model on a time-shifted input data stream, this autocorrelation can effectively be harnessed to reduce the burden of manual labelling. This is critical in medical patient monitoring, as it enables the development of personalized forecasting models without demanding the annotation of long sequences of physiological signal recordings. We perform a feasibility study on seizure prediction, which is identified as an ideal test case, as pre-ictal brainwaves are patient-specific, and tailoring models to individual patients is known to improve forecasting performance significantly. Our self-supervised approach is used to train individualized forecasting models for 10 patients, showing an average relative improvement in sensitivity by 14.30% and a reduction in false alarms by 19.61% in early seizure forecasting. This proof-of-concept on the feasibility of using a continuous stream of time-series neurophysiological data paves the way towards a low-power neuromorphic neuromodulation system.

show abstract

Section: Methodsmentioning

confidence: 99%