Towards Improved Design and Evaluation of Epileptic Seizure Predictors.

OBJECTIVE: Key issues in the epilepsy seizure prediction research are (1) the reproducibility of results (2) the inability to compare multiple approaches directly. To overcome these problems, the seizure prediction challenge was organized on Kaggle.com. It aimed at establishing benchmarks on a dataset with predefined train, validation, and test sets. Our main objective is to analyze the competition format, and to propose improvements, which would facilitate a better comparison of algorithms. The second objective is to present a novel deep learning approach to seizure prediction and compare it to other commonly used methods using patient centered metrics. METHODS: We used the competition's datasets to illustrate the effects of data contamination. Having better data partitions, we compared three types of models in terms of different objectives. RESULTS: We found that correct selection of test samples is crucial when evaluating the performance of seizure forecasting models. Moreover, we showed that models, which achieve state-of-the-art performance with respect to commonly used AUC, sensitivity, and specificity metrics, may not yet be suitable for practical usage because of low precision scores. CONCLUSION: Correlation between validation and test datasets used in the competition limited its scientific value. SIGNIFICANCE: Our findings provide guidelines which allow for a more objective evaluation of seizure prediction models.

Crowdsourcing reproducible seizure forecasting in human and canine epilepsy.

SEE MORMANN AND ANDRZEJAK DOI101093/BRAIN/AWW091 FOR A SCIENTIFIC COMMENTARY ON THIS ARTICLE : Accurate forecasting of epileptic seizures has the potential to transform clinical epilepsy care. However, progress toward reliable seizure forecasting has been hampered by lack of open access to long duration recordings with an adequate number of seizures for investigators to rigorously compare algorithms and results. A seizure forecasting competition was conducted on kaggle.com using open access chronic ambulatory intracranial electroencephalography from five canines with naturally occurring epilepsy and two humans undergoing prolonged wide bandwidth intracranial electroencephalographic monitoring. Data were provided to participants as 10-min interictal and preictal clips, with approximately half of the 60 GB data bundle labelled (interictal/preictal) for algorithm training and half unlabelled for evaluation. The contestants developed custom algorithms and uploaded their classifications (interictal/preictal) for the unknown testing data, and a randomly selected 40% of data segments were scored and results broadcasted on a public leader board. The contest ran from August to November 2014, and 654 participants submitted 17 856 classifications of the unlabelled test data. The top performing entry scored 0.84 area under the classification curve. Following the contest, additional held-out unlabelled data clips were provided to the top 10 participants and they submitted classifications for the new unseen data. The resulting area under the classification curves were well above chance forecasting, but did show a mean 6.54 ± 2.45% (min, max: 0.30, 20.2) decline in performance. The kaggle.com model using open access data and algorithms generated reproducible research that advanced seizure forecasting. The overall performance from multiple contestants on unseen data was better than a random predictor, and demonstrates the feasibility of seizure forecasting in canine and human epilepsy.media-1vid110.1093/brain/aww045_video_abstractaww045_video_abstract.