Crowdsourcing reproducible seizure forecasting in human and canine epilepsy

Benjamin H. Brinkmann, Joost Wagenaar, Drew Abbot, Phillip Adkins, Simone C. Bosshard, Min Chen, Quang M. Tieng, Jialune He, F. J. Muñoz-Almaraz, Paloma Botella-Rocamora, Juan Pardo, Francisco Zamora-Martinez, Michael Hills, Wei Wu, Iryna Korshunova, Will Cukierski, Charles Vite, Edward E. Patterson, Brian Litt, Gregory A. Worrell

Research output: Contribution to journalArticlepeer-review

178 Scopus citations


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 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 60GB 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 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.

Original languageEnglish (US)
Pages (from-to)1713-1722
Number of pages10
Issue number6
StatePublished - Jun 2016

Bibliographical note

Funding Information:
The authors acknowledge the generous support of the American Epilepsy Society, The Epilepsy Foundation, (which waived a portion of its normal fee for this competition), and the National Institutes of Health. Data collection, processing, analysis, and manuscript preparation were supported by NeuroVista Inc. and grants NIH-NINDS UH2/UH3 95495 (G.W.), U01-NS 73557 (G.W.), U24-NS063930 (B.L., G.W.), K01 ES025436-01 (J.W.), and R01-NS92882 (G.W.), the Mirowski family foundation, and Mayo Clinic.


  • Epilepsy
  • Experimental models
  • Intracranial EEG
  • Refractory epilepsy


Dive into the research topics of 'Crowdsourcing reproducible seizure forecasting in human and canine epilepsy'. Together they form a unique fingerprint.

Cite this