Forecasting Seizure Likelihood With Wearable Technology

Rachel E Stirling; David B Grayden; Wendyl D'Souza; Mark J Cook; Ewan Nurse; Dean R Freestone; Daniel E Payne; Benjamin H Brinkmann; Tal Pal Attia; Pedro F Viana; Mark P Richardson; Philippa J Karoly

doi:10.3389/fneur.2021.704060

Forecasting Seizure Likelihood With Wearable Technology

Front Neurol. 2021 Jul 15:12:704060. doi: 10.3389/fneur.2021.704060. eCollection 2021.

Authors

Rachel E Stirling¹, David B Grayden^{1

2

3}, Wendyl D'Souza², Mark J Cook^{2

3}, Ewan Nurse^{2

4}, Dean R Freestone⁴, Daniel E Payne¹, Benjamin H Brinkmann⁵, Tal Pal Attia⁵, Pedro F Viana^{6

7}, Mark P Richardson⁶, Philippa J Karoly^{1

2

3}

Affiliations

¹ Department of Biomedical Engineering, The University of Melbourne, Melbourne, VIC, Australia.
² Departments of Medicine and Neurology, St Vincent's Hospital, The University of Melbourne, Melbourne, VIC, Australia.
³ Graeme Clark Institute for Biomedical Engineering, The University of Melbourne, Melbourne, VIC, Australia.
⁴ Seer Medical, Melbourne, VIC, Australia.
⁵ Bioelectronics Neurophysiology and Engineering Lab, Department of Neurology, Mayo Clinic, Rochester, MN, United States.
⁶ School of Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom.
⁷ Faculty of Medicine, University of Lisbon, Lisbon, Portugal.

Abstract

The unpredictability of epileptic seizures exposes people with epilepsy to potential physical harm, restricts day-to-day activities, and impacts mental well-being. Accurate seizure forecasters would reduce the uncertainty associated with seizures but need to be feasible and accessible in the long-term. Wearable devices are perfect candidates to develop non-invasive, accessible forecasts but are yet to be investigated in long-term studies. We hypothesized that machine learning models could utilize heart rate as a biomarker for well-established cycles of seizures and epileptic activity, in addition to other wearable signals, to forecast high and low risk seizure periods. This feasibility study tracked participants' (n = 11) heart rates, sleep, and step counts using wearable smartwatches and seizure occurrence using smartphone seizure diaries for at least 6 months (mean = 14.6 months, SD = 3.8 months). Eligible participants had a diagnosis of refractory epilepsy and reported at least 20 seizures (mean = 135, SD = 123) during the recording period. An ensembled machine learning and neural network model estimated seizure risk either daily or hourly, with retraining occurring on a weekly basis as additional data was collected. Performance was evaluated retrospectively against a rate-matched random forecast using the area under the receiver operating curve. A pseudo-prospective evaluation was also conducted on a held-out dataset. Of the 11 participants, seizures were predicted above chance in all (100%) participants using an hourly forecast and in ten (91%) participants using a daily forecast. The average time spent in high risk (prediction time) before a seizure occurred was 37 min in the hourly forecast and 3 days in the daily forecast. Cyclic features added the most predictive value to the forecasts, particularly circadian and multiday heart rate cycles. Wearable devices can be used to produce patient-specific seizure forecasts, particularly when biomarkers of seizure and epileptic activity cycles are utilized.

Keywords: circadian rhythms; cycles (cyclical); multiday rhythms; seizure cycles; seizure forecasting; wearable sensors.