Seizure Forecasting from Idea to Reality. Outcomes of the My Seizure Gauge Epilepsy Innovation Institute Workshop

Abstract

The Epilepsy Innovation Institute (Ei2) is a new research program of the Epilepsy Foundation designed to be an innovation incubator for epilepsy. Ei2 research areas are selected based on community surveys that ask people impacted by epilepsy what they would like researchers to focus on. In their 2016 survey, unpredictability was selected as a top issue regardless of seizure frequency or severity. In response to this need, Ei2 launched the My Seizure Gauge challenge, with the end goal of creating a personalized seizure advisory system device. Prior to moving forward, Ei2 convened a diverse group of stakeholders from people impacted by epilepsy and clinicians, to device developers and data scientists, to basic science researchers and regulators, for a state of the science assessment on seizure forecasting. From the discussions, it was clear that we are at an exciting crossroads. With the advances in bioengineering, we can utilize digital markers, wearables, and biosensors as parameters for a seizure-forecasting algorithm. There are also over a thousand individuals who have been implanted with ambulatory intracranial EEG recording devices. Pairing up peripheral measurements to brain states could identify new relationships and insights. Another key component is the heterogeneity of the relationships indicating that pooling findings across groups is suboptimal, and that data collection will need to be done on longer time scales to allow for individualization of potential seizure-forecasting algorithms.

Forecasting cycles of seizure likelihood

“…We hypothesize that mobile apps to forecast cycles of seizure likelihood have the power to improve quality of life for people with epilepsy, even without delivering direct intervention. In support of this hypothesis, we note that unpredictability is the primary disability of epilepsy, 1 and for people with refractory seizures, quality of life is far more strongly determined by the degree of drug‐related side effects or depressive symptoms than by seizure frequency 51 . Reliable seizure forecasting has the potential to improve quality of life by reducing uncertainty and improving mood.…”

“…Medically refractory epilepsy is a condition associated with persistent uncertainty. Most people with epilepsy report that, regardless of seizure frequency, it is the unpredictability of when seizures will occur that is the most debilitating aspect of their condition 1 . A forecast of seizure likelihood could provide immense benefits to people with epilepsy, especially for those with refractory seizures.…”

“…More than 30% of all people with epilepsy cannot control their seizures with medication, 2 and for decades, new drugs have mostly failed to improve overall rates of seizure freedom 3 . Surveys have shown that seizure forecasting is considered a highly attractive management option by people with uncontrolled seizures 1 . At the same time, epilepsy research has uncovered numerous factors affecting seizure likelihood from long‐term trends in behavioural, environmental, and physiological data.…”

“…For example, some people are more prone to seizures due to stress, 4 poor sleep, 5 exercise, 6 diet, 7 weather, 8 alcohol use, 9 poor drug adherence, 10 and a multitude of other factors. Investigating the utility of these seizure risk factors and developing personalized forecasting devices is now a key goal for clinical epilepsy management 1 …”

“…It is now recognized that estimating the probability of someone having a seizure in the near future is more feasible than trying to predict the exact timing of their next seizure 12,17,20 . There are increasing efforts to develop a clinical seizure forecasting device 1 and understand user requirements 21‐23 . Patient surveys have confirmed that probabilistic forecasts are considered useful and that perfect accuracy is not a requirement of such devices 21,23 .…”