Seizure Forecasting: Patient and Caregiver Perspectives

Abstract

Accurate seizure forecasting is emerging as a near-term possibility due to recent advancements in machine learning and EEG technology improvements. Large-scale data curation and new data element collection through consumer wearables and digital health tools such as longitudinal seizure diary data has uncovered new possibilities for personalized algorithm development that may be used to predict the likelihood of future seizures. The Epilepsy Foundation recognized the unmet need for development in seizure forecasting following a 2016 survey where an overwhelming majority of respondents across all seizure types and frequencies reported that unpredictability of seizures had the strongest impact on their life while living with or caring for someone living with epilepsy. In early 2021, the Epilepsy Foundation conducted an updated survey among those living with epilepsies and/or their caregivers to better understand the use-cases that best suit the needs of our community as seizure forecast research advances. These results will provide researchers with insight into user-acceptance of using a forecasting tool and incorporation into their daily life. Ultimately, this input from people living with epilepsy and caregivers will provide timely feedback on what the community needs are and ensure researchers and companies first and foremost consider these needs in seizure forecasting tools/product development.

Keywords: community survey; epilepsy; patient perception; seizure forecasting; seizure forecasting devices; wearable sensors.

Figure 1

Seizure Frequency of survey participants (n = 652). Bar graph showing the percentage of respondents across the various seizure types. No significant differences were found between segments using the Mann-Whitney U-Test.

Figure 2

Assessment of epilepsy community perspectives and need for forecasting tools. Bar graphs showing the percentage of survey respondents who indicated (A) whether they believed whether it was possible for a device to predict their chance of seizures; (B) whether they would use such a device if it existed; and (C) whether they believed it was important for the epilepsy community to have the device. Of those who did not believe that a device would be useful to them, (D) a bar graph indicated the breakdown of whether those respondents thought this was still an important device for the epilepsy community to have. Note that all numbers have been rounded to two significant figures. No significant differences were found between segments using the Mann-Whitney U-Test.

Figure 3

Seizure forecasting device scenario testing. (A) Bar graph indicating the breakdown by percentage of survey respondents who wanted to be alerted at different time scales for their likelihood of seizure (time ranges indicated on X-axis). (B) Pie chart breaking down the percentage of respondents who indicated whether they had a preference to use a device that would forecast seizure-prone vs. seizure-safe states. (C,D) Bar graph indicating the percentage of survey respondents that would use the device in daily planning when the device forecasted a 20% chance of seizure (C) or 70% chance of seizure (D). Note that all numbers have been rounded to two significant figures. No significant differences were found between segments using the Mann-Whitney U-Test.

Figure 4

Assessing user tolerance for error. Pie charts indicating the percentage breakdown of survey respondents that would keep using the forecasting tool if (A) there was no seizure on a day that forecasted high seizure risk or (B) there was a seizure on a day that forecasted low seizure risk. Note that all numbers have been rounded to two significant figures. No significant differences were found between segments using the Mann-Whitney U-Test.