Christian Meisel, MD

"It is clear that even if you have something that statistically may predict a seizure, it’s not clear that this will be clinically useful. If there are a lot of false alarms, people may not take the device seriously anymore. In fact, it may be harmful.”

Seizure forecasting, or the ability to predict when a seizure is coming, provides a number of obvious advantages for patients with epilepsy and the clinicians that provide clinical care for them. For patients, having this ability may help them plan their day better, avoid certain activities, and alert caregivers to when a seizure may be oncoming. From a clinician perspective, seizure forecasting can help personalize a patient’s treatment regimen even further by catering certain therapies around time frames when seizures are more frequent.

Though the execution of this concept would resolve a number of issues, there are challenges associated with developing devices that do this forecasting. Sensitivity is among the more notable. If a device is too sensitive, it runs the risk of incorrectly predicting a seizure, which could lead to a false alarm and a call to 9-1-1. As a result, the treatment landscape for these devices remains relatively stagnant. Although, in February 2018, Empactica’s Embrace became the world’s first smart watch to be cleared by the FDA to monitor generalized tonic-clonic seizures and alert caregivers for help.

American Epilepsy Society (AES) Virtual Meeting

, December 4–8, 2020, Christian Meisel, MD, PhD, presented his study which evaluated the use of multi-modal wristband data to forecast seizures. He sat down with 

 to discuss those data, what the treatment landscape looks like for these seizure forecasting devices, and the challenges associated with developing them.

Embrace by Empactica is the world’s first smart watch to be cleared by FDA for use in neurology. News release. Empactica. February 5, 2020. Accessed December 15, 2020. 

https://www.prnewswire.com/news-releases/embrace-by-empatica-is-the-worlds-first-smart-watch-to-be-cleared-by-fda-for-use-in-neurology-300593398.html

Videos

The neurologist from Universitätsmedizin Berlin and Berlin Institute of Health provided his insight on the reasons for the limited number of FDA-approved seizure forecasting devices.

Christian Meisel, MD, PhD: Treatment Landscape for Seizure Forecasting Devices

"If we combined data and increased the data sets from, potentially, other labs and build longer recording methods that collect longer periods of time, then we can improve this algorithm even further. At least, that’s what our data suggest.”

, December 4–8, 2020, found easy-to-use, non-invasive devices in combination with deep learning can provide statistically significant and clinically meaningful seizure forecasting. Lead author Christian Meisel, MD, PhD, and colleagues used multi-modal wristband sensor data in combination with the Empactica E4 device on 69 persons with epilepsy (PWE) in their clinical trial.

The results proved to be positive, with a mean prediction horizon of 1896 (±101) seconds, a time that may be long enough to afford reasonable warning of seizures in advance. The researchers of the study concluded that the initial results may provide the basis for future re-evaluation, algorithm improvement and benchmarking as a step towards patient empowerment and objective epilepsy diagnostics for broad application.

Meisel, a neurologist from Universitätsmedizin Berlin and Berlin Institute of Health, sat down with 

 to discuss the specific ways of how to build from these results and what else needs to be done in the seizure forecasting field.

1. Meisel C, El Atrache R, Jackson M, et al. Machine learning from wristband sensor data for wearable, non-invasive seizure forecasting. Presented at AES 2020 Annual Meeting; December 4–8, 2020; Abstract 241

The neurologist from Universitätsmedizin Berlin and Berlin Institute of Health spoke about his study presented at AES 2020 and how the next steps following the positive results.

Christian Meisel, MD, PhD: Expanding Preliminary Data on Seizure Forecasting

"Some way to tell these patients when the seizure risk is high or low would help them plan their days better and avoid certain activities. For clinicians, having a better objective measure of seizure risk would allow them to target therapies better.”

Forecasting seizures has been a goal for epilepsy specialists for many years—if perfected, may help design and coordinate more personalized treatment strategies. Christian Meisel, MD, PhD, and colleagues recently conducted a study that found multi-modal wristband sensor data from easy-to-use, non-invasive devices in combination with deep learning to provide statistically significant and clinically useful seizure forecasting.

American Epilepsy Society (AES) Annual Meeting

, December 4–8, 2020, applied deep learning networks including long short-term memory and 1DConv to these wristband sensor data from 69 persons with epilepsy and found a mean prediction horizon of 1896 (±101) seconds. The period was deemed long enough to afford reasonable warning of seizures in advance.

Meisel, neurologist, Universitätsmedizin Berlin, and Berlin Institute of Health, sat down with 

 to discuss the findings from his study and the increased research that has gone into using devices to forecast seizures.

Meisel C, El Atrache R, Jackson M, et al. Machine learning from wristband sensor data for wearable, non-invasive seizure forecasting. Presented at AES 2020 Annual Meeting; December 4–8, 2020; Abstract 241

The neurologist from Universitätsmedizin Berlin and Berlin Institute of Health detailed his study from AES 2020 on using wristband sensor data to forecast seizures.

Christian Meisel, MD

Articles

Christian Meisel, MD, PhD: Treatment Landscape for Seizure Forecasting Devices

Christian Meisel, MD, PhD: Expanding Preliminary Data on Seizure Forecasting

Christian Meisel, MD, PhD: Forecasting Seizures Using Multi-Modal Wristband Sensors