Epilepsy is a chronic neurological condition that affects 3.4 million people in the U.S. and 65 million worldwide. Despite the number of people with the disorder, “one-third live with uncontrollable seizures because no available treatment works for them.”
Stigma, which has surrounded those living with epilepsy for years, also presents significant barriers to treatment. Adults and children are often unfairly ostracized socially or judged due to a public who is largely misinformed about the condition. According to the Epilepsy Foundation, “Public perception and treatment of people with epilepsy are often bigger problems than actual seizures.” And the CDC notes that “Public misunderstanding and stigma can limit life opportunities for people with epilepsy.”
Epilepsy can be difficult to manage, especially without access to effective treatments for those living with it. However, new innovation that incorporates data and techniques like machine learning, may be changing the narrative for patients by enabling a more personalized and effective delivery of care.
Breakthroughs in epilepsy management
A new study found that a medical device may be able to predict seizures in patients with epilepsy using deep learning and big data.
The study used “an automated epileptic seizure prediction system that would allow patients to directly tune its sensitivity. The system would classify incoming data segments as either preictal (time before a seizure) or interictal (time between seizures) and compared its performance to that of a random predictor,” reported HealthIT Analytics. The prediction system was then placed onto a computer chip and put into a device worn by the patient to predict an upcoming seizure.
The results were encouraging—“the prediction system achieved a mean sensitivity of 68.6 percent and spent an average of 26.9 percent of the time in the warning state, which significantly outperformed the equivalent random predictor for all patients by 42.3 percent.”
With epilepsy, the wide range of seizure types and control which vary from person-to-person makes seizures difficult to predict. However, this device affords a high-level of personalization—patients and clinicians can set preferences and personalize their device in a way that works best for each individual, helping them to better manage their disorder.
“This study demonstrates that deep learning in combination with neuromorphic hardware can provide the basis for a wearable, real-time, always-on, patient-specific seizure warning system with low power consumption and reliable long-term performance.”
Another wearable, the FDA-approved Embrace seizure monitoring watch, uses an AI-based system to predict seizures. The device detects signs of seizures by continuously monitoring the patient’s wrist movements and “electrodermal activity that signals stress,” reported Medgadget.
“When seizure activity is detected, the device sends out signals via the patient’s smartphone to caregivers, notifying them of the situation.” Patient data relating to the seizure is also recorded in the app to inform physicians and patients. The interoperability of the Embrace watch makes it easier for patients living with epilepsy to have greater insight into their own health, while alerting their caregivers when intervention is needed.
Personalized care key to effective treatment
One of the biggest challenges with successfully managing epilepsy and other chronic conditions is that every person experiences illness uniquely. This is where technology is poised to be champion for patients. Specifically, as the delivery of health care becomes more patient-focused.
Personalization is key and data will help make that possible. The value of devices and digital tools that can capture data and use it in a way that will educate physicians and patients about which approach to care will be most impactful, is becoming clear. Particularly for disorders like epilepsy that are largely misunderstood and have significant barriers limiting care.