Natural Language Processing Identifies Patients Who May be Good Candidates for Epilepsy Surgery 

Article published by AJMC


A review of 6 studies found natural language processing (NLP) showed moderate-to-high performance levels in identifying suitable candidates to undergo epilepsy surgery, an effective, but oftentimes underutilized treatment, in which approximately 50% to 60% of patients became seizure-free after surgery. 


“This study has found that there is evidence, using multiple algorithms, that NLP may aid in the identification of candidates who may benefit from referral for epilepsy surgery evaluation,” wrote the researchers of the study. “It is noteworthy that these studies have shown that the NLP approaches may identify suitable candidates prior to the time that treating neurologists refer their patients.” 


The systemic review is published in the Journal of Clinical Neuroscience. 


Similar to machine learning, NLP uses computers to analyze or interact with human language and has various uses in health care, including information extraction, information retrieval, document categorization, and text summarization. Furthermore, NLP can aid in generating meaningful information, such as diagnosis or prognosis from electric health record data. 


Previous research has suggested that NLP may be useful in identifying patients with drug-resistant focal epilepsy, who account for about 30% of individuals with epilepsy. In the current review, researchers aimed to examine previous studies using NLP to identify patients for epilepsy surgery. 


A data search identified 1369 publication results from PubMed (n = 324), EMBASE (n = 94) and Cochrane library (n = 951), in which 58 full-text articles were identified for review. 


After exclusion, 6 studies were selected for analysis. Most studies were conducted in a single study center, with 1 study utilizing data from 2 centers, and 1 study from 6 centers. Study characteristics included were the number of participants, age, gender, and NLP information, such as task assigned, ground truth (gold standard), and the type of NLP algorithms used. 


Five of the 6 studies used support vector machines and 1 study used NLP strategies, such as random forest models and gradient boosted machines. Furthermore, all studies showed moderate-to-to-high levels of performance. 


Some of the studies showed that NLP could identify patients 1 to 2 years prior to the treating clinicians initial referral. However, none of the studies identified evaluated the influence of implementing these algorithms on health care systems or patient outcomes. 

“NLP is a promising technology for the identification of patients who may benefit from epilepsy surgery referral,” wrote the researchers. 

A Novel Wearable Device for Automated Real-time Detection of Epileptic Seizures

 Abstract found on PubMed


Background: Epilepsy is a neurological disorder that has a variety of origins. It is caused by hyperexcitability and an imbalance between excitation and inhibition, which results in seizures. The World Health Organization (WHO) and its partners have classified epilepsy as a major public health concern. Over 50 million individuals globally are affected by epilepsy which shows that the patient’s family, social, educational, and vocational activities are severely limited if seizures are not controlled. Patients who suffer from epileptic seizures have emotional, behavioral, and neurological issues. Alerting systems using a wearable sensor are commonly used to detect epileptic seizures. However, most of the devices have no multimodal systems that increase sensitivity and lower the false discovery rate for screening and intervention of epileptic seizures. Therefore, the objective of this project was, to design and develop an efficient, economical, and automatically detecting epileptic seizure device in real-time.

Methods: Our design incorporates different sensors to assess the patient’s condition such as an accelerometer, pulsoxymeter and vibration sensor which process body movement, heart rate variability, oxygen denaturation, and jerky movement respectively. The algorithm for real-time detection of epileptic seizures is based on the following: acceleration increases to a higher value of 23.4 m/s2 or decreases to a lower value of 10 m/s2 as energy is absorbed by the body, the heart rate increases by 10 bpm from the normal heart rate, oxygen denaturation is below 90% and vibration should be out of the range of 3 Hz -17 Hz. Then, a pulsoxymeter device was used as a gold standard to compare the heart rate variability and oxygen saturation sensor readings. The accuracy of the accelerometer and vibration sensor was also tested by a fast-moving and vibrating normal person’s hand.

Results: The prototype was built and subjected to different tests and iterations. The proposed device was tested for accuracy, cost-effectiveness and ease of use. An acceptable accuracy was achieved for the accelerometer, pulsoxymeter, and vibration sensor measurements, and the prototype was built only with a component cost of less than 40 USD excluding design, manufacturing, and other costs. The design is tested to see if it fits the design criteria; the results of the tests reveal that a large portion of the scientific procedures utilized in this study to identify epileptic seizures is effective.

Conclusion: This project is objectively targeted to design a medical device with multimodal systems that enable us to accurately detect epileptic seizures by detecting symptoms commonly associated with an episode of epileptic seizure and notifying a caregiver for immediate assistance. The proposed device has a great impact on reducing epileptic seizer mortality, especially in low-resource settings where both expertise and treatment are scarce.