Head first – Review of epilepsy head injury risk and protection

The Application of Deep Learning to Electroencephalograms, Magnetic Resonance Imaging, and Implants for the Detection of Epileptic Seizures: A Narrative Review

Epilepsy is a neurological disorder characterized by recurrent seizures affecting millions worldwide. Medically intractable seizures in epilepsy patients are not only detrimental to the quality of life but also pose a significant threat to their safety. Outcomes of epilepsy therapy can be improved by early detection and intervention during the interictal window period. Electroencephalography is the primary diagnostic tool for epilepsy, but accurate interpretation of seizure activity is challenging and highly time-consuming. Machine learning (ML) and deep learning (DL) algorithms enable us to analyze complex EEG data, which can not only help us diagnose but also locate epileptogenic zones and predict medical and surgical treatment outcomes. DL models such as convolutional neural networks (CNNs), inspired by visual processing, can be used to classify EEG activity. By applying preprocessing techniques, signal quality can be enhanced by denoising and artifact removal. DL can also be incorporated into the analysis of magnetic resonance imaging (MRI) data, which can help in the localization of epileptogenic zones in the brain. Proper detection of these zones can help in good neurosurgical outcomes. Recent advancements in DL have facilitated the implementation of these systems in neural implants and wearable devices, allowing for real-time seizure detection. This has the potential to transform the management of drug-refractory epilepsy. This review explores the application of ML and DL techniques to Electroencephalograms (EEGs), MRI, and wearable devices for epileptic seizure detection. This review briefly explains the fundamentals of both artificial intelligence (AI) and DL, highlighting these systems' potential advantages and undeniable limitations.

Adult-onset epilepsy and risk of traumatic brain injury: a nationwide cohort study

BACKGROUND

A knowledge gap exists regarding the risk of traumatic brain injury (TBI) in patients with epilepsy.

METHODS

Patients with adult-onset epilepsy during 2005-2018 in Finland were studied using retrospective longitudinal national registry-linkage design. Patients with epilepsy (n=35 686; 51% men; mean age 56.6 years) were 1:1 matched to non-epileptic controls by age, sex, comorbidity burden and cohort entry year. The primary outcome was TBI leading to admission or death, secondary outcomes were TBI admission, fatal TBI, acute neurosurgical operations (ANOs) for TBI and TBI recurrence.

RESULTS

The cumulative rate of the primary endpoint was 1.2% at 1 year, 5.6% at 10 years and 7.3% at 14 years in the epilepsy group versus 2.9% at 14 years in the matched controls (HR=3.77; p<0.0001). Epilepsy was associated with increased risk of TBI admission (6.9% vs 2.7%; HR=3.96; p<0.0001), ANOs (1.3% vs 0.4%; HR=7.00; p<0.0001) and fatal TBI (1.3% vs 0.5%; HR=3.82; p<0.0001), during follow-up. Competing risk analyses confirmed the association of epilepsy with all outcomes (p<0.0001). Epilepsy was associated with TBI recurrence during follow-up (HR 1.72; p=0.002).

CONCLUSION

Patients with adult-onset epilepsy have a significantly increased risk of severe and fatal TBI. The results underline the importance of TBI prevention in epilepsy.

Epilepsy in cerebral amyloid angiopathy: an observational retrospective study of a large population

OBJECTIVE

Cerebral amyloid angiopathy (CAA) is a major cause of spontaneous intracranial hemorrhage in older adults. Epilepsy represents a possible sequela of the disease. To date, studies on epilepsy in CAA are lacking, and the few data available mainly focus on CAA-related inflammation (CAA-ri), the inflammatory form of the disease.

METHODS

In this retrospective observational study, we consecutively recruited CAA patients observed over a time span of 10 years, collecting demographic, clinical, and instrumental data. Significant baseline characteristics were evaluated as potential risk factors for the development of epilepsy in the CAA population, and in the subgroups of CAA-ri and CAA without inflammatory reaction (CAA-nri). The effect of potential risk factors for epilepsy was measured as odds ratio with 95% confidence interval.

RESULTS

Within 96 recruited CAA cases, 33 (34.4%) developed epilepsy during follow-up (median = 13.5 months). The prevalent type of seizure was focal (81.3%); 12.1% of the epileptic patients presented status epilepticus, and 6.1% developed drug-resistant epilepsy. Electroencephalographic traces revealed slow and epileptic discharge activity in the majority of epileptic patients, but also in those without epilepsy. The presence of focal or disseminated cortical superficial siderosis (cSS) was associated with an increased risk of epilepsy in the CAA-nri group, and the association with CAA-ri and epilepsy was present in the overall population.

SIGNIFICANCE

Epilepsy is a common manifestation during the course of CAA, where CAA-ri and cSS represent predisposing factors for the development of seizures. These data suggest the importance of a deep characterization of CAA patients, to better select those more prone to develop epilepsy.

Methylphenidate and TBI in ADHD and co-occurring epilepsy and mental disorders: a self-controlled case series study

It is suggested that medication for attention-deficit hyperactivity disorder (ADHD) links to lower risk of traumatic brain injury (TBI). Little is known about whether the beneficial effect of methylphenidate is persistent in individuals with other comorbid mental disorders and epilepsy. We identified 90,634 participants who were less than 18 years old and diagnosed with ADHD from Taiwan's National Health Insurance Research Database (NHIRD) from January 1, 2000 to December 31, 2013. Cox proportional hazards models with hazard ratio (HR) and 95% confidence interval were conducted to compare the risks of TBI event between groups of ADHD-only and ADHD with co-occurring other mental disorders. Within-individual comparisons using a self-controlled case series study design were conducted using conditional Poisson regression models with relative incidence (RR) and 95% CI to examine the effect of methylphenidate on TBI with adjustment for medication of psychotropics and anticonvulsants. For children and adolescents with ADHD, we found comorbid mental disorders and epilepsy increase the risk of TBI, with HRs ranged from 1.21 to 1.75. For the effect of MPH, we found reduced risks for TBI in ADHD (RR = 0.83, 95% CI = 0.70-0.98). Similar results were found among individuals with co-occurring oppositional defiant disorders or conduct disorder, MDD, tic disorders and epilepsy. Methylphenidate treatment was linked to lower risk for TBI in patients with ADHD and the inverse association was persistent among those with other comorbid mental disorders and epilepsy.

A reappraisal of injuries and accidents in people with epilepsy

PURPOSE OF REVIEW

We review data on injuries and traffic accidents affecting people with epilepsy with emphasis on the overall risk of injuries, specific types of injuries, and risk factors.

RECENT FINDINGS

Population-based studies of incident epilepsy cohorts indicate that the risk of physical injuries in people with epilepsy in general is increased only modestly. The risk is higher in selected populations that attend epilepsy clinics or referral centers. Soft tissue injuries, dislocations, and fractures are the most common injures, whereas the greatest increase in risk is reported for more uncommon injuries such as drowning. People with epilepsy are at a two-fold to four-fold increased risk for fatal injuries. Comorbidities contribute to fatal as well as nonfatal injuries. The other major risk factor is poorly controlled major convulsive seizures (generalized as well as focal to bilateral tonic-clonic seizures). Serious transport accidents associated with increased risks for people with epilepsy include pedestrian, bicycle, as well as car accidents.

SUMMARY

Individualized information on the risk of physical injuries and accidents should be part of counseling of patients with epilepsy. Improved seizure control is likely the most effective way to reduce risks, but work place and home adjustments should also be considered.