The latest medical research on Neuro Intensive Care

The aim of this study was to develop a machine learning algorithm using an off-the-shelf digital watch, the Samsung watch (SM-R800), and evaluate its effectiveness for the detection of generalized convulsive seizures (GCS) in persons with epilepsy.

This multisite epilepsy monitoring unit (EMU) phase 2 study included 36 adult patients. Each patient wore a Samsung watch that contained accelerometer, gyroscope, and photoplethysmographic sensors. Sixty-eight time and frequency domain features were extracted from the sensor data and were used to train a random forest algorithm. A testing framework was developed that would better reflect the EMU setting, consisting of (1) leave-one-patient-out cross-validation (LOPO CV) on GCS patients, (2) false alarm rate (FAR) testing on nonseizure patients, and (3) "fixed-and-frozen" prospective testing on a prospective patient cohort. Balanced accuracy, precision, sensitivity, and FAR were used to quantify the performance of the algorithm. Seizure onsets and offsets were determined by using video-electroencephalographic (EEG) monitoring. Feature importance was calculated as the mean decrease in Gini impurity during the LOPO CV testing.

LOPO CV results showed balanced accuracy of .93 (95% confidence interval [CI] = .8-.98), precision of .68 (95% CI = .46-.85), sensitivity of .87 (95% CI = .62-.96), and FAR of .21/24 h (interquartile range [IQR] = 0-.90). Testing the algorithm on patients without seizure resulted in an FAR of .28/24 h (IQR = 0-.61). During the "fixed-and-frozen" prospective testing, two patients had three GCS, which were detected by the algorithm, while generating an FAR of .25/24 h (IQR = 0-.89). Feature importance showed that heart rate-based features outperformed accelerometer/gyroscope-based features.

Commercially available wearable digital watches that reliably detect GCS, with minimum false alarm rates, may overcome usage adoption and other limitations of custom-built devices. Contingent on the outcomes of a prospective phase 3 study, such devices have the potential to provide non-EEG-based seizure surveillance and forecasting in the clinical setting.

To investigate the underlying reasons for variability in the incidence rate of amyotrophic lateral sclerosis (ALS) within the Irish population between the years 1996 and 2021.

The Irish ALS register was used to calculate the incidence and to subsequently extract age at diagnosis (age), year of diagnosis (period), and date of birth (cohort) for all incident patients within the study period (n = 2,771). An age-period-cohort (APC) model using partial least squares regression was constructed to examine each component separately and their respective contribution to the incidence while minimizing the well-known identifiability problem of APC effects. A dummy regression model consisting of 5 periods, 19 cohorts, and 16 age groups was used to examine nonlinear relationships within the data over time. The CIs for each of these were estimated using the jackknife method.

The nonlinear model achieved R2 of 99.43% with 2-component extraction. Age variation was evident with those in the ages 65-79 years contributing significantly to the incidence (βmax = 0.0746, SE = 0.000410, CI 0.00665-0.00826). However, those aged 25-60 years contributed significantly less (βmin = -0.00393, SE = 0.000291, CI -0.00454 to -0.00340). Each successive period showed an increase in the regression model coefficient suggesting an increasing incidence over time, independent of the other factors examined-an increase of β from -0.00489 (SE = 0.000264, CI -0.00541 to -0.00437) to 0.00973 (SE = 0.000418, CI 0.0105-0.00891). A cohort effect was demonstrated showing that the contribution of those born between 1927 and 1951 contributed to a significantly greater degree than the other birth cohorts (βmax = 0.00577, SE = 0.000432, CI 0.00493-0.00662).

Using the Irish population-based ALS Register, robust age, period, and cohort effects can be identified. The age effect may be accounted for by demographic shifts within the population. Changes in disease categorization, competing risks of death, and improved surveillance may account for period effects. The cohort effect may reflect lifestyle and environmental factors associated with the challenging economic circumstances in Ireland between 1927 and 1951. Age-period-cohort studies can help to account for changes in disease incidence and prevalence, providing additional insights into likely demographic and environmental factors that influence population-based disease risk.