Predicting the occurrence of thrombocytopenia from free valproate levels: A prospective study

Development and validation of an automatic machine learning model to predict abnormal increase of transaminase in valproic acid-treated epilepsy

Valproic acid (VPA) is a primary medication for epilepsy, yet its hepatotoxicity consistently raises concerns among individuals. This study aims to establish an automated machine learning (autoML) model for forecasting the risk of abnormal increase of transaminase levels while undergoing VPA therapy for 1995 epilepsy patients. The study employed the two-tailed T test, Chi-square test, and binary logistic regression analysis, selecting six clinical parameters, including age, stature, leukocyte count, Total Bilirubin, oral dosage of VPA, and VPA concentration. These variables were used to build a risk prediction model using "H2O" autoML platform, achieving the best performance (AUC training = 0.855, AUC test = 0.789) in the training and testing data set. The model also exhibited robust accuracy (AUC valid = 0.742) in an external validation set, underscoring its credibility in anticipating VPA-induced transaminase abnormalities. The significance of the six variables was elucidated through importance ranking, partial dependence, and the TreeSHAP algorithm. This novel model offers enhanced versatility and explicability, rendering it suitable for clinicians seeking to refine parameter adjustments and address imbalanced data sets, thereby bolstering classification precision. To summarize, the personalized prediction model for VPA-treated epilepsy, established with an autoML model, displayed commendable predictive capability, furnishing clinicians with valuable insights for fostering pharmacovigilance.

Trends in antiseizure medication prescription patterns among all adults, women, and older adults with epilepsy: A German longitudinal analysis from 2008 to 2020

INTRODUCTION

The prescription patterns of antiseizure medication (ASM) are subject to new scientific evidence and sociodemographic and practical aspects. This study analyzed trends in ASM prescription patterns among all adults with epilepsy, with special consideration for women of childbearing potential (WOCBP) and older adult (≥65 years old) patients.

METHODS

Data from four questionnaire-based cohort studies, conducted in 2008, 2013, 2016, and 2020, were analyzed for ASM prescription frequencies and common mono- and dual therapy regimens. Statistical comparisons were performed with the Chi-square test and one-way analysis of variance.

RESULTS

Overall, the individual prescription patterns among 1,642 adult patients with epilepsy were analyzed. A significant increase in the prescription frequency of third-generation ASMs, from 59.3% to 84.2% (p = 0.004), was accompanied by a decrease in the frequency of first- and second-generation ASMs (5.4% to 2.1% and 34.9% to 12.6%, respectively). This trend was accompanied by a significant decrease in the use of enzyme-inducing ASMs, from 23.9% to 4.6% (p = 0.004). Among frequently prescribed ASMs, prescriptions of carbamazepine (18.6% to 3.1%, p = 0.004) and valproate (15.4% to 8.7%, p = 0.004) decreased, whereas prescriptions of levetiracetam (18.0% up to 32.4%, p = 0.004) increased significantly. The prescription frequency of lamotrigine remained largely constant at approximately 20% (p = 0.859). Among WOCBP, the prescription frequencies of carbamazepine (11.4% to 2.0%, p = 0.004) and valproate (16.1% to 6.1%, p = 0.004) decreased significantly. Levetiracetam monotherapy prescriptions increased significantly (6.6% to 30.4%, p = 0.004) for WOCBP, whereas lamotrigine prescriptions remained consistent (37.7% to 44.9%, p = 0.911). Among older adult patients, a significant decrease in carbamazepine prescriptions (30.1% to 7.8%, p = 0.025) was the only relevant change in ASM regimens between 2008 and 2020. In patients with genetic generalized epilepsies, levetiracetam was frequently used as an off-label monotherapy (25.0% to 35.3%).

CONCLUSION

These results show a clear trend toward the use of newer and less interacting third-generation ASMs, with lamotrigine, levetiracetam, and lacosamide representing the current ASMs of choice, displacing valproate and carbamazepine over the last decade. In WOCBP, prescription patterns shifted to minimize teratogenic effects, whereas, among older adults, the decrease in carbamazepine use may reflect the avoidance of hyponatremia risks and attempts to reduce the interaction potential with other drugs and ASMs. Levetiracetam is frequently used off-label as a monotherapy in patients with genetic generalized epilepsy.