Joint use of population pharmacokinetics and machine learning for optimizing antiepileptic treatment in pediatric population

Purpose

Unpredictable drug efficacy and safety of combined antiepileptic therapy is a major challenge during pharmacotherapy decisions in everyday clinical practice. The aim of this study was to describe the pharmacokinetics of valproic acid (VA), lamotrigine (LTG), and levetiracetam (LEV) in a pediatric population using nonlinear mixed-effect modeling, while machine learning (ML) algorithms were applied to identify any relationships among the plasma levels of the three medications and patients' characteristics, as well as to develop a predictive model for epileptic seizures.

Methods

The study included 71 pediatric patients of both genders, aged 2-18 years, on combined antiepileptic therapy. Population pharmacokinetic (PopPK) models were developed separately for VA, LTG, and LEV. Based on the estimated pharmacokinetic parameters and the patients' characteristics, three ML approaches were applied (principal component analysis, factor analysis of mixed data, and random forest). PopPK models and ML models were developed, allowing for greater insight into the treatment of children on antiepileptic treatment.

Results

Results from the PopPK model showed that the kinetics of LEV, LTG, and VA were best described by a one compartment model with first-order absorption and elimination kinetics. Reliance on random forest model is a compelling vision that shows high prediction ability for all cases. The main factor that can affect antiepileptic activity is antiepileptic drug levels, followed by body weight, while gender is irrelevant. According to our study, children's age is positively associated with LTG levels, negatively with LEV and without the influence of VA.

Conclusion

The application of PopPK and ML models may be useful to improve epilepsy management in vulnerable pediatric population during the period of growth and development.

Kaleidoscopic Hues of Antiepileptics in Pediatric Population: Comparison of Prevailing Antiepileptics

BACKGROUND AND OBJECTIVES

Currently, we have a shortage of comprehensive information about newer antiepileptic drugs (AEDs) in the pediatric population. This might explain the discrepancies among pediatricians' preferences in this regard. Therefore, it is crucial to study the multifaceted impacts of these drugs on children. The endpoints of our study were non-AED predictors of the requirement of combination therapy for seizure management, seizure-free period >6 months and >12 months, change in Quality of Life in Childhood Epilepsy Questionnaire - 55 (QOLCE-55), and incidence of adverse events.

METHODS

This prospective, observational study was conducted in KIMS, Bhubaneswar, India, from January 2021 to November 2022. Children of 2-12 years of age were treated with monotherapy of either newer antiepileptics, e.g., levetiracetam, topiramate, and oxcarbazepine or older antiepileptics, e.g., valproic acid, phenytoin, phenobarbital, and carbamazepine. Univariate and multivariate analyses were performed for the assessment of predictors. We used R software (version 4.1.1) for data analysis.

RESULTS

One hundred and ninety-eight (91.7%) of 216 enrolled participants completed this study. The mean age of the study population was 5.2 years and 117 (59%) of them were males. The univariate analysis showed that male gender, low birth weight, preterm birth, assisted vaginal delivery and site-specific epilepsy, and maternal history of epilepsy were significant predictors of combination therapy and reduced seizure-free period. There was a non-significant difference regarding the improvement of QOLCE-55 scores. None of the adverse events were serious.

CONCLUSIONS

Perinatal complications and maternal history of epilepsy contribute significantly toward the efficacy of antiepileptics. However, multivariate analysis did not yield statistically significant results.

Isolated ictal apnea in neonatal age: Clinical features and treatment options. A systematic review

BACKGROUND

Among autonomic seizures apnea still represent a challenge for physicians, and it might constitute the only isolated sign of neurological disorder. The aim of this review is to describe ictal apnea (IA) and its treatment options.

METHODS

MeSH and keywords were combined: "neonatal seizures", "ictal neonatal apnea", "apneic seizures". All identified papers were screened for neonatal seizures titles and abstracts; case reports describing patients with IA as an isolated manifestation of neonatal seizures were included.

RESULTS

Eight studies including a total of 13 patients were identified. Among 13 patients, 9 were full-term and 4 were preterm neonates. All patients developed IA within twenty-one days from birth. Etiologies of seizures included: temporal lobe hemorrhage (3 pt), occipital stroke (1 pt), hypoxic-ischemic encephalopathy (HIE) (1 pt), parasagittal injury (1 pt), 18 trisomy (2 pt). Five patients showed no structural CNS alterations. Ten patients had the ictal focus localized in the temporal lobe; the occipital lobe was the second most involved site. Phenobarbital was administered in 76 % of cases with IA (10 pt), and showed efficacy in 74 % of them; 2 required a second anti-epileptic drug (AED) to reach seizure control. Levetiracetam was given to 11 % (2 pt) successfully. Only one was treated with midazolam and one did not require any anticonvulsant.

CONCLUSIONS

Not homogeneous data and paucity of isolated IA currently reported in literature limits agreement about definition, management and treatment of entity, however an ever-growing attention is needed, and EEG/aEEG, despite their possible controversies in the diagnosis, should be performed to investigate unexplained forms of apnea.