Quantifying and controlling the impact of regression to the mean on randomized controlled trials in epilepsy

Placebo response in patients with Dravet syndrome: Post-hoc analysis of two clinical trials

OBJECTIVE

Dravet syndrome is a rare, early childhood-onset epileptic and developmental encephalopathy. Responses to placebo in clinical trials for epilepsy therapies range widely, but factors influencing placebo response remain poorly understood. This study explored placebo response and its effects on safety, efficacy, and quality of life outcomes in patients with Dravet syndrome.

METHODS

We performed exploratory post-hoc analyses of pooled data from placebo-treated patients from the GWPCARE 1B and GWPCARE 2 randomized controlled phase III trials, comparing cannabidiol and matched placebo in 2-18 year old Dravet syndrome patients. All patients had ≥4 convulsive seizures during a baseline period of 4 weeks.

RESULTS

124 Dravet syndrome-treated patients were included in the analysis (2-5 years: n = 35; 6-12 years: n = 52; 13-18 years: n = 37). Convulsive seizures were experienced by all placebo group patients at all timepoints, with decreased median convulsive seizure frequency during the treatment period versus baseline; the number of convulsive seizure-free days was similar to baseline. Convulsive seizure frequency had a nominally significant positive correlation with age and a nominally significant negative correlation with body mass index. Most placebo-treated patients experienced a treatment-emergent adverse event; however, most resolved quickly, and serious adverse events were infrequent. Placebo treatment had very little effect on reported Caregiver Global Impression of Change outcomes versus baseline.

INTERPRETATION

Placebo had little impact on convulsive seizure-free days and Caregiver Global Impression of Change versus baseline, suggesting that these metrics may help differentiate placebo and active treatment effects in future studies. However, future research should further assess placebo responses to confirm these results.

Challenges and directions in epilepsy diagnostics and therapeutics: Proceedings of the 17th Epilepsy Therapies and Diagnostics Development conference

Substantial efforts are underway toward optimizing the diagnosis, monitoring, and treatment of seizures and epilepsy. We describe preclinical programs in place for screening investigational therapeutic candidates in animal models, with particular attention to identifying and eliminating drugs that might paradoxically aggravate seizure burden. After preclinical development, we discuss challenges and solutions in the design and regulatory logistics of clinical trial execution, and efforts to develop disease biomarkers and interventions that may be not only seizure-suppressing, but also disease-modifying. As disease-modifying treatments are designed, there is clear recognition that, although seizures represent one critical therapeutic target, targeting nonseizure outcomes like cognitive development or functional outcomes requires changes to traditional designs. This reflects our increasing understanding that epilepsy is a disease with profound impact on quality of life for the patient and caregivers due to both seizures themselves and other nonseizure factors. This review examines selected key challenges and future directions in epilepsy diagnostics and therapeutics, from drug discovery to translational application.

Inductive reasoning with large language models: a simulated randomized controlled trial for epilepsy

Importance

The analysis of electronic medical records at scale to learn from clinical experience is currently very challenging. The integration of artificial intelligence (AI), specifically foundational large language models (LLMs), into an analysis pipeline may overcome some of the current limitations of modest input sizes, inaccuracies, biases, and incomplete knowledge bases.

Objective

To explore the effectiveness of using an LLM for generating realistic clinical data and other LLMs for summarizing and synthesizing information in a model system, simulating a randomized clinical trial (RCT) in epilepsy to demonstrate the potential of inductive reasoning via medical chart review.

Design

An LLM-generated simulated RCT based on a RCT for treatment with an antiseizure medication, cenobamate, including a placebo arm and a full-strength drug arm, evaluated by an LLM-based pipeline versus a human reader.

Setting

Simulation based on realistic seizure diaries, treatment effects, reported symptoms and clinical notes generated by LLMs with multiple different neurologist writing styles.

Participants

Simulated cohort of 240 patients, divided 1:1 into placebo and drug arms.

Intervention

Utilization of LLMs for the generation of clinical notes and for the synthesis of data from these notes, aiming to evaluate the efficacy and safety of cenobamate in seizure control either with a human evaluator or AI-pipeline.

Measures

The AI and human analysis focused on identifying the number of seizures, symptom reports, and treatment efficacy, with statistical analysis comparing the 50%-responder rate and median percentage change between the placebo and drug arms, as well as side effect rates in each arm.

Results

AI closely mirrored human analysis, demonstrating the drug's efficacy with marginal differences (<3%) in identifying both drug efficacy and reported symptoms.

Conclusions and Relevance

This study showcases the potential of LLMs accurately simulate and analyze clinical trials. Significantly, it highlights the ability of LLMs to reconstruct essential trial elements, identify treatment effects, and recognize reported symptoms, within a realistic clinical framework. The findings underscore the relevance of LLMs in future clinical research, offering a scalable, efficient alternative to traditional data mining methods without the need for specialized medical language training.