Large Language Model-Based Simplification of Digital Therapeutics Explanations for Insomnia and Nicotine Dependence: Two Randomized Online Experiments.

What Was Tested

This randomized controlled trial looks at Therapeutic nicotine (patch, non-peptide).

This study aimed to examine whether LLM-based simplification of DTx explanatory materials enhances perceived understanding and subjective evaluations of readability, clarity, and comprehensibility compared with manufacturer-provided documents.

Why It Was Studied

Digital therapeutics (DTx) are evidence-based software interventions with the potential to treat health conditions.

However, uptake remains limited by low public awareness and overly complex patient education materials that exceed recommended readability levels.

Who Took Part

The abstract describes 1000, participants taking part.

By PubMed's age tags, the people studied were adults and middle-aged adults, both men and women.

Two randomized, between-subject online experiments were conducted (n=1000, with 500 participants in each experiment).

Within each experiment, participants were randomly assigned to review either the original or the LLM-simplified explanatory material.

How the Study Was Run

The design is described as randomized.

Because people in this Therapeutic nicotine (patch, non-peptide) study were split into groups at random, differences between the groups are less likely to reflect who happened to join each one.

The researchers developed a simplification tool using the GPT-4o application programming interface (API), configured for deterministic outputs and guided by structured readability instructions.

Original DTx explanatory materials about insomnia and nicotine dependence were obtained from manufacturers and transformed into simplified versions.

Perceived understanding was assessed before and after exposure.

Postexposure evaluations of ease, clarity, and comprehensibility were also collected.

What Was Measured

However, uptake remains limited by low public awareness and overly complex patient education materials that exceed recommended readability levels.

PubMed files the paper under topics including Large Language Models, Tobacco Use Disorder, Sleep Initiation and Maintenance Disorders, Patient Education as Topic, Comprehension and Digital Media.

Author keywords: digital therapeutics, patient education materials, randomized online experiment and text simplification.

What This Means in Plain Language

The paper is a randomized study of Therapeutic nicotine (patch, non-peptide) in 1000, participants.

With several hundred people or more, it is a fairly large study for this kind of research.

Results are reported in around 5 sentences of the abstract; we leave them to the paper itself rather than summarise them.

The publication is from 2026 (JMIR human factors), a journal based in Canada.

More context: the Therapeutic nicotine (patch, non-peptide) compound page, all human trials.