Related Experiment Video
Updated: Mar 19, 2026
08:50
How to Study Placebo Responses in Motion Sickness with a Rotation Chair Paradigm in Healthy Participants
Published on: December 14, 2014
9.7K
Investigating Placebos and Controls Used in Large Language Model-Based Chatbot Intervention Trials: Protocol for a
Leo Druart1,2, Vanda Faria1,3,4, Marco Annoni5
1Participatory eHealth and Health Data Research Group, Department of Women's and Children's Health, Uppsala University, Uppsala, Uppsala, Sweden.
JMIR Research Protocols
|March 17, 2026
Summary
This systematic review will map control strategies in large language model (LLM) chatbot trials for digital health. It aims to improve comparator selection for more accurate and reproducible patient-facing LLM intervention studies.
Area of Science:
- Digital Health
- Artificial Intelligence
- Clinical Trials
Background:
- Large language model (LLM)-based chatbots are increasingly used as patient-facing digital health tools.
- Their engaging nature complicates causal inference due to expectancy-nonspecific factors.
- Inconsistent and undermatched comparator strategies in LLM trials risk biased results and poor reproducibility.
Purpose of the Study:
- To systematically identify and categorize control conditions in LLM-based patient-facing digital health intervention studies.
- To evaluate the methodological appropriateness of these control conditions.
- To explore variations by health domain and study design, and the relationship between control type/quality and reported effects.
Main Methods:
- Protocol follows PRISMA-P guidelines and is registered with PROSPERO.
- Eligible studies include interventional designs of LLM-based patient-facing digital health interventions with any control type.
- Searches will be conducted across major databases (PubMed, PsycINFO, CENTRAL, CINAHL, Scopus) from January 1, 2023, with dual independent screening and data extraction.
Main Results:
- Scoping searches are complete; full screening and data extraction are pending.
- The protocol is registered in PROSPERO (CRD420251246148).
- No specific funding has been received at the time of submission.
Conclusions:
- This review will empirically map control practices in LLM chatbot trials.
- It will provide guidance for designing better-matched comparators.
- This supports more valid and interpretable evaluations as LLMs are adopted in patient care.
More Related Videos
Related Concept Videos
02:07Blind Procedures
13.8K
Ideally, the people who observe and record the children’s behavior are unaware of who was assigned to the experimental or control group, in order to control for experimenter bias. Experimenter bias refers to the possibility that a researcher’s expectations might skew the results of the study. Remember, conducting an experiment requires a lot of planning, and the people involved in the research project have a vested interest in supporting their hypotheses. If the observers knew which...
13.8K
01:11Blinding
4.0K
Blinding is a commonly used method of not telling participants which treatment a subject is receiving. Blinding is a critical part of a randomized control trial or RCT. It reduces the bias that affects the results. In an RCT, blinding is used in the form of a placebo. A placebo effect occurs when untreated subjects falsely believe they have received the treatment and report improved symptoms. A placebo or a dummy treatment is administered to subjects to negate the bias caused by such an effect.
4.0K
01:54The Placebo Effect
7.0K
The placebo effect occurs when people's expectations or beliefs influence or determine their experience in a given situation. In other words, simply expecting something to happen can actually make it happen.
7.0K
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
520
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
520
01:13Controls in Experiments
18.7K
When conducting an experiment, it is crucial to have control to reduce bias and accurately measure the dependent variables. It also marks the results more reliable. Controls are elements in an experiment that have the same characteristics as the treatment groups but are not affected by the independent variable. By sorting these data into control and experimental conditions, the relationship between the dependent and independent variables can be drawn. A randomized experiment always includes a...
18.7K
01:15Bioequivalence Experimental Study Designs: Repeated Measures, Cross-Over, Carry-Over, and Latin Square Designs
367
Bioequivalence experimental study designs play a pivotal role in testing the effectiveness of various treatments. Key among these are the repeated measures, cross-over, carry-over, and Latin square designs. In the repeated measures design, each subject receives all treatments, allowing for temporal comparisons. This type of design is useful in reducing variability but requires careful planning to avoid bias.The cross-over design, an economical method, involves sequential administration of...
367