Investigating Placebos and Controls Used in Large Language Model–Based Chatbot Intervention Trials: Protocol for a Methodological Review (Preprint)
Preprint
- 29 December 2025
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
BACKGROUND Large language model (LLM)–based chatbots are rapidly being repurposed as patient-facing digital health tools. Their interactive, adaptive, and seemingly empathic behavior can heighten engagement and expectancy—nonspecific factors that complicate causal inference. Yet, comparator strategies in LLM trials are inconsistently defined and often undermatched (eg, minimal education vs highly engaging chatbots), risking biased effect estimates and poor reproducibility. OBJECTIVE The aim of this study was to systematically identify and categorize the control conditions used in interventional studies of LLM-based, patient-facing digital health interventions and to evaluate their methodological appropriateness. Secondary aims are to describe variability by health domain and study design and to explore whether control type/quality relates to the direction of reported effects. METHODS This protocol follows PRISMA-P (Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols) and is registered in PROSPERO. Eligible studies are interventional designs that evaluate LLM-based, patient-facing digital health interventions; any control condition is eligible (including no control, waitlist, treatment-as-usual, attention/education, active comparator, or sham digital control). We will search PubMed, PsycINFO, CENTRAL, CINAHL, and Scopus for records from January 1, 2023, onward. All records will be managed and screened in Rayyan by 2 independent reviewers. Dual, independent data extraction will target study context, intervention details, and control-arm characteristics (typology, rationale, matching to nonspecifics, blinding, reporting). No formal risk-of-bias assessments are planned, as the focus is on meta-research. RESULTS At submission, the protocol is registered in PROSPERO and has received no specific funding. Scoping searches are complete; full screening and extraction have not yet commenced. CONCLUSIONS This review will provide an empirical map of control practices in LLM chatbot trials and guidance for designing better-matched comparators, supporting more valid and interpretable evaluations as LLMs diffuse into patient care. CLINICALTRIAL PROSPERO CRD420251246148; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251246148 INTERNATIONAL REGISTERED REPORT PRR1-10.2196/90507Keywords
All Related Versions
- Published version: JMIR Research Protocols, 15 (1), e90507.
This publication has 22 references indexed in Scilit:
- A scoping review of large language models for generative tasks in mental health carenpj Digital Medicine, 2025
- Large Language Models for Chatbot Health Advice StudiesJAMA Network Open, 2025
- Generative artificial intelligence in primary care: an online survey of UK general practitionersBMJ Health & Care Informatics, 2024
- Injecting Artificial Intelligence into MedicineNEJM AI, 2024
- Selecting and describing control conditions in mobile health randomized controlled trials: a proposed typologynpj Digital Medicine, 2023
- Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media ForumJAMA Internal Medicine, 2023
- Cochrane Handbook for Systematic Reviews of Interventions2019
- PRESS Peer Review of Electronic Search Strategies: 2015 Guideline StatementJournal of Clinical Epidemiology, 2016
- The digital placebo effect: mobile mental health meets clinical psychiatryThe Lancet Psychiatry, 2016
- GRADE: an emerging consensus on rating quality of evidence and strength of recommendationsBMJ, 2008