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. Trial registration: PROSPERO CRD420251246148; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251246148. International registered report identifier (irrid): PRR1-10.2196/90507.
Investigating Placebos and Controls Used in Large Language Model–Based Chatbot Intervention Trials: Protocol for a Methodological Review
Marco Annoni;
2026
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. Trial registration: PROSPERO CRD420251246148; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251246148. International registered report identifier (irrid): PRR1-10.2196/90507.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
