Interactive Conversational Agents for Health Promotion, Prevention, and Care: Protocol for a Mixed Methods Systematic Scoping Review
Bibliographic record
Abstract
BACKGROUND: Interactive conversational agents, also known as "chatbots," are computer programs that use natural language processing to engage in conversations with humans to provide or collect information. Although the literature on the development and use of chatbots for health interventions is growing, important knowledge gaps remain, such as identifying design aspects relevant to health care and functions to offer transparency in decision-making automation. OBJECTIVE: This paper presents the protocol for a scoping review that aims to identify and categorize the interactive conversational agents currently used in health care. METHODS: A mixed methods systematic scoping review will be conducted according to the Arksey and O'Malley framework and the guidance of Peters et al for systematic scoping reviews. A specific search strategy will be formulated for 5 of the most relevant databases to identify studies published in the last 20 years. Two reviewers will independently apply the inclusion criteria using the full texts and extract data. We will use structured narrative summaries of main themes to present a portrait of the current scope of available interactive conversational agents targeting health promotion, prevention, and care. We will also summarize the differences and similarities between these conversational agents. RESULTS: The search strategy and screening steps were completed in March 2022. Data extraction and analysis started in May 2022, and the results are expected to be published in October 2022. CONCLUSIONS: This fundamental knowledge will be useful for the development of interactive conversational agents adapted to specific groups in vulnerable situations in health care and community settings. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/40265.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.153 | 0.172 |
| Meta-epidemiology (narrow) | 0.006 | 0.006 |
| Meta-epidemiology (broad) | 0.013 | 0.016 |
| Bibliometrics | 0.018 | 0.017 |
| Science and technology studies | 0.005 | 0.006 |
| Scholarly communication | 0.009 | 0.009 |
| Open science | 0.006 | 0.008 |
| Research integrity | 0.011 | 0.008 |
| Insufficient payload (model declined to judge) | 0.060 | 0.014 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".