Evaluating the role of visit audio recordings in triadic dementia care: study protocol
Bibliographic record
Abstract
BACKGROUND: Effective interpersonal communication is associated with improved health-related outcomes, yet it is unclear to what extent this occurs in triadic clinic visits for persons living with dementia (PLWD) and few tools exist to characterize triadic interpersonal communication and assess its effectiveness. The objective of this project is to characterize the interpersonal communication that occurs during triadic visits for PLWD, examine how interpersonal communication is related to health outcomes and use this understanding to adapt an innovative clinic visit audio recording intervention, HealthPAL (Personal Audio Library) for use in this setting. METHODS: Following the NIH Stage Model, we will redesign a visit recording platform, HealthPAL, which leverages natural language processing to structure visit information. In Aim 1, we will use an explanatory sequential mixed methods design. Informed by the Behavior Change Wheel, targets for behavior change will be identified using quantitative assessment of interpersonal communication during triadic visits (200 dyads, 3 visits annually; ∼600 visits), supplemented by semi-structured interviews with a purposive sample of triads (n = 42); In Aim 2, we will use participatory design methods (n = 60) to redesign HealthPAL using findings from Aim 1; and in Aim 3, we will use an open label, single-arm, multi-site pilot trial (n = 30) to determine usability, feasibility and acceptability of HealthPAL and gather preliminary data on its impact on interpersonal communication in triadic AD/ADRD visits. We hypothesize: (1) Constructs from models of interpersonal communication will be associated with health-related outcomes; (2) HealthPAL will surpass usability, feasibility, and acceptability metrics for dyads and clinicians. DISCUSSION: This work is a necessary first step to improving PLWD triadic care by identifying behaviors that impact triadic interpersonal communication and their associations with health-related outcomes. The novel intervention that we will develop--the use of visit recordings--and the diverse and extensive data we will collect will serve as a unique resource that can be leveraged to address other gaps in clinical knowledge related to the care of PLWD.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".