1260 Can clinicians be trained to use the serious illness conversation guide using digital avatars?
Bibliographic record
Abstract
Aim To evaluate the effectiveness of a novel digital serious illness conversation (SIC) guide training vs. instructor-led training in improving clinician attitudes and communication behaviors in a pilot randomized controlled trial. Background SICs improve patient care, but training clinicians remains resource-intensive and, by itself, does not lead to widespread practice change. Health systems face significant barriers to sustaining traditional instructor-led training models. To improve scalability and access for less-resourced organizations, we developed a 90-minute asynchronous, avatar-based digital guide training (DGT) as an alternative to our well-studied 3.5 hour synchronous instructor-led training (ILT). Methods We are conducting a pilot randomized controlled trial comparing the effectiveness of DGT to ILT using the Serious Illness Conversation Guide. Clinicians complete post-training surveys assessing attitudes, confidence, and self-efficacy. A total of 48 clinicians across two sites will be randomized (12 in DGT, 12 in ILT, at each site). SIC documentation data will be collected three months before and after training completion. Results To date, 23 participants have completed the study (12 in DGT, 11 in ILT). There are no significant differences between groups in demographics (profession, specialty, experience, gender, race). All participants (100%) of both training types agreed or strongly agreed that the teaching methods were effective. Confidence scores significantly increased in both groups (p<0.01). DGT participants showed a 15.6-point increase (SD 15.2; 65.5 before, 81.1 after), while ILT participants increased by 18.2 points (SD 8.5; 55.6 before, 73.8 after). Additional survey data for 25 participants and conversation outcome data for all 48 participants are pending at time of abstract submission. Discussion Preliminary results show both training methods improve clinician attitudes, confidence, self-efficacy following both training modalities. The small size of the current sample limits the power to detect significant differences, however data collection and analysis will be completed by the time of the proposed presentation. Unique Contribution Ariadne Labs’ avatar-based guide training is the first asynchronous, low-cost training for SICs. Evaluating its effectiveness compared to the instructor-led model is important to ensuring that the quality of training is retained in this more affordable, scalable approach. Implications A digital training model can expand access to SIC training for more clinicians. By reducing the time and resources spent on training coordination, health systems can shift efforts toward implementation strategies that drive real practice change.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.021 | 0.002 |
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".