Impact of virtual triage and care referral on patient care seeking intent and clinical acuity alignment in an Australian health plan: A cross-sectional study
Bibliographic record
Abstract
Objective: Evaluate if artificial intelligence (AI)-based virtual triage and care referral (VTCR) improved care acuity alignment and has the potential to reduce unwarranted, avoidable care costs when integrated into the patient engagement capabilities of an Australian private health insurance company. Methods: A cross-sectional study compared patient pre- and post-VTCR care intent across 4,471 encounters to evaluate the degree of clinical care acuity re-alignment (or divergence) which occurred and potential associated cost savings. Results: Overall compliance or alignment with triage recommendations was high (74.0%), and VTCR was effective in educating patients about the most appropriate care to meet their actual clinical needs. One-half of patients (50.5%) changed their care intent. Following VTCR there was a 91.3% reduction of patients with uncertain care intent (39.8 percentage points [PP]); a 56.5% (6.2 PP) increase in intent to engage self-care, and a 35.7% (0.5 PP) decrease in emergency care intent (all p < .05). This yielded a potential $4.27 (8.6%) overall net savings per completed VTCR encounter, with potential savings of $284.55 (72.2%) per completed encounter among patients initially intending to seek emergency care, and 35 unnecessary outpatient visits potentially avoided per 1,000 encounters producing potential savings of $3.39 (6.5%) per completed encounter among patients initially intending to seek outpatient care. Almost 10% of patients intended to book a clinically appropriate telemedicine consultation following VTCR. Conclusions: VTCR was found to be potentially clinically and cost-effective in re-directing patients who had an initial care intent not supported by their actual clinical acuity, reducing patient care uncertainty and potentially avoidable care utilization. Future research should include clinical validation of patient diagnosis and care services delivered as a primary outcome in order to confirm the potential savings identified in this study.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".