Implementation and Evaluation of a Virtual Transitional Care Intervention Using Automated Text Messaging and Virtual Visits After Emergency Department Discharges: Retrospective Cohort Study
Bibliographic record
Abstract
BACKGROUND: Emergency Department (ED) overcrowding and avoidable revisits represent significant challenges for healthcare systems, with approximately 20% of patients returning to the ED within 30 days of discharge. To reduce avoidable acute care use, many health systems have adopted ED-based transitional care interventions (TCIs). Among the most scalable and cost-effective strategies is automated text messaging outreach, which facilitates timely follow-up and reinforces discharge instructions. Despite its promise, evidence supporting this approach remains limited. OBJECTIVE: (1) Describe the design, implementation, and outcomes of a novel TCI utilizing SMS text messaging and virtual transitional care visits, and (2) assess its effect on unplanned ED revisits for the same presenting complaint as well as subsequent ambulatory follow-up engagement. METHODS: This retrospective observational cohort study included patients discharged from four EDs within a single U.S. health system between September 2023 and September 2024. Patients were categorized into two groups based on their engagement with the intervention: (1) the Completed Virtual Transitional Care Visit group (requested, scheduled, and completed a visit) and the (2) Noncompleted Virtual Transitional Care Visit group (requested, scheduled, but did not complete a visit). The primary outcome was spontaneous, unplanned ED revisits within 90 days. Secondary outcomes included outpatient follow-up and time to first outpatient evaluation. Between group differences were assessed using descriptive statistics and multivariable regression models (P < 0.05). RESULTS: Of the 68,115 discharged patients during the study period, 42.7% (29,100) received an automated text for the virtual transitional care program, and 2.9% (853/29,100) accessed the scheduling link. Of these, 56.5% (482/853) requested a virtual transitional care visit, 49.8% (240/482) scheduled an appointment, and 70.0% (168/240) completed the visit (Completed group). Among the 72 Noncompleted patients, 56.9% no-showed, 31.9% canceled, and 11.1% scheduled two appointments but completed neither. Nearly half (48.6%) of the Noncompleted group had an outpatient follow-up, indicating variable engagement. Demographics, comorbidities, and clinical acuity were similar between groups. The Noncompleted group was nearly twice as likely to return to the ED within 90 days (27.8% vs 15.5%; χ²₁=4.20, P=0.04; OR=2.11, 95% CI 1.02-4.33) while the Completed group was more likely to complete outpatient follow-up (48.6% vs 30.0%; χ²₁=6.60, P=0.01; OR=2.17, 95% CI 1.23-3.83). Time to first outpatient visit did not differ significantly between groups (mean = 15.7 days vs. 19.8 days; Δβ = -1.93; 95% CI: -10.09 to 6.42; P = 0.65). CONCLUSIONS: A TCI combining automated text messaging with virtual visits was associated with reduced 90-day spontaneous ED revisits and increased outpatient follow-up. While the intervention demonstrated significant clinical benefits among engaged patients, the low initial engagement rate (2.9%) highlights substantial challenges in achieving population-level impact. Future efforts should focus on optimizing care delivery for engaged patients while developing strategies to expand program reach across the broader ED discharge population.
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 | 0.007 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".