Prompted Text-Based Vital Sign Recording Versus Unprompted Electronic Medical Record Entries in Patients With Advanced Heart Failure: Observational Study (Preprint)
Bibliographic record
Abstract
Abstract Background Long-term remote patient monitoring of weight, pulse, and blood pressure has been shown to significantly reduce mortality and hospitalization rates among patients with heart failure. Despite its proven effectiveness, maintaining patient engagement in remote monitoring programs remains challenging. Objective This study aimed to evaluate the impact of 2-way text-based communication on prompting patients to record key vital signs and to compare it with unprompted patient reporting through electronic medical records in terms of engagement and clinical outcomes. Methods We analyzed data from patients participating in the University of Michigan Advanced Heart Failure Program who reported daily weight, blood pressure, and pulse using either the MiChart Patient Outreach Texting Application (MPOTA) or patient enrolled flowsheets (PEFs). The study’s primary metric was the consistency of patient-reported vital signs, with secondary descriptive metrics including variations in hospitalization and emergency room visits pre-enrollment and postenrollment in the programs. Results A total of 890 patients were included, with 301 enrolled in the MPOTA group and 589 in the PEF group. The engagement rate for the PEF group had a median of 2.29% (IQR 0%‐23.93%). In contrast, the MPOTA group showed a significantly higher median engagement rate of 66.67% (IQR 30.67%‐88.24%). There were no significant differences in hospitalization or emergency room visit rates across engagement categories (none, low, medium, and high) or between programs. Mean hospitalizations declined by 21% in the MPOTA group (from mean 0.53, SD 0.90 to mean 0.42, SD 0.88; P =.06) and 18% in the PEF group (from mean 0.50, SD 0.86 to mean 0.41, SD 0.80; P =.03) after the initiation of each program. This reduction was small and statistically significant only for the PEF group. Mean emergency room visits did not significantly change in either group. Regression analyses showed no significant association between engagement level and hospitalization or emergency room utilization, although medium engagement was associated with a nonsignificant trend toward fewer events. Despite improved engagement with MPOTA, this did not translate into significant reductions in hospitalizations or emergency room visits. All analyses of clinical outcomes were exploratory and underpowered, and no significant associations were found between engagement level and utilization. Conclusions Although MPOTA was associated with substantially higher patient engagement levels compared to unprompted patient reporting, neither demonstrated significant differences in hospitalization or emergency room visits across engagement levels or between programs. Small reductions in hospitalizations were observed, but these were significant only in PEF, not in MPOTA. Observed changes in utilization were exploratory, small in magnitude, and underpowered to detect clinically meaningful effects. These findings suggest that mobile text-based communication may be a useful tool for improving engagement in remote monitoring programs for patients with advanced heart failure; however, further research is needed to assess its impact on clinical outcomes.
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 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".