The Influence of Baseline Hemoglobin A1c on Digital Health Coaching Outcomes in Adults With Type 2 Diabetes: Real-World Retrospective Cohort Study
Bibliographic record
Abstract
Background Digital health coaching is an increasingly common diabetes self-management support strategy for individuals with type 2 diabetes and has been linked to positive mental and physical health outcomes. However, the relationship between baseline risk and outcomes is yet to be evaluated in a real-world setting. Objective The purpose of this real-world study was to evaluate trends in digital health coaching outcomes by baseline hemoglobin A1c (HbA1c) to better understand which populations may experience the greatest clinical and psychosocial benefit. Methods A retrospective cohort study design was used to evaluate program effect in a convenience sample of participants in a 12-week digital health coaching program administered by Pack Health. Participants were referred through their health care provider, payer, or employer. The program included patient-centered lifestyle counseling and psychosocial support delivered via telephone, text, and/or email. Self-reported HbA1c and weight were collected at baseline and completion. Physical and mental health were assessed using the Patient-Reported Outcomes Measurement Information System (PROMIS) Global Health Short Form and the Diabetes Distress Scale-2. Changes in HbA1c, weight, BMI, and physical and mental health were analyzed within three participant cohorts stratified by baseline HbA1c level. Results Participants with complete HbA1c data sets (n=226) were included in the analysis. The sample population was 71.7% (162/226) female, with 61.5% (139/226) identifying as white and 34.1% (77/226) as black. Most participants (184/226, 81.4%) reported a baseline HbA1c ≥7%, and 20.3% (46/226) were classified as high risk (HbA1c >9%). Across HbA1c cohorts, the mean baseline BMI was 35.83 (SD 7.79), and the moderate-risk cohort (7% ≤ HbA1c ≤ 9%) reported the highest mean value (36.6, SD 7.79). At 12 weeks, patients reported a significant decrease in HbAlc, and high-risk participants reduced their levels by the greatest margin (2.28 points; P<.001). Across cohorts, BMI improved by 0.82 (P<.001), with the moderate-risk cohort showing the greatest reduction (−0.88; P<.001). Overall, participants reported significant improvements for PROMIS scores, with the greatest change occurring in the high-risk cohort for whom physical health improved 3.84 points (P<.001) and mental health improved 3.3 points (P<.001). However, the lowest-risk cohort showed the greatest improvements in diabetes distress (−0.76; P=.005). Conclusions Acknowledging the limitations in this real-world study design, the results reported here suggest that adults with type 2 diabetes with a high baseline HbA1c or high BMI may benefit the most from patient-centered digital health coaching programs when compared to their lower risk counterparts. While all participants improved in physical and mental health categories, participants with high HbA1c experienced the greatest HbA1c reduction and individuals with the highest baseline BMI lost the most weight. These results may be used to inform referrals for patients who are more likely to benefit from digital health coaching.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".