Novel Implementation Strategy to Electronically Screen and Signpost Patients to Health Behavior Apps: Mixed Methods Implementation Study (OptiMine Study)
Bibliographic record
Abstract
BACKGROUND: Behavior change apps have the potential to provide individual support on a population scale at low cost, but they face numerous barriers to implementation. Electronic health records (EHRs) in acute care hospitals provide a valuable resource for identifying patients at risk, who may benefit from behavior change apps. A novel, emerging implementation strategy is to use digital technologies not only for providing support to help-seeking individuals but also for signposting patients at risk to support services (also called proactive referral in the United States). OBJECTIVE: The OptiMine study aimed to increase the reach of behavior change apps by implementing electronic signposting for smoking cessation and alcohol reduction in a large, at-risk population that was identified through an acute care hospital EHR. METHODS: This 3-phase, mixed methods implementation study assessed the acceptability, feasibility, and reach of electronic signposting to behavior change apps by using a hospital's EHR system to identify patients who are at risk. Phase 1 explored the acceptability of the implementation strategy among the patients and staff through focus groups. Phase 2 investigated the feasibility of using the hospital EHR to identify patients with target risk behaviors and contact them via SMS text message, email, or patient portal. Phase 3 assessed the impact of SMS text messages sent to patients who were identified as smokers or risky drinkers, which signposted them to behavior change apps. The primary outcome was the proportion of participants who clicked on the embedded link in the SMS text message to access information about the apps. The acceptability of the SMS text messages among the patients who had received them was also explored in a web-based survey. RESULTS: Our electronic signposting strategy-using SMS text messages to promote health behavior change apps to patients at risk-was found to be acceptable and feasible and had good reach. The hospital sent 1526 SMS text messages, signposting patients to either the National Health Service Smokefree or Drink Free Days apps. A total of 13.56% (207/1526) of the patients clicked on the embedded link to the apps, which exceeded our 5% a priori success criterion. Patients and staff contributed to the SMS text message content and delivery approach, which were perceived as acceptable before and after the delivery of the SMS text messages. The feasibility of the SMS text message format was determined and the target population was identified by mining the EHR. CONCLUSIONS: The OptiMine study demonstrated the proof of concept for this novel implementation strategy, which used SMS text messages to signpost at-risk individuals to behavior change apps at scale. The level of reach exceeded our a priori success criterion in a non-help-seeking population of patients receiving unsolicited SMS text messages, disconnected from hospital visits. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/23669.
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 | 0.031 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| 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".