MétaCan
Menu
← Back to cohort
Record W4407372462 · doi:10.2196/62874

Technical Requirements, Design, and Automation Process for a Statewide Registry-Based Tailored Text Messaging System: Protocol for a Longitudinal Observational Study

2025· article· en· W4407372462 on OpenAlexvenueno aff
Deborah Ogunsanmi, J. Chambers, Asos Mahmood, Avinash Reddy Pakker, Anusha Kompalli, Umar Kabir, Satya Surbhi, Justin Gatwood, Md Sultan Mahmud, James E. Bailey

Bibliographic record

VenueJMIR Research Protocols · 2025
Typearticle
Languageen
FieldHealth Professions
TopicMobile Health and mHealth Applications
Canadian institutionsnot available
FundersAgency for Healthcare Research and Quality
KeywordsPreprintProtocol (science)Computer scienceProcess (computing)MultimediaWorld Wide WebMedicineOperating system

Abstract

fetched live from OpenAlex

BACKGROUND: Tailored text messaging is a low-cost mobile health intervention approach shown to effectively improve self-care behaviors and clinical outcomes for patients with chronic cardiometabolic conditions. Given the ubiquitous nature of mobile phones, text messages have the potential to reach a large audience. However, automating and disseminating tailored text messages to large populations at low cost presents major logistical challenges that serve as barriers to implementation. OBJECTIVE: This study aimed to describe the protocol for a longitudinal observational study designed to assess the feasibility of an innovative approach for automating and disseminating personalized and tailored text messages to large populations at risk of cardiovascular events using a low-cost registry-based tailored text messaging system known as the Heart Health Messages (HHM) program. Further, it describes the technical requirements, architectural design, automation process, and challenges associated with program implementation. METHODS: Patients at high risk of cardiovascular diseases are identified using a statewide population health registry known as the Tennessee Population Data Network. Tailored invitation messages and enrollment surveys are sent to eligible patients via Twilio. Upon completion of the receipt of consent and enrollment forms, participants receive tailored text messages from a library of generic messages based on participant-selected frequency of message delivery (daily or every other day). In addition, participants receive monthly text-based check-in survey messages designed to assess intervention adherence and improvement in self-care. Participants are also sent quarterly follow-up surveys to update enrollment information and preferences. All enrolled participants will receive tailored text messages for a 12-month intervention period. RESULTS: Since the start of the program, 18,974 patients from 2 major health systems have met the inclusion criteria and were eligible for the HHM program. A total of 3 phases of HHM 1.0 have been implemented so far, reaching 225 eligible patients in phase 1, a total of 5288 patients in phase 2, and 13,461 patients in phase 3, with an enrollment of approximately 2% (n=4/225), 3% (n=137/5228), and 3% (n=350/13461), respectively. Efforts are underway to implement strategies in collaboration with the health systems to enhance the HHM program rollout and patient participation. CONCLUSIONS: The HHM program is a low-cost tailored text messaging intervention set for broader dissemination and potential replication. The program has the capacity to improve outcomes for people with chronic medical conditions. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/62874.

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 imitation

Not 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.

metaresearch head score (Codex)0.129
metaresearch head score (Gemma)0.089
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Protocol · Consensus signal: Protocol
Teacher disagreement score0.129
Threshold uncertainty score0.681

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1290.089
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0020.003
Bibliometrics0.0030.003
Science and technology studies0.0060.003
Scholarly communication0.0030.002
Open science0.0030.003
Research integrity0.0050.006
Insufficient payload (model declined to judge)0.0300.011

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.

Opus teacher head0.680
GPT teacher head0.696
Teacher spread0.016 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreProtocol

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".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Research Protocols→Same topicMobile Health and mHealth Applications→French-language works237,207→