MétaCan
Menu
← Back to cohort
Record W2758084785 · doi:10.2196/formative.7211

A Novel Patient Engagement Platform Using Accessible Text Messages and Calls (Epharmix): Feasibility Study

2017· article· en· W2758084785 on OpenAlexvenueno aff
Avik Som, Kunjan Patel, Eric Sink, Robert Peters, Kavon Javaherian, Jacob Groenendyk, Tonya W. An, Zhuchen Xu, Gregory Polites, Melvin Blanchard, Will Ross

Bibliographic record

VenueJMIR Formative Research · 2017
Typearticle
Languageen
FieldHealth Professions
TopicMobile Health and mHealth Applications
Canadian institutionsnot available
FundersNational Cancer Institute
KeywordsMedicineMedical emergencyHealthcare deliveryHealth careService providerService (business)Business

Abstract

fetched live from OpenAlex

BACKGROUND: Patient noncompliance with therapy, treatments, and appointments represents a significant barrier to improving health care delivery and reducing the cost of care. One method to improve therapeutic adherence is to improve feedback loops in getting clinically acute events and issues to the relevant clinical providers as necessary (ranging from detecting hypoglycemic events for patients with diabetes to notifying the provider when patients are out of medications). Patients often don't know which information should prompt a call to their physician and proactive checks by the clinics themselves can be very resource intensive. We hypothesized that a two-way SMS system combined with a platform web service for providers would enable both high patient engagement but also the ability to detect relevant clinical alerts. OBJECTIVE: The objectives of this study are to develop a feasible two-way automated SMS/phone call + web service platform for patient-provider communication, and then study the feasibility and acceptability of the Epharmix platform. First, we report utilization rates over the course of the first 18 months of operation including total identified clinically significant events, and second, review results of patient user-satisfaction surveys for interventions for patients with diabetes, COPD, congestive heart failure, hypertension, surgical site infections, and breastfeeding difficulties. METHODS: To test this question, we developed a web service + SMS/phone infrastructure ("Epharmix"). Utilization results were measured based on the total number of text messages or calls sent and received, with percentage engagement defined as a patient responding to a text message at least once in a given week, including the number of clinically significant alerts generated. User satisfaction surveys were sent once per month over the 18 months to measure satisfaction with the system, frequency and degree of communication. Descriptive statistics were used to describe the above information. RESULTS: In total, 28,386 text messages and 24,017 calls were sent to 929 patients over 9 months. Patients responded to 80% to 90% of messages allowing the system to detect 1164 clinically significant events. Patients reported increased satisfaction and communication with their provider. Epharmix increased the number of patient-provider interactions to over 10 on average in any given month for patients with diabetes, COPD, congestive heart failure, hypertension, surgical site infections, and breastfeeding difficulties. CONCLUSIONS: Engaging high-risk patients remains a difficult process that may be improved through novel, digital health interventions. The Epharmix platform enables increased patient engagement with very low risk to improve clinical outcomes. We demonstrated that engagement among high-risk populations is possible when health care comes conveniently to where they are.

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)0.008
metaresearch head score (Gemma)0.008
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: Empirical · Consensus signal: Empirical
Teacher disagreement score0.008
Threshold uncertainty score0.044

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.008
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0010.001
Scholarly communication0.0010.002
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0050.001

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.

Opus teacher head0.460
GPT teacher head0.624
Teacher spread0.164 · 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
GenreEmpirical

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

Citations7
Published2017
Admission routes1
Has abstractyes

Explore more

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