MétaCan
Menu
← Back to cohort
Record W2897357222 · doi:10.2196/mhealth.9967

Predicting Attrition in a Text-Based Nutrition Education Program: Survival Analysis of Text2BHealthy

2018· article· en· W2897357222 on OpenAlexvenueno aff
Stephanie Grutzmacher, Ashley Munger, Katherine E. Speirs, Yassaman Vafai, Evan Hilberg, Erin Braunscheidel Duru, L. Worthington, Lisa Lachenmayr

Bibliographic record

VenueJMIR mhealth and uhealth · 2018
Typearticle
Languageen
FieldHealth Professions
TopicMobile Health and mHealth Applications
Canadian institutionsnot available
FundersU.S. Department of Agriculture
KeywordsAttritionShort Message ServiceComputer scienceText messageText messagingContext (archaeology)Duration (music)Drop outVariety (cybernetics)mHealthMultimediaWorld Wide WebMedicineNursingArtificial intelligenceComputer networkPsychological intervention

Abstract

fetched live from OpenAlex

BACKGROUND: Text-based programs have been shown to effectively address a wide variety of health issues. Although little research examines short message service (SMS) text messaging program characteristics that predict participant retention and attrition, features of SMS text message programs, such as program duration and intensity, message content, and the participants' context, may have an impact. The impact of stop messages-messages with instructions for how to drop out of an SMS text message program-may be particularly important to investigate. OBJECTIVE: The aim of this study was to describe attrition from Text2BHealthy, a text-based nutrition and physical activity promotion program for parents of low-income elementary school children, and to determine the impact of message content and number of stop messages received on attrition. METHODS: Using data from 972 parents enrolled in Text2BHealthy, we created Kaplan-Meier curves to estimate differences in program duration for different SMS text message types, including nutrition, physical activity, stop, and other messages. Covariates, including rurality and number of stop messages received, were included. RESULTS: Retention rates by school ranged from 74% (60/81) to 95.0% (132/139), with an average retention rate of 85.7% (833/972) across all schools. Program duration ranged from 7 to 282 days, with a median program duration of 233 days and an average program duration of 211.7 days. Among those who dropped out, program duration ranged from 7 to 247 days, with a median program duration of 102.5 days. Receiving a stop message increased the probability of attrition compared with receiving messages about nutrition, physical activity, or other topics (hazard ratio=51.5, 95% CI 32.46-81.7; P<.001). Furthermore, each additional stop message received increased the probability of attrition (hazard ratio=10.36, 95% CI 6.14-17.46; P<.001). The degree of rurality also had a significant effect on the probability of attrition, with metropolitan county participants more likely to drop out of the program than rural county participants. The interaction between SMS text message type and total number of stop messages received had a significant effect on attrition, with the effect of the number of stop messages received dependent on the SMS text message type. CONCLUSIONS: This study demonstrates the potential of SMS text message programs to retain participants over time. Furthermore, this study suggests that the probability of attrition increases substantially when participants receive messages with instructions for dropping out of the program. Program planners should carefully consider the impact of stop messages and other program content and characteristics on program retention. Additional research is needed to identify participant, programmatic, and contextual predictors of program duration and to explicate the relationship between program duration and program efficacy.

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)0.022
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: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.008
Threshold uncertainty score0.042

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.022
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.001

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 head0.087
GPT teacher head0.495
Teacher spread0.408 · 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

Citations15
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueJMIR mhealth and uhealth→Same topicMobile Health and mHealth Applications→French-language works237,207→