Can a Single Variable Predict Early Dropout From Digital Health Interventions? Comparison of Predictive Models From Two Large Randomized Trials
Open accessThe DOI matches its Crossref record; 49 of the 50 references it cites were found in a registry or an index.
Abstract
Background: A single generalizable metric that accurately predicts early dropout from digital health interventions has the potential to readily inform intervention targets and treatment augmentations that could boost retention and intervention outcomes. We recently identified a type of early dropout from digital health interventions for smoking cessation, specifically, users who logged in during the first week of the intervention and had little to no activity thereafter. These users also had a substantially lower smoking cessation rate with our iCanQuit smoking cessation app compared with users who used the app for longer periods. Objective: This study aimed to explore whether log-in count data, using standard statistical methods, can precisely predict whether an individual will become an iCanQuit early dropout while validating the approach using other statistical methods and randomized trial data from 3 other digital interventions for smoking cessation (combined randomized N=4529). Methods: Standard logistic regression models were used to predict early dropouts for individuals receiving the iCanQuit smoking cessation intervention app, the National Cancer Institute QuitGuide smoking cessation intervention app, the WebQuit.org smoking cessation intervention website, and the Smokefree.gov smoking cessation intervention website. The main predictors were the number of times a participant logged in per day during the first 7 days following randomization. The area under the curve (AUC) assessed the performance of the logistic regression models, which were compared with decision trees, support vector machine, and neural network models. We also examined whether 13 baseline variables that included a variety of demographics (eg, race and ethnicity, gender, and age) and smoking characteristics (eg, use of e-cigarettes and confidence in being smoke free) might improve this prediction. Results: The AUC for each logistic regression model using only the first 7 days of log-in count variables was 0.94 (95% CI 0.90-0.97) for iCanQuit, 0.88 (95% CI 0.83-0.93) for QuitGuide, 0.85 (95% CI 0.80-0.88) for WebQuit.org, and 0.60 (95% CI 0.54-0.66) for Smokefree.gov. Replacing logistic regression models with more complex decision trees, support vector machines, or neural network models did not significantly increase the AUC, nor did including additional baseline variables as predictors. The sensitivity and specificity were generally good, and they were excellent for iCanQuit (ie, 0.91 and 0.85, respectively, at the 0.5 classification threshold). Conclusions: Logistic regression models using only the first 7 days of log-in count data were generally good at predicting early dropouts. These models performed well when using simple, automated, and readily available log-in count data, whereas including self-reported baseline variables did not improve the prediction. The results will inform the early identification of people at risk of early dropout from digital health interventions with the goal of intervening further by providing them with augmented treatments to increase their retention and, ultimately, their intervention outcomes.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Modern Applied Statistics with S
Venables, W. N., & Ripley, B. D. (2002) · Statistics and Computing · doi:10.1007/978-0-387-21706-2 · Cited by 24,305
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697 · cited 1×
“AUC values were compared between models using the “roc.test” function in the R library pROC [47].”
Finding Groups in Data: An Introduction to Cluster Analysis
Kaufman, L., & Rousseeuw, P. J. (1990) · Wiley Series in Probability and Statistics · doi:10.1002/9780470316801 · Cited by 7,344
Receiver Operating Characteristic Curve in Diagnostic Test Assessment
Mandrekar, J. N. (2010) · Journal of Thoracic Oncology · doi:10.1097/jto.0b013e3181ec173d · Cited by 4,506 · cited 1×
“In general, an AUC value between 0.7 and 0.8 is considered acceptable, 0.8 to 0.9 is considered excellent, and >0.9 is considered outstanding [46].”
InfluentialEysenbach, G. (2005) · Journal of Medical Internet Research · doi:10.2196/jmir.7.1.e11 · Cited by 2,524 · cited 2×
“An ongoing central challenge to the overall efficacy and broadly scalable implementation of digital interventions is the phenomenon of users dropping out early [10].”
Tu, J. V. (1996) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(96)00002-9 · Cited by 1,818 · cited 1×
“…model that best predicted early dropout was a standard logistic regression model, as opposed to more sophisticated machine learning models that require more advanced knowledge of machine learning as well as large amounts of data, have greater computational burden, and are prone to overfitting [50].”
A Clinical Practice Guideline for Treating Tobacco Use and Dependence: 2008 Update
(2008) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2008.04.009 · Cited by 1,410 · cited 2×
“…diverse sample of 2415 adult daily smokers from all 50 US states who were randomized 1:1 to receive access to an ACT-based smartphone app (iCanQuit; n=1214) or a United States Clinical Practice Guidelines (USCPG) approach–based smartphone app (QuitGuide; n=1201) for smoking cessation [27].”
Adherence in Internet Interventions for Anxiety and Depression
Christensen, H., Griffiths, K. M., & Farrer, L. (2009) · Journal of Medical Internet Research · doi:10.2196/jmir.1194 · Cited by 1,133 · cited 1×
“Although early drop out has been variously defined across studies (eg, completing only 1 module or stopping within the first week or the first few weeks) [10,11], the fraction of users who fall into this category is quite large, with some studies showing it as high as 82% [12-14].”
Research works printed but not linked: 4
- 10.2196/17738 · doi:10.2196/17738 · Paper page
- Witten, IH, 2000, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations
- Alpaydin, E, 2020, Introduction to Machine Learning. 4th edition
- Pedregosa, F, 2011, J Mach Learn Res, 12, 2825
Cited by
Zantvoort, K., Nacke, B., Görlich, D., Hornstein, S., Jacobi, C., & Funk, B. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01360-w · Cited by 116
“As pre-intervention questionnaire data has limited predictive power regarding dropout by itself 27,30,32,57 , it was used to inves-tigatealowpredictivepowersetting.”
Ardito, V., Golubev, G., Ciani, O., & Tarricone, R. (2023) · JMIR Cancer · doi:10.2196/42092 · Cited by 56
“Figure 1 describes the PRISMA flowchart [36,37].”
BackgroundWillingham, T. B., Stowell, J. F., Collier, G., & Backus, D. A. (2024) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph21010079 · Cited by 62
Krotter, A., Diego, G. A., Menéndez, A. G., González‐Roz, A., Secades‐Villa, R., & Pérez, Á. G. (2024) · Journal of Contextual Behavioral Science · doi:10.1016/j.jcbs.2024.100773 · Cited by 37
Predicting early user churn in a public digital weight loss intervention
Jakob, R., Lepper, N., Fleisch, E., & Kowatsch, T. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642321 · Cited by 21
“As a baseline, we adopt a low-dimensional model informed by Bricker et al. (2023) that predicts churn based on the number of app logins per day of the first seven days of user interaction [7].”
BackgroundMethodResultInfluential
Metadata
- Authors
- Bricker, J., Miao, Z., Mull, K., Santiago-Torres, M., & Vock, D. M.
- Affiliations
- University of Washington (US)
- Fred Hutch Cancer Center (US)
- University of Minnesota (US)
- Corresponding author
- Bricker, Jonathan
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2023-01-20
- Volume
- 25
- Pages
- e43629
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC9898835
- OpenAlex
- W4313335732
- Cited by
- 22
- References
- 50
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 10 · 2023: 1
- FWCI
- 2.94
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Cancer Institute (R01CA192849, R01CA247156, R01CA253975)
- Topics
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Smoking Behavior and Cessation
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Keywords
- digital health interventions, smoking cessation apps, user retention, predictive modeling, decision tree, support vector machine, artificial neural networks, logistic regression, electronic cigarettes, baseline predictors, augmentation therapy, user engagement
- MeSH terms
- Humans, Randomized Controlled Trials as Topic, Smoking Cessation, Self Report, Mobile Applications, Electronic Nicotine Delivery Systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.