Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Sep 4;21(9):e13617.
doi: 10.2196/13617.

Predicting Dropouts From an Electronic Health Platform for Lifestyle Interventions: Analysis of Methods and Predictors

Daniel Hansen Pedersen  1 , Marjan Mansourvar  2 , Camilla Sortsø  1 , Thomas Schmidt  2
Affiliations

Predicting Dropouts From an Electronic Health Platform for Lifestyle Interventions: Analysis of Methods and Predictors

Daniel Hansen Pedersen et al. J Med Internet Res. .

Abstract

Background: The increasing prevalence and economic impact of chronic diseases challenge health care systems globally. Digital solutions can potentially improve efficiency and quality of care, but these initiatives struggle with nonusage attrition. Machine learning methods have been proven to predict dropouts in other settings but lack implementation in health care.

Objective: This study aimed to gain insight into the causes of attrition for patients in an electronic health (eHealth) intervention for chronic lifestyle diseases and evaluate if attrition can be predicted and consequently prevented. We aimed to build predictive models that can identify patients in a digital lifestyle intervention at high risk of dropout by analyzing several predictor variables applied in different models and to further assess the possibilities and impact of implementing such models into an eHealth platform.

Methods: Data from 2684 patients using an eHealth platform were iteratively analyzed using logistic regression, decision trees, and random forest models. The dataset was split into a 79.99% (2147/2684) training and cross-validation set and a 20.0% (537/2684) holdout test set. Trends in activity patterns were analyzed to assess engagement over time. Development and implementation were performed iteratively with health coaches.

Results: Patients in the test dataset were classified as dropouts with an 89% precision using a random forest model and 11 predictor variables. The most significant predictors were the provider of the intervention, 2 weeks inactivity, and the number of advices received from the health coach. Engagement in the platform dropped significantly leading up to the time of dropout.

Conclusions: Dropouts from eHealth lifestyle interventions can be predicted using various data mining methods. This can support health coaches in preventing attrition by receiving proactive warnings. The best performing predictive model was found to be the random forest.

Keywords: adherence; chronic disease; data mining; decision trees; digital health; eHealth; law of attrition; logistic regression; patient dropouts.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: DHP and CS are employed by Liva Healthcare A/S.

Figures

Figure 1
Figure 1
Proportion of active patients over 4 segments of the intervention period.
Figure 2
Figure 2
Average number of activities in the platform per week in the program for patients who either completed the intervention or entered retention (n=175), excluding week 0 in the program.
Figure 3
Figure 3
Proportion of active patients over the total number of inactive weeks in the program defined by gender.
Figure 4
Figure 4
Proportion of active patients over the total number of inactive weeks in the program defined by age.
Figure 5
Figure 5
Variable importance plot for the 11 selected variables. Period of intervention is separated into 4 dummy variables.
Figure 6
Figure 6
Receiver operating characteristic curve with area under the curve for the random forest model on the holdout test data.
Figure 7
Figure 7
Histogram of current activity level (%; calculated using Equation 1) compared with forecasted activity based on the linear overall population trend line. Only patients with at least 6 weeks on the platform included
See this image and copyright information in PMC

References

    1. Gemmill M. CiteSeerX. 2008. Research Note: Chronic Disease Management in Europe http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.619.4434&rep=re....
    1. Fiordelli M, Diviani N, Schulz PJ. Mapping mhealth research: a decade of evolution. J Med Internet Res. 2013 May 21;15(5):e95. doi: 10.2196/jmir.2430. - DOI - PMC - PubMed
    1. Brandt V, Brandt CJ, Glintborg D, Arendal C, Toubro S, Brandt K. Sustained weight loss during 20 months using a personalized interactive internet based dietician advice program in a general practice setting. Int J Adv Life Sci. 2011;3(1-2):23–8. https://www.researchgate.net/publication/228480051_Sustained_Weight_Loss...
    1. Afshin A, Babalola D, Mclean M, Yu Z, Ma W, Chen CY, Arabi M, Mozaffarian D. Information technology and lifestyle: a systematic evaluation of internet and mobile interventions for improving diet, physical activity, obesity, tobacco, and alcohol use. J Am Heart Assoc. 2016 Aug 31;5(9):pii: e003058. doi: 10.1161/JAHA.115.003058. http://www.ahajournals.org/doi/full/10.1161/JAHA.115.003058?url_ver=Z39.... - DOI - DOI - PMC - PubMed
    1. Coiera E. Guide to Health Informatics. Third Edition. Florida, United States: CRC Press; 2015. Telehealth and mobile health; pp. 343–69.

Publication types

MeSH terms