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

10.2196/13617 ◽  
2019 ◽  
Vol 21 (9) ◽  
pp. e13617 ◽  
Author(s):  
Daniel Hansen Pedersen ◽  
Marjan Mansourvar ◽  
Camilla Sortsø ◽  
Thomas Schmidt
Keyword(s):  
Health Care ◽  
Random Forest ◽  
Health Care Systems ◽  
Activity Patterns ◽  
Predictor Variables ◽  
Lifestyle Interventions ◽  
Health Coaches ◽  
Care Systems ◽  
Electronic Health ◽  
Ehealth Intervention

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.

scholarly journals Predicting Dropouts From an Electronic Health Platform for Lifestyle Interventions: Analysis of Methods and Predictors (Preprint)

2019 ◽  
Author(s):  
Daniel Hansen Pedersen ◽  
Marjan Mansourvar ◽  
Camilla Sortsø ◽  
Thomas Schmidt
Keyword(s):  
Health Care ◽  
Random Forest ◽  
Health Care Systems ◽  
Activity Patterns ◽  
Predictor Variables ◽  
Lifestyle Interventions ◽  
Health Coaches ◽  
Care Systems ◽  
Electronic Health ◽  
Ehealth Intervention

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.

scholarly journals An efficient approach for surveillance of childhood diabetes by type derived from electronic health record data: the SEARCH for Diabetes in Youth Study

2016 ◽  
Vol 23 (6) ◽  
pp. 1060-1067 ◽  
Author(s):  
Victor W Zhong ◽  
Jihad S Obeid ◽  
Jean B Craig ◽  
Emily R Pfaff ◽  
Joan Thomas ◽  
...  
Keyword(s):  
Health Care ◽  
Electronic Health Record ◽  
Health Care Systems ◽  
Diabetes Type ◽  
Health Record ◽  
Childhood Diabetes ◽  
Electronic Health Record Data ◽  
Efficient Approach ◽  
Care Systems ◽  
Electronic Health

Abstract Objective To develop an efficient surveillance approach for childhood diabetes by type across 2 large US health care systems, using phenotyping algorithms derived from electronic health record (EHR) data. Materials and Methods Presumptive diabetes cases <20 years of age from 2 large independent health care systems were identified as those having ≥1 of the 5 indicators in the past 3.5 years, including elevated HbA1c, elevated blood glucose, diabetes-related billing codes, patient problem list, and outpatient anti-diabetic medications. EHRs of all the presumptive cases were manually reviewed, and true diabetes status and diabetes type were determined. Algorithms for identifying diabetes cases overall and classifying diabetes type were either prespecified or derived from classification and regression tree analysis. Surveillance approach was developed based on the best algorithms identified. Results We developed a stepwise surveillance approach using billing code–based prespecified algorithms and targeted manual EHR review, which efficiently and accurately ascertained and classified diabetes cases by type, in both health care systems. The sensitivity and positive predictive values in both systems were approximately ≥90% for ascertaining diabetes cases overall and classifying cases with type 1 or type 2 diabetes. About 80% of the cases with “other” type were also correctly classified. This stepwise surveillance approach resulted in a >70% reduction in the number of cases requiring manual validation compared to traditional surveillance methods. Conclusion EHR data may be used to establish an efficient approach for large-scale surveillance for childhood diabetes by type, although some manual effort is still needed.

scholarly journals Pragmatic (trial) informatics: a perspective from the NIH Health Care Systems Research Collaboratory

2017 ◽  
Vol 24 (5) ◽  
pp. 996-1001 ◽  
Author(s):  
Rachel L Richesson ◽  
Beverly B Green ◽  
Reesa Laws ◽  
Jon Puro ◽  
Michael G Kahn ◽  
...  
Keyword(s):  
Health Care ◽  
Health System ◽  
Health Care Systems ◽  
Pragmatic Trial ◽  
Heterogeneous Systems ◽  
Full Potential ◽  
Systems Research ◽  
Pragmatic Clinical Trials ◽  
Care Systems ◽  
Electronic Health

Abstract Pragmatic clinical trials (PCTs) are research investigations embedded in health care settings designed to increase the efficiency of research and its relevance to clinical practice. The Health Care Systems Research Collaboratory, initiated by the National Institutes of Health Common Fund in 2010, is a pioneering cooperative aimed at identifying and overcoming operational challenges to pragmatic research. Drawing from our experience, we present 4 broad categories of informatics-related challenges: (1) using clinical data for research, (2) integrating data from heterogeneous systems, (3) using electronic health records to support intervention delivery or health system change, and (4) assessing and improving data capture to define study populations and outcomes. These challenges impact the validity, reliability, and integrity of PCTs. Achieving the full potential of PCTs and a learning health system will require meaningful partnerships between health system leadership and operations, and federally driven standards and policies to ensure that future electronic health record systems have the flexibility to support research.

scholarly journals eSyM: An Electronic Health Record–Integrated Patient-Reported Outcomes–Based Cancer Symptom Management Program Used by Six Diverse Health Systems

2022 ◽  
Author(s):  
Michael J. Hassett ◽  
Christine Cronin ◽  
Terrence C. Tsou ◽  
Jason Wedge ◽  
Jessica Bian ◽  
...  
Keyword(s):  
Health Care ◽  
Electronic Health Record ◽  
Symptom Management ◽  
Patient Reported Outcomes ◽  
Health Care Systems ◽  
Management Program ◽  
Health Record ◽  
Patient Reported ◽  
Care Systems ◽  
Electronic Health

PURPOSE Collecting patient-reported outcomes (PROs) can improve symptom control and quality of life, enhance doctor-patient communication, and reduce acute care needs for patients with cancer. Digital solutions facilitate PRO collection, but without robust electronic health record (EHR) integration, effective deployment can be hampered by low patient and clinician engagement and high development and deployment costs. The important components of digital PRO platforms have been defined, but procedures for implementing integrated solutions are not readily available. METHODS As part of the NCI's IMPACT consortium, six health care systems partnered with Epic to develop an EHR-integrated, PRO-based electronic symptom management program (eSyM) to optimize postoperative recovery and well-being during chemotherapy. The agile development process incorporated user-centered design principles that required engagement from patients, clinicians, and health care systems. Whenever possible, the system used validated content from the public domain and took advantage of existing EHR capabilities to automate processes. RESULTS eSyM includes symptom surveys on the basis of the PRO-Common Terminology Criteria for Adverse Events (PRO-CTCAE) plus two global wellness questions; reminders and symptom self-management tip sheets for patients; alerts and symptom reports for clinicians; and population management dashboards. EHR dependencies include a secure Health Insurance Portability and Accountability Act-compliant patient portal; diagnosis, procedure and chemotherapy treatment plan data; registries that identify and track target populations; and the ability to create reminders, alerts, reports, dashboards, and charting shortcuts. CONCLUSION eSyM incorporates validated content and leverages existing EHR capabilities. Build challenges include the innate technical limitations of the EHR, the constrained availability of site technical resources, and sites' heterogenous EHR configurations and policies. Integration of PRO-based symptom management programs into the EHR could help overcome adoption barriers, consolidate clinical workflows, and foster scalability and sustainability. We intend to make eSyM available to all Epic users.

Sign in / Sign up

Export Citation Format

Share Document