Abstract
Background: Treatment goals for diabetes and related conditions including hypertension and prediabetes are defined as reductions in health metrics: blood glucose concentration (BG), blood pressure (BP) and weight. Accurately predicting these metrics enables the delivery of timely treatment and lifestyle recommendations, leading to improved outcomes. We used health and self-care data collected in the One Drop app to forecast changes in BG, BP and weight, one to six months in advance. Method: Data from a sample of over 50,000 app users were used to train a suite of patent-pending supervised learning models, each for a different health metric (weight, BP or BG) and time horizon (1-2, 2-3, 3-4, or 4-6 months). People in the sample were not enrolled in One Drop programs focused on reducing weight or blood pressure. Data collected prior to 2019 were used for training; data from January 2019 through February 2020 were used for testing. Prediction root mean square error (RMSE) was compared to the RMSE that would result from assuming persistence (no change from current values). For each health metric, population subsets were identified, based on information available at prediction time, for whom predictions were more accurate. Results: The test set comprised over 200,000 predictions. Error reduction relative to persistence varied by metric, forecast horizon, and subset. For weight, persistence RMSE ranged from 2.2-5.4 kg; predictions reduced RMSE by 6.0-9.3%. For 30-day average systolic BP, persistence RMSE ranged from 11.3-16.1 mm Hg; predictions reduced RMSE by 14.2-20.0%. For 30-day average BG, persistence RMSE ranged from 19.4 to 58.8 mg/dL; predictions reduced RMSE by 12.6-40.5%. Conclusion: Machine learning models based on app-collected health and self-care data can predict changes in BG, BP and weight up to six months in advance. These predictions can contribute to prioritizing interventions and guiding self-care, potentially improving outcomes. Disclosure Y. Wexler: Employee; Self; One Drop. D. Goldner: Employee; Self; One Drop. G. Merchant: Employee; Self; One Drop. A. Hirsch: Employee; Self; Informed Data Systems Inc. B. Huddleston: Employee; Self; One Drop. Stock/Shareholder; Self; One Drop. J. Dachis: Board Member; Self; One Drop. Employee; Self; One Drop. Stock/Shareholder; Self; One Drop.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.