Complication Risk Profiling in Diabetes Care: A Bayesian Multi-Task and Feature Relationship Learning Approach
- 8 March 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 32 (7) , 1276-1289
Abstract
Diabetes is a chronic disease that often results in multiple complications. Risk prediction and profiling of diabetes complications is critical for improved outcomes. In this paper, focusing on Type 2 diabetes mellitus (T2DM), we study the risk of developing complications after the initial T2DM diagnosis from longitudinal patient records. We propose a novel multi-task learning approach to simultaneously model multiple complications where each task corresponds to the risk modeling of one complication. Specifically, the proposed method strategically captures the relationships (1) between the risks of multiple T2DM complications, (2) between the different risk factors, and (3) between the risk factor selection patterns, which assumes similar complications have similar contributing risk factors. The method uses coefficient shrinkage to identify an informative subset of risk factors from high-dimensional data, and uses a hierarchical Bayesian framework to allow domain knowledge to be incorporated as priors. The proposed method is favorable for healthcare applications because in additional to improved prediction performance, relationships among the different risks and risk factors are also identified. Extensive experimental results on a large electronic medical claims database show that the proposed method outperforms state-of-the-art models by a significant margin.Keywords
This publication has 44 references indexed in Scilit:
- Copulas in Machine Learning2013
- Mechanisms of Diabetic ComplicationsPhysiological Reviews, 2013
- The horseshoe estimator for sparse signalsBiometrika, 2010
- Prediction of Chronic Obstructive Pulmonary Disease (COPD) in Asthma Patients Using Electronic Medical RecordsJournal of the American Medical Informatics Association, 2009
- Joint Regression Analysis of Correlated Data Using Gaussian CopulasBiometrics, 2009
- Diabetes-Related Microvascular and Macrovascular Diseases in the Physical Therapy SettingPhysical Therapy, 2008
- Convex multi-task feature learningMachine Learning, 2008
- The human disease networkProceedings of the National Academy of Sciences, 2007
- Polypharmacy as commonly defined is an indicator of limited value in the assessment of drug‐related problemsBritish Journal of Clinical Pharmacology, 2006
- Report of the Expert Committee on the Diagnosis and Classification of Diabetes MellitusDiabetes Care, 2003