Application of Machine Learning Models to Evaluate Hypoglycemia Risk in Type 2 Diabetes

Introduction To identify predictors of hypoglycemia and five other clinical and economic outcomes among treated patients with type 2 diabetes (T2D) using machine learning and structured data from a large, geographically diverse administrative claims database. Methods A retrospective cohort study des...

Full description

Saved in:
Bibliographic Details
Published in:Diabetes therapy 2020-03, Vol.11 (3), p.681-699
Main Authors: Mueller, Luke, Berhanu, Paulos, Bouchard, Jonathan, Alas, Veronica, Elder, Kenneth, Thai, Ngoc, Hitchcock, Cody, Hadzi, Tiffany, Khalil, Iya, Miller-Wilson, Lesley-Ann
Format: Article
Language:English
Subjects:
Antidiabetics
Cardiology
Complications and side effects
Diabetes
Drug therapy
Endocrinology
Generalized linear models
Hypoglycemia
Insulin
Internal Medicine
Machine learning
Medical research
Medicine
Medicine & Public Health
Medicine, Experimental
Methods
Original Research
Physiological aspects
Risk assessment
Risk factors
Technology application
Type 2 diabetes
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Introduction To identify predictors of hypoglycemia and five other clinical and economic outcomes among treated patients with type 2 diabetes (T2D) using machine learning and structured data from a large, geographically diverse administrative claims database. Methods A retrospective cohort study design was applied to Optum Clinformatics claims data indexed on first antidiabetic prescription date. A hypothesis-free, Bayesian machine learning analytics platform (GNS Healthcare REFS™: Reverse Engineering and Forward Simulation) was used to build ensembles of generalized linear models to predict six outcomes defined in patients’ 1-year post-index claims history, including hypoglycemia, antidiabetic class persistence, glycated hemoglobin (HbA1c) target attainment, HbA1c change, T2D-related inpatient admissions, and T2D-related medical costs. A unified set of 388 variables defined in patients’ 1-year pre-index claims history constituted the set of predictors for all REFS models. Results The derivation cohort comprised 453,487 patients with a T2D diagnosis between 2014 and 2017. Patients with comorbid conditions had the highest risk of hypoglycemia, including those with prior hypoglycemia (odds ratio [OR] = 25.61) and anemia (OR = 1.29). Other identified risk factors included insulin (OR = 2.84) and sulfonylurea use (OR = 1.80). Biguanide use (OR = 0.75), high blood glucose (> 125 mg/dL vs. 
ISSN:1869-6953
1869-6961
DOI:10.1007/s13300-020-00759-4