Predicting the Risk of Inpatient Hypoglycemia With Machine Learning Using Electronic Health Records

Abstract

We analyzed data from inpatients with diabetes admitted to a large university hospital to predict the risk of hypoglycemia through the use of machine learning algorithms. RESEARCH DESIGN AND METHODSFour years of data were extracted from a hospital electronic health record system. This included laboratory and point-of-care blood glucose (BG) values to identify biochemical and clinically significant hypoglycemic episodes (BG £3.9 and £2.9 mmol/L, respectively). We used patient demographics, administered medications, vital signs, laboratory results, and procedures performed during the hospital stays to inform the model. Two iterations of the data set included the doses of insulin administered and the past history of inpatient hypoglycemia. Eighteen different prediction models were compared using the area under the receiver operating characteristic curve (AUROC) through a 10-fold cross validation. RESULTSWe analyzed data obtained from 17,658 inpatients with diabetes who underwent 32,758 admissions between July 2014 and August 2018. The predictive factors from the logistic regression model included people undergoing procedures, weight, type of diabetes, oxygen saturation level, use of medications (insulin, sulfonylurea, and metformin), and albumin levels. The machine learning model with the best performance was the XGBoost model (AUROC 0.96). This outperformed the logistic regression model, which had an AUROC of 0.75 for the estimation of the risk of clinically significant hypoglycemia. CONCLUSIONSAdvanced machine learning models are superior to logistic regression models in predicting the risk of hypoglycemia in inpatients with diabetes. Trials of such models should be conducted in real time to evaluate their utility to reduce inpatient hypoglycemia.Hypoglycemia is a common and serious complication affecting people with diabetes (1). It is an inappropriately low blood glucose (BG) that results in significant morbidity in people with type 1 diabetes and in many people with type 2 diabetes (2). A BG level of #3.9 mmol/L is defined as level 1 hypoglycemia. A BG level of 2.9 mmol/L and lower is defined as level 2 hypoglycemia requiring immediate action, as at that level, neurogenic and neuroglycopenic symptoms begin to occur (3). Hypoglycemia can lead

Machine Learning Techniques for Hypoglycemia Prediction: Trends and Challenges

“…Multiple systems used text and language processing for the detection of hypoglycemia. For instance, hypoglycemia was detected from electronic health records (EHRs) in the investigations proposed by Jin et al [ 29 ], Ruan et al [ 31 ], and Jin Li et al [ 34 ]. Chen et al [ 30 ] employed patient secure messages for automatic detection of hypoglycemia while Zhou et al [ 26 ] aimed at detecting hypoglycemia by processing the text of clinical notes of patients.…”

“…Seo et al [ 43 ], Güemes et al [ 60 ], Vahedi et al [ 33 ], G Noaro et al [ 72 ], Vu et al [ 47 ], Reddy et al [ 40 ], Chen et al [ 30 ], Dave et al [ 52 ], Calhoun et al [ 45 ], Amar et al [ 75 ], Hidalgo et al [ 77 ], and Rodriguez et al [ 79 ] have all used RF for predicting/detecting hypoglycemia. Ruan et al [ 31 ] and Cappon et al [ 66 ] used the XGboost algorithm. XGboost is the gradient-boosted variant of DT and is aimed at enhancing the performance of decisions trees.…”

Ability of Current Machine Learning Algorithms to Predict and Detect Hypoglycemia in Patients With Diabetes Mellitus: Meta-analysis

“…Table 1 shows the summary of study characteristics. Of the 33 studies, 19 studies (58%) [ 26 - 31 , 33 , 35 , 36 , 38 - 42 , 44 - 47 , 54 ] predicted hypoglycemia, and the remaining 14 studies (42%) detected hypoglycemia [ 15 , 20 , 25 , 32 , 34 , 37 , 43 , 48 - 53 , 55 ]. As much as 25 of the 33 included studies (76%) [ 15 , 20 , 25 - 27 , 29 , 30 , 32 , 35 , 36 , 38 , 39 , 41 - 44 , 46 - 53 , 55 ] specified type 1 as the type of DM.…”

Recent evolutions of machine learning applications in clinical laboratory medicine

“…of 13,309 Canadian patients, Lai et al [45] achieved an AUROC of 0.85 with a sensitivity of 71.6% using a GBM algorithm and an AUROC of 0.84 and sensitivity of 73.4% using a Logistic Regression model. In another study, an XGBoost model based on demographics, vital signs, laboratory tests, and medication use appeared to be superior in predicting the risk of hypoglycemia in patients with DM (AUROC of 0.96) [46]. An alternative screening tool using Raman spectroscopy and an ANN was able to identify DM patients with 88.9-90.0% accuracy, depending on the sample size (i.e.…”

“…Predictive models have also been developed to screen for diabetes mellitus (DM) and its complications [45][46][47]. Using the most recent EHRs and laboratory information (e.g.…”