Predicting Inpatient Glucose Levels and Insulin Dosing by Machine Learning on Electronic Health Records
Liu, X.; Jankovic, I.; Chen, J. H.
Show abstract
Poorly controlled glucose levels are associated with serious morbidity and mortality in hospitalized patients. Hospital diabetes management aims to maintain the glucose level within a desired range, primarily via insulin administration. Current inpatient glucose control relies significantly on expert knowledge, but this results in large variability and often suboptimal blood sugars in practice. We applied supervised machine learning methods to electronic health record (EHR) data to build predictive models that can inform inpatient insulin management. We found that individual blood glucose levels and insulin dosing are highly erratic and cannot be predicted precisely (MAE 28mg/dL, R2 0.2). However, prescribing decisions can still be driven by the more reliable predictions of average daily glucose levels (MAE 21mg/dL, R2 0.4) and whether any patients glucose levels will be higher than the clinically desired range in the next day (sens 0.73, spec 0.79).
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Causal modeling of chronic kidney disease in a participatory framework for informing the inclusion of social drivers in health algorithms 91%
- Large Language Models Facilitate the Generation of Electronic Health Record Phenotyping Algorithms 91%
- medExtractR: A medication extraction algorithm for electronic health records using the R programming language 91%
Similar papers in this journal
- GLUCOSE: A Distributional Reinforcement Learning Model for Optimal Glucose Control After Cardiac Surgery 93%
- Predicting critical state after COVID-19 diagnosis: Model development using a large US electronic health record dataset 92%
- Continuous-Time and Dynamic Suicide Attempt Risk Prediction with Neural Ordinary Differential Equations 90%
Similar papers in this journal
- Clinical interpretation of machine learning models for prediction of diabetic complications using electronic health records 93%
- Framework for Identifying Drug Repurposing Candidates from Observational Healthcare Data 91%
- Modeling physician variability to prioritize relevant medical record information 90%
Similar papers in this journal
- Estimating Heritability of Glycaemic Response to Metformin using Nationwide Electronic Health Records and Population-Sized Pedigree 92%
- Predicting future hospital antimicrobial resistance prevalence using machine learning 89%
- Pretrained Patient Trajectories for Adverse Drug Event Prediction Using Common Data Model-based Electronic Health Records 89%
Similar papers in this journal
- An Interpretable Risk Prediction Model for Healthcare with Pattern Attention 91%
- Implicit bias in Critical Care Data: Factors affecting sampling frequencies and missingness patterns of clinical and biological variables in ICU Patients 90%
- Temporal Relationship of Computed and Structured Diagnoses in Electronic Health Record Data 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.