Abstract

Introduction: This evidence-based practice (EBP) project aims to improve patient safety and outcomes through the implementation of a predictive modeling tool (XGBoost) to predict and prevent hypoglycemic events in hospitalized adults at Sanford Health. Hypoglycemia continues to be a major safety concern, and early prediction can prevent complications

Methods: The project involved a literature review of articles to identify and recommend a hypoglycemic predictive modeling tool for Sanford Health. Included articles were published between 2019 and 2024 and selected through keywords like inpatients, hypoglycemia, glucose prediction, and predictive modeling. Searches across databases, including PubMed, JAMA, JIML, and UpToDate, initially yielded 18 articles, of which only 10 met criteria for this project’s focus on inpatient hypoglycemia.

Results

The review highlighted that inpatient hypoglycemia results from multiple complex factors. Additionally, the implementation of predictive tools can effectively analyze patient data to identify those at high risk. These models use algorithms to assess risk factors, calculate probabilities, and forecast patient outcomes. Predictive modeling tools decrease hypoglycemic events and enhance patient care. The machine learning model, XGBoost, was selected for this project due to its accuracy and adaptability into Sanford’s EHR system. The recommendation is for nurses and other clinical staff to be trained and evaluated on the usability of this model.

Included in

Nursing Commons

Share

COinS
 
Apr 3rd, 11:00 AM Apr 3rd, 1:00 PM

Hypoglycemic Predictive Modeling Tool

Introduction: This evidence-based practice (EBP) project aims to improve patient safety and outcomes through the implementation of a predictive modeling tool (XGBoost) to predict and prevent hypoglycemic events in hospitalized adults at Sanford Health. Hypoglycemia continues to be a major safety concern, and early prediction can prevent complications

Methods: The project involved a literature review of articles to identify and recommend a hypoglycemic predictive modeling tool for Sanford Health. Included articles were published between 2019 and 2024 and selected through keywords like inpatients, hypoglycemia, glucose prediction, and predictive modeling. Searches across databases, including PubMed, JAMA, JIML, and UpToDate, initially yielded 18 articles, of which only 10 met criteria for this project’s focus on inpatient hypoglycemia.

Results

The review highlighted that inpatient hypoglycemia results from multiple complex factors. Additionally, the implementation of predictive tools can effectively analyze patient data to identify those at high risk. These models use algorithms to assess risk factors, calculate probabilities, and forecast patient outcomes. Predictive modeling tools decrease hypoglycemic events and enhance patient care. The machine learning model, XGBoost, was selected for this project due to its accuracy and adaptability into Sanford’s EHR system. The recommendation is for nurses and other clinical staff to be trained and evaluated on the usability of this model.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.