Abstract
We evaluated a neural network model for prediction of glucose in critically ill trauma and post-operative cardiothoracic surgical patients. A prospective, feasibility trial evaluating a continuous glucose-monitoring device was performed. After institutional review board approval, clinical data from all consenting surgical intensive care unit patients were converted to an electronic format using novel software. This data was utilized to develop and train a neural network model for real-time prediction of serum glucose concentration implementing a prediction horizon of 75 minutes. Glycemic data from 19 patients were used to “train” the neural network model. Subsequent real-time simulated testing was performed in 5 patients to whom the neural network model was naive. Performance of the model was evaluated by calculating the mean absolute difference percent (MAD%), Clarke Error Grid Analysis, and calculation of the percent of hypoglycemic (≤70 mg/dL), normoglycemic (>70 and <150 mg/dL), and hyperglycemic (≥150 mg/dL) values accurately predicted by the model; 9,405 data points were analyzed. The models successfully predicted trends in glucose in the 5 test patients. Clark Error Grid Analysis indicated that 100.0% of predictions were clinically acceptable with 87.3% and 12.7% of predicted values falling within regions A and B of the error grid respectively. Overall model error (MAD%) was 9.0% with respect to actual continuous glucose modeling data. Our model successfully predicted 96.7% and 53.6% of the normo- and hyperglycemic values respectively. No hypoglycemic events occurred in these patients. Use of neural network models for real-time prediction of glucose in the surgical intensive care unit setting offers healthcare providers potentially useful information which could facilitate optimization of glycemic control, patient safety, and improved care. Similar models can be implemented across a wider scale of biomedical variables to offer real-time optimization, training, and adaptation that increase predictive accuracy and performance of therapies.
Highlights
Severe traumatic injury represents a significant injury burden for the human body
The objective of this study was to evaluate the feasibility of utilizing a neural network model (NNM) for glycemic predictions across a broad range of critically ill surgical patients
Sampling of glucose concentrations via point of care (POC) measurement provides a means to glycemic control, hypoglycemia or hyperglycemia can occur between glucose measurement and correction
Summary
Previous research clearly associates significant physiologic stress and acute hyperglycemic spikes, with elevated glucose levels serving as a form of ‘‘physiologic barometer’’ [1] It is not surprising, that acute hyperglycemia is present in 25% or more of severely injured patients [2]. Active glycemic management aimed at lowering glucose levels after severe trauma has been associated with a reduction in mortality, length of time on ventilators, incidence of infection, and length of stays in the intensive care unit and hospital. This goal can be elusive in trauma patients that require multiple critical care therapies [4]. In addition to maintaining serum glucoses within the relatively narrow therapeutic window described above, it is important to note that glycemic variability plays an important role as a predictor of survival in critically ill surgical patients, with glycemic variability among non-survivors being twice the variability of survivors [1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
