Evaluation of a Model for Glycemic Prediction in Critically Ill Surgical Patients

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.

Continuous versus bolus tube feeds: Does the modality affect glycemic variability, tube feeding volume, caloric intake, or insulin utilization?

“…The initial increase and the subsequent peak in insulin utilization [ Figure 3 and 1 st –17 th epochs], followed by a decrease in insulin use [ Figure 3 and 18 th –34 th epochs] may be attributable to a number of factors such as corresponding changes in illness severity, fewer acute events (i.e., sepsis, hemorrhage),[ 20 29 ] and/or more closely adherent glucose protocol implementation by nursing. [ 36 39 ] Related to the latter two points, the current study provides no evidence that either BTF or CTF are associated with greater incidence of hypoglycemia (≤75 mg/dL, Table 1 ).…”

“…Further research in this area is warranted, and should include multi-variable assessment of factors related to both GV and physiologic stress. [ 20 29 36 ]…”

Implementation of a Dietitian‐Led Enteral Nutrition Support Clinic Results in Quality Improvement, Reduced Readmissions, and Cost Savings

“…Dietitian‐led, protocol‐driven care has been successfully attempted before in other contexts, 13 and numerous examples of protocol‐driven care by nonphysicians have been documented in both inpatient and outpatient settings 14 , 15 . Nutrition support teams in the inpatient setting have been demonstrated to improve outcomes, including lower infection rates, higher survival, higher caloric delivery, better glycemic control, and reduced monetary costs 16 – 18 . There is also precedence to support the incorporation of specialist enteral access skills into dietetic practice.…”

Burn Shock and Resuscitation: Many Priorities, One Goal

“…Insulin administration has been shown to improve muscle protein synthesis, normalize mitochondrial function, reduce oxidative stress, limit lean muscle mass loss, accelerate healing time, and improve long-term rehabilitation [176][177][178][179]. In addition to the normalization of serum glucose levels, the reduction in glycemic variability may be equally important [180,181]. Other beneficial effects of goal-directed insulin therapy have been identified, including potential reductions in mortality, infections, sepsis, acute kidney injury, multiple organ failure, days on a ventilator, and hospital length of stay [177,178,182].…”