Development of a neural network model for predicting glucose levels in a surgical critical care setting

Scott M Pappada, Marilyn J Borst, Brent D Cameron, Raymond E Bourey, Jason D Lather, Desmond Shipp, Antonio Chiricolo, Thomas J Papadimos, Scott M Pappada, Marilyn J Borst, Brent D Cameron, Raymond E Bourey, Jason D Lather, Desmond Shipp, Antonio Chiricolo, Thomas J Papadimos

Abstract

Development of neural network models for the prediction of glucose levels in critically ill patients through the application of continuous glucose monitoring may provide enhanced patient outcomes. Here we demonstrate the utilization of a predictive model in real-time bedside monitoring. Such modeling may provide intelligent/directed therapy recommendations, guidance, and ultimately automation, in the near future as a means of providing optimal patient safety and care in the provision of insulin drips to prevent hyperglycemia and hypoglycemia.

Figures

Figure 1
Figure 1
Neural network architecture and data flow.
Figure 2
Figure 2
Real-time predictions generated using patient specific model. conc. = concentration; mg = milligrams; dl = deciliter.
Figure 3
Figure 3
Real-time predictions generated using general model. conc. = concentration; mg = milligrams; dl = deciliter.
Figure 4
Figure 4
Clark error grid of predictions generated by patient specific model. mg = milligrams; dl = deciliter.
Figure 5
Figure 5
Clark error grid of predictions by general model. mg = milligrams; dl = deciliter.

References

    1. Sung J, Bochicchio GV, Joshi M. Admission hyperglycemia is predictive of outcome in critically ill trauma patients. J Trauma. 2005;59:80–83. doi: 10.1097/01.TA.0000171452.96585.84.
    1. Bochicchio GV, Sung J, Joshi M. Persistent hyperglycemia is predictive of outcome in critically ill trauma patients. J Trauma. 2005;58:921–924. doi: 10.1097/01.TA.0000162141.26392.07.
    1. Collier B, Diaz J Jr, Forbes R. The impact of a normoglycemic management protocol on clinical outcomes in the trauma intensive care unit. Parenter Enteral Nutr. 2005;29:353–358. doi: 10.1177/0148607105029005353.
    1. Laird AM, Miller PR, Preston R, Kilgo PD, Chang MC. Relationship of early hyperglycemia to mortality in trauma patients. J Trauma. 2004;56:1058–1062. doi: 10.1097/01.TA.0000123267.39011.9F.
    1. Yendamuri S, Fulda GJ, Tinkoff GA. Admission hyperglycemia as a prognostic indicator in trauma. J Trauma. 2003;55:33–38. doi: 10.1097/01.TA.0000074434.39928.72.
    1. Jessen M. Glucose control during cardiac surgery: how sweet it is. J Thorac Cardiovasc Surg. 2003;125:985–987. doi: 10.1067/mtc.2003.454.
    1. Jones KW, Cain AS, Mitchel JH, Millar RC, Rimmasch HL, French TK, Abbate SL, Roberts CA, Stenson SR, Marshall D, Lappe DL. Hyperglycemia predicts mortality after CABG: postoperative hyperglycemia predicts dramatic increases in mortality after coronary artery bypass grafting. J Diabetes Complications. 2008;22:365–370. doi: 10.1016/j.jdiacomp.2007.05.006.
    1. Doenst T, Wijeysundera D, Karkouti K, Zechner C, Magnant M, Rao V, Borger MA. Hyperglycemia during cardiopulmonary bypass is an independent risk factor for mortality in patients undergoing cardiovascular surgery. J Thorac Cardiovasc Surg. 2005;130:1144.e1–1144.e8. doi: 10.1016/j.jtcvs.2005.05.049.
    1. Kanji S, Buffie J, Hutton B. et al.Reliability of point-of-care testing for glucose measurement in critically ill adults. Critical Care Medicine. 2005;33:2778–2785. doi: 10.1097/01.CCM.0000189939.10881.60.
    1. Holzinger U, Warszawska J, Kitzberger R. et al.Real-Time Continuous Glucose Monitoring in Critically Ill Patients. Diabetes Care. 2010;33:467–472. doi: 10.2337/dc09-1352.
    1. Pappada SM, Cameron BD, Rosman PM. Development of a neural network for prediction of glucose in type I diabetes patients. J Diabetes Sci Technol. 2008;2:792–801.
    1. Clark WL, Gonder-Federick LA, Carter W, Pohl SL. Evaluating clinical accuracy of systems for self-monitoring of blood glucose. Diabetes Care. 1987;10:622–628. doi: 10.2337/diacare.10.5.622.
    1. Kovatchev BP, Gonder-Federick LA, Cox DJ, Clark WL. Evaluating the accuracy of continuous glucose-monitoring sensors. Diabetes Care. 2004;27:1922–1928. doi: 10.2337/diacare.27.8.1922.

Source: PubMed

Спонсоры и соавторы

Заболевания

Медикаментозные вмешательства

Подписаться