Download PDF
Methods Inf Med 2007; 46(05): 553-557
DOI: 10.1160/ME0411
Paper
Schattauer GmbH

A Study of Trained Clinicians’ Blood Glucose Predictions Based on Diaries of People with Type 1 Diabetes

J. Kildegaard
1   University of Aalborg, Department of Health Science and Technology, Aalborg, Denmark
,
J. Randløv
2   Novo Nordisk A /S, Department of Concept Research, Hillerød, Denmark
,
J. U. Poulsen
2   Novo Nordisk A /S, Department of Concept Research, Hillerød, Denmark
,
O. Hejlesen
1   University of Aalborg, Department of Health Science and Technology, Aalborg, Denmark
› Author Affiliations
Further Information

Publication History

Publication Date:
22 January 2018 (online)

    Permissions and Reprints

Summary

Objectives: How accurate can trained clinicians predict blood glucose concentrations? Good clinical treatment is, among other things, related to understanding the factors influencing blood glucose level. We analyze trained clinician’s prediction accuracy in comparison with selected computer-implemented prediction algorithms and models.

Methods: We have in this study included diaries of 12 people with type 1 diabetes. This test group consists of seven males and five females, ages 24 to 60, HbA1c 6.0 to 8.9 and a BMI between 20 and 28 kg/m2. Eight experienced clinicians tried to predict the blood glucose measurements based on minimum three days of diary history. Selected prediction algorithms and models were used for comparison. The reason we focus on type 1 diabetes is that it has the most critical insulin requirement, so accurate prediction can be more critical than for type 2.

Results: An accuracy of 28.5% and an error of 26.7% were found from predictions made by the clinicians. A physiological model and an artificial intelligence model showed higher accuracy of 32.2% and 34.2% in comparison with the clinicians (p < 0.05). A simple predictor algorithm based on the mean blood glucose history showed significant (p < 0.05) lower total root mean square error compared to predictions made by the clinicians.

Conclusion: To predict blood glucose level from diaries has shown to be profoundly difficult even for experienced clinicians in comparison with predictions from computer algorithms and models. This suggests that computer-based systems incorporating predicting algorithms and models are likely to contribute positively to the day-to-day treatment of people with diabetes.

Keywords

Forecasting - blood glucose - diabetes mellitus
 

  • References

  • 1 American DA. Standards of medical care in diabetes – 2006. Diabetes care 2006; 29 (Suppl. 01) S4-42.
    PubMedGoogle Scholar
  • 2 The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus. The Diabetes Control and Complications Trial Research Group. N Engl J Med 1993; 329 (14) 977-86.
    CrossrefPubMedGoogle Scholar
  • 3 Zierler K. Whole body glucose metabolism. Am J Physiol-Endocrinol Metab 1999; 39 (03) E409-E426.
    PubMedGoogle Scholar
  • 4 Cox DJ, Cryer PE, Gonder-Frederick L, Clarke WL, Antoun B. Perceived symptoms in the recognition of hypoglycemia. Diabetes care 1993; 16 (02) 519-27.
    CrossrefPubMedGoogle Scholar
  • 5 Albisser AM, Baidal D, Alejandro R, Ricordi C. Home blood glucose prediction: Clinical feasibility and validation in islet cell transplantation candidates. Diabetologia 2005; 48 (07) 1273-9.
    CrossrefPubMedGoogle Scholar
  • 6 Collste G, Shahsavar N, Gill H. A decision support system for diabetes care: Ethical aspects. Methods Inf Med 1999; 38 4-5 313-6.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 7 Hejlesen OK, Andreassen S, Hovorka R, Cavan DA. DIAS – the diabetes advisory system: An outline of the system and the evaluation results obtained so far. Comput Methods Programs Biomed 1997; 54 1-2 49-58.
    CrossrefPubMedGoogle Scholar
  • 8 Hejlesen OK, Andreassen S, Frandsen NE, Sorensen TB, Sando SH, Hovorka R. et al. Using a double blind controlled clinical trial to evaluate the function of a Diabetes Advisory System: A feasible approach?. Comput Methods Programs Biomed 1998; 56 (02) 165-73.
    CrossrefPubMedGoogle Scholar
  • 9 Hovorka R, Canonico V, Chassin LJ, Haueter U, Massi-Benedetti M, Orsini-Federici M. et al. Nonlinearmodel predictive control of glucose concentration in subjects with type 1 diabetes. Physiol Meas 2004; 25 (04) 905-20.
    CrossrefPubMedGoogle Scholar
  • 10 Lehmann ED, Deutsch T. Compartmental models for glycaemic prediction and decision-support in clinical diabetes care: Promise and reality. Comput Methods Programs Biomed 1998; 56 (02) 193-204.
    CrossrefPubMedGoogle Scholar
  • 11 Armengol E, Palaudaries A, Plaza E. Individual prognosis of diabetes long-term risks: a CBR approach. Methods Inf Med 2001; 40 (01) 46-51.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 12 Kildegaard J, Randløv J, Poulsen JU, Hejlesen OK. Method using clinicians to establish prediction baseline of blood glucose in people with type 1 diabetes. 2006. Scandinavian conference on Health Informatics 2006.. Ref Type: Generic.;
    Google Scholar
  • 13 Lehmann ED, Deutsch T. A physiological model of glucose-insulin interaction in type 1 diabetes mellitus. J Biomed Eng 1992; 14 (03) 235-42.
    CrossrefPubMedGoogle Scholar
  • 14 Mougiakakou SG, Nikita KS. Blood glucose profile prediction for type 1 diabetes patients using a hybrid approach. 1160-1161. 2002. EMBEC; 2002. RefType: Generic.
    Google Scholar
  • 15 Clarke WL, Cox D, Gonder-Frederick LA, Carter W, Pohl SL. Evaluating clinical accuracy of systems for self-monitoring of blood glucose. Diabetes care 1987; 10 (05) 622-8.
    CrossrefPubMedGoogle Scholar
  • 16 Meltzer LJ, Johnson SB, Pappachan S, Silverstein J. Blood glucose estimations in adolescents with type 1 diabetes: predictors of accuracy and error. J Pediatr Psychol 2003; 28 (03) 203-11.
    CrossrefPubMedGoogle Scholar
  • 17 Freund A, Johnson SB, Rosenbloom A, Alexander B, Hansen CA. Subjective symptoms, blood glucose estimation, and blood glucose concentrations in adolescents with diabetes. Diabetes care 1986; 9 (03) 236-43.
    CrossrefPubMedGoogle Scholar
  • 18 Ruggiero L, Kairys S, Fritz G, Wood M. Accuracy of blood glucose estimates in adolescents with diabetes mellitus. J Adolesc Health 1991; 12 (02) 101-6.
    CrossrefPubMedGoogle Scholar
  • 19 Alemzadeh R, Goldberg T, Fort P, Recker B, Lifshitz F. Reported dietary intakes of patients with insulin-dependent diabetes mellitus: limitations of dietaryrecall. Nutrition 1992; 8 (02) 87-93.
    PubMedGoogle Scholar
  • 20 Alto WA, Meyer D, Schneid J, Bryson P, Kindig J. Assuring the accuracy ofhome glucose monitoring. J Am Board Fam Pract 2002; 15 (01) 1-6.
    PubMedGoogle Scholar
  • 21 Goodyear LJ, Kahn BB. Exercise, glucose transport, and insulin sensitivity. Annu Rev Med 1998; 49: 235-61.
    CrossrefPubMedGoogle Scholar
  • 22 Guelfi KJ, Jones TW, Fournier PA. The decline in blood glucose levels is less with intermittent high-intensity compared with moderate exercise in individuals with type 1 diabetes. Diabetes care 2005; 28 (06) 1289-94.
    CrossrefPubMedGoogle Scholar
  • 23 Gonder-Frederick LA, Carter WR, Cox DJ, Clarke WL. Environmental stress and blood glucose change in insulin-dependent diabetes mellitus. Health Psychol 1990; 9 (05) 503-15.
    CrossrefPubMedGoogle Scholar