An assessment of patient behavior over time-periods: a case study of managing type 2 diabetes through blood glucose readings and insulin doses

J Med Syst. 2012 Nov:36 Suppl 1:S65-80. doi: 10.1007/s10916-012-9894-3. Epub 2012 Oct 27.

Abstract

This paper focuses on assessing the behavior of a patient over time periods for managing type 2 Diabetes. In some cases, patients with type 2 diabetes not only behave differently from other patients, but the severity of a given health problem varies even for an individual patient. We focus on understanding how and when patients differ from other patients. In addition, we also look at the diversity that exists within an individual patient especially over time-periods throughout the day. Our aim is to identify such time intervals when a patient may need more targeted care. Thus, for type 2 Diabetes we identify which time-periods exhibit a mismatch in terms of the blood glucose readings and the insulin doses. For instance, if the blood glucose readings fluctuate and the insulin doses are fixed it may indicate a poor management of the insulin doses and therefore a poor management of Diabetes. Based on such findings a number of factors can be taken into consideration when drawing out a care plan for example diet, lifestyle, and type of treatment, among others. Our study uses a data mining approach, particularly clustering to study the measurements in blood glucose and doses of regular insulin for a selected number of patients. We look at their behavior on an overall days' basis, which we refer to as large-scale binning. Additionally, we study their behavior at specified time intervals throughout the day, which we refer to as small-scale binning. Our findings indicate that we are clearly able to see the trends in blood glucose readings as compared to the insulin doses for different patients indicating a well managed or a poorly managed plan.

MeSH terms

  • Behavior*
  • Blood Glucose Self-Monitoring / psychology
  • Blood Glucose Self-Monitoring / statistics & numerical data*
  • Cluster Analysis
  • Data Mining / methods
  • Diabetes Mellitus, Type 2 / blood
  • Diabetes Mellitus, Type 2 / drug therapy*
  • Diabetes Mellitus, Type 2 / psychology
  • Diet
  • Health Behavior
  • Humans
  • Insulin / administration & dosage*
  • Insulin / therapeutic use
  • Life Style
  • Motivation
  • Patient Compliance / statistics & numerical data
  • Time Factors

Substances

  • Insulin