Method and apparatus for providing derived glucose information utilizing physiological and/or contextual parameters

Abstract

Various methods and apparatuses for measuring a state parameter of an individual using signals based on one or more sensors are disclosed. In one embodiment, a first set of signals is used in a first function to determine how a second set of signals is used in one or more second functions to predict the state parameter. In another embodiment, first and second functions are used where the state parameter or an indicator of the state parameter may be obtained from a relationship between the first function and the second function. The state parameter may, for example, include blood glucose levels, calories consumed or calories burned by the individual. Various methods for making such apparatuses are also disclosed.

Description

CROSS REFERENCE TO A RELATED APPLICATION[0001]This application is a continuation-in-part of co-pending U.S. patent application Ser. No. 10 / 682,293 filed Oct. 9, 2003, which claims the benefit of U.S. Provisional Application No. 60 / 417,163 filed on Oct. 9, 2002. This application also contains the benefit of U.S. Provisional Application No. 60 / 958,516 filed Jul. 6, 2007.FIELD OF THE INVENTION[0002]The present invention relates to methods and apparatuses for measuring a state parameter, in particular glucose, of an individual using signals based on one or more sensors. The present invention also relates to various methods for making such apparatuses.BACKGROUND OF THE INVENTION[0003]Type II diabetes is approaching “epidemic” incidence in the United States, driven in large part by a remarkable rise in obesity rates over the past 15 years. According to the American Diabetes Association (ADA), 18.2 million people in the United States, or 6.3% of the population have diabetes. From 1980 thro...

AI Technical Summary

Benefits of technology

[0010]The invention utilizes machine learning techniques to indirectly predict glucose levels using a noninvasive, multi-sensor, comfortable, continuously worn body-monitor. By combining signals from different sensors that themselves do not directly measure blood glucose signals but instead measures aspects of physiology that are related to blood glucose levels, the invention can obtain an accurate prediction of blood glucose levels without invasive measurements.

Problems solved by technology

These figures underestimate the effects of diabetes on society, as they do not include the decreased quality of life and resultant pain and suffering that accompany the disease, nor the economic value of unpaid caregivers or the medical expenses of people with undiagnosed diabetes.

The major burden of this disease to the patient and to health care resources is due to the long-term complications that are catastrophic to the eyes, kidneys, nerves, heart and limbs.

Glucose selfmonitoring has had a major impact on improving diabetes care in the last few decades, the disadvantages of this technology include the fact that the discomfort of obtaining a blood sample leads to non-compliance, that testing cannot be performed during sleeping, and that intermittent testing may miss episodes of hyper- and hypo-glycemia.

However, each of these techniques has significant obstacles and weaknesses.

For example, the major problem in measuring glucose concentration in interstitial fluid is that there is a “lag time”.

Furthermore, the attachment and measurement in interstitial fluid can also cause skin irritations and rashes.

For most implanted or semi-invasive techniques, bio-compatibility is the major problem; even subcutaneously implanted devices with prolonged contact will provoke an inflammatory response.

In general, direct measurement techniques all suffer from problems of invasiveness; indirect techniques suffer from the problem of accuracy.

Images