METHOD AND DEVICE FOR PREDICTING PHYSIOLOGICAL VALUES
The invention relates generally to methods, systems, and devices for measuring the concentration of target analytes present in a biological system using a series of measurements obtained from a monitoring system and a Mixtures of Experts (MOE) algorithm. In one embodiment, the present invention describes a method for measuring blood glucose in a subject.
1 - 24 . (canceled)
25 . One or more microprocessors for use in an analyte monitoring system for measuring an amount of concentration of analyte present in a biological system, said one or more microprocessors comprising programming to control:
providing two or more ranges of measurement values, wherein said measurement values are indicative of amounts or concentration of analyte present in the biological system:
identifying the range in which a selected measurement value falls, and
employing an algorithm for prediction of further measurement values wherein said algorithm is optimized for performance in the identified range.
26 . The one or more microprocessors of claim 25 , wherein a Mixtures of Experts algorithm is used to determine said selected measurement value and said Mixtures of Experts algorithm is trained using a global training set.
27 . The one more microprocessors of claim 25 , wherein said algorithm for prediction of further measurement values is a Mixtures of Experts algorithm and said Mixtures of Experts algorithm is trained using data from the identified range.
28 . The one or more microprocessors of claim 25 , wherein said or more microprocessors are further programmed to control operation of a sensing device that provides raw signal specifically related to analyte amount or concentration in the biological system.
29 . The one or more microprocessors of claim 28 , wherein said one or more microprocessors are further programmed to control correlating the raw signal with a measurement value indicative of analyte amount of concentration in the biological system.
30 . The one or more microprocessors of claim 29 , wherein for the Mixtures of Experts algorithm the individual experts have a linear form
An
=
∑
i
=
l
n
An
i
w
i
(
1
)
wherein (An) is an analyte of interest, n is the number of experts, An i is the analyte predicted by Expert i; and w i is a parameter, and the individual experts An i are further defined by the expression shown as Equation (2)
An
i
=
∑
j
=
l
m
a
ij
P
j
+
z
i
(
2
)
wherein, An i is the analyte predicted by Expert i; P j is one of m parameters, m is typically less then 100 ; a ij are coefficients; and z i is a constant; and further where the weighting value, w i , is defined by the formula shown as Equation (3)
w
i
=
d
i
[
∑
k
=
l
n
d
k
]
(
3
)
where e refers to the exponential function, d i is one of the d k , d i and d k are parameter sets analogous to Equation 2 used to determine the weight w i , the d k are given by Equation 4
d
k
=
∑
j
=
l
m
α
jk
P
j
+
ω
k
(
4
)
where a jk is coefficient, P j is one of m parameters, and where ω k is a constant.
31 . The one or more microprocessors of claim 30 , wherein the analyte is glucose.
32 . A method to measure an amount of concentration of analyte present in a biological system, the method comprising:
providing two or more ranges of measurement values, in which said measurement values are indicative of amounts or concentration of analyte present in the biological system;
identifying the range in which a selected measurement value falls; and
employing an algorithm to predict further measurement values in the identified range.
33 . The method of claim 32 , in which the algorithm comprises: for the Mixtures of Experts algorithm the individual experts have a linear form
An
=
∑
i
=
l
n
An
i
w
i
(
1
)
wherein (An) is an analyte of interest, n is the number of experts, An i is the analyte predicted by Expert i; and w i is a parameter, and the individual experts An i are further defined by the expression shown as Equation (2)
An
i
=
∑
j
=
l
m
a
ij
P
j
+
z
i
(
2
)
wherein, An i is the analyte predicted by Expert i; P j is one of m parameters, m is typically less then 100 ; a ij are coefficients; and z i is a constant; and further where the weighting value, w i , is defined by the formula shown as Equation (3)
w
i
=
d
i
[
∑
k
=
l
n
d
k
]
(
3
)
where e refers to the exponential function, d i is one of the d k , d i and d k are parameters sets analogous to Equation 2 used to determine the weight w i , the d k are given by Equation 4
d
k
=
∑
j
=
l
m
α
jk
P
j
+
ω
k
.
(
4
)
where a jk is coefficient, P j is one of m parameters, and where ω k is a constant.