Patent US6512936B1 successfully refreshed from Google Patents.
US6512936B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Multi-tier method of classifying sample spectra for non-invasive blood analyte prediction
Assignee: GLT Acquisition Corp
•
Filing: 2000-09-18
•
Granted: 2003-01-28
•
Expires: 2020-09-18
Abstract
Abstract A method of multi-tier classification and calibration in noninvasive blood analyte prediction minimizes prediction error by limiting co-varying spectral interferents. Tissue samples are categorized based on subject demographic and instrumental skin measurements, including in vivo near-IR spectral measurements. A multi-tier intelligent pattern classification sequence organizes spectral data into clusters having a high degree of internal consistency in tissue properties. In each tier, categories are successively refined using subject demographics, spectral measurement information and other device measurements suitable for developing tissue classifications. The multi-tier classification approach to calibration utilizes multivariate statistical arguments and multi-tiered classification using spectral features. Variables used in the multi-tiered classification can be skin surface hydration, skin surface temperature, tissue volume hydration, and an assessment of relative optical thickness of the dermis by the near-IR fat band. All tissue parameters are evaluated using the NIR spectrum signal along key wavelength segments.
Inventors
- 👤 Stephen L. Monfre
- 👤 Thomas B. Blank
- 👤 Timothy L. Ruchti
- 👤 Suresh Thennadil
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-24 09:41
CPC Classifications
A; A61; A61B; A61B5/00; A61B5/145; A61B5/14532; A61B5/1455; A61B5/1495; A61B5/72; A61B5/7235; A61B5/7264; G; G01; G01N; G01N21/00; G01N21/17; G01N21/25; G01N21/27; G01N21/274; G01N21/31; G01N21/35; G01N21/359; G01N21/47; G01N21/4785; G01N21/49; G06; G06F; G06F18/00; G06F18/20; G06F18/21; A61B2560/00; A61B2560/02; A61B2560/0223; A61B2560/0228; A61B2560/0233; A61B5/103; A61B5/107; A61B5/1075; G16; G16H; G16H50/00; G16H50/20; Y; Y10; Y10S; Y10S128/00; Y10S128/92
Claims Analysis
Total Claims: 46
Claim 1
Independent Claim
92 words
A multi-tier pattern classification method for estimating a level of a target blood analyte comprising the steps of: providing a measured tissue absorbance spectrum from a subject; initially, classifying said measured spectrum into previously defined classes based on a priori information pertaining to said subject; further classifying said measured spectrum into previously defined classes based on at least one instrumental measurement at a tissue measurement site at which an optical sample was taken for said tissue absorbance spectrum; and extracting at least one feature from said measured spectrum for still further classification.
Claim 2
Dependent Claim
92 words
A multi-tier pattern classification method for estimating a level of a target blood analyte comprising the steps of: providing a measured tissue absorbance spectrum from a subject; initially, classifying said measured spectrum into previously defined classes based on a priori information pertaining to said subject; further classifying said measured spectrum into previously defined classes based on at least one instrumental measurement at a tissue measurement site at which an optical sample was taken for said tissue absorbance spectrum; and extracting at least one feature from said measured spectrum for still further classification.
Claim 3
Dependent Claim
51 words
The pattern classification method of claim 1 , wherein said initial classification step comprises the steps of: in a first tier, classifying said measured spectrum into previously defined classes based on subject's age; and in a second tier, further classifying said measured spectrum into previously defined classes based on subject's sex.
Claim 4
Dependent Claim
67 words
The pattern classification method of claim 1 , wherein said further classification step further comprises the steps of; in a third tier, further classifying said measured spectrum into previously defined classes based on an estimation of stratum corneum hydration at said tissue measurement site; and in a fourth tier, further classifying said measured spectrum into previously defined classes based on skin temperature at said tissue measurement site.
Claim 5
Dependent Claim
27 words
The pattern classification method of claim 3 , wherein said stratum corneum hydration estimate is based on a measurement of ambient humidity at said tissue measurement site.
Claim 6
Dependent Claim
66 words
The pattern classification method of claim 1 , wherein said feature extraction step comprises any mathematical transformation that enhances a quality or aspect of sample measurement for interpretation to represent concisely structural properties and physiological state of a tissue measurement site, wherein a resulting set of features is used to classify a subject and determine a calibration model that is most useful for blood analyte prediction.
Claim 7
Dependent Claim
118 words
The pattern classification method of claim 5 , wherein said features are represented in a vector, zεR M that is determined from a preprocessed measurement through: z=f (λ, x ) where f(•): R N →R M is a mapping from a measurement space to a feature space, wherein decomposing f(•) yields specific transformations, f i (•):R N →R M i for determining a specific feature, wherein the dimension M i , indicates whether an i th feature is a scalar or a vector and an aggregation of all features is the vector z, and wherein a feature exhibits a certain structure indicative of an underlying physical phenomenon when said feature is represented as a vector or a pattern.
Claim 8
Dependent Claim
56 words
The pattern classification method of claim 6 , wherein individual features are divided into two categories comprising: abstract features that do not necessarily have a specific interpretation related to a physical system; and simple features that are derived from an a priori understanding of a sample and that can be related directly to a physical phenomenon.
Claim 9
Dependent Claim
68 words
The pattern classification method of claim 7 , wherein said simple features can be calculated from NIR spectral absorbance measurements, said simple features including any of: thickness of adipose tissue; hematocrit level; tissue hydration; magnitude of protein absorbance; scattering properties of said tissue; skin thickness; temperature related effects; age related effects; spectral characteristics; pathlength estimates; volume fraction of blood in tissue; and spectral characteristics related to environmental influences.
Claim 10
Dependent Claim
26 words
The pattern classification method of claim 1 , further comprising the step of: employing spectral decomposition to determine features related to a known spectral absorbance pattern.
Claim 11
Dependent Claim
54 words
The pattern classification method of claim 1 , further comprising the step of: employing factor-based methods to build a model capable of representing variation in a measured absorbance related to a demographic variable; wherein projection of a measured absorption onto said model constitutes a feature that represents spectral variation related to said demographic variable.
Claim 12
Dependent Claim
46 words
The pattern classification method of claim 1 , wherein said feature extraction step determines at least one calibration model that is most appropriate for measurement; wherein a subject is assigned to one of many predefined classes for which a calibration model has been developed and tested.
Claim 13
Dependent Claim
26 words
The pattern classification method of claim 1 , further comprising the steps of; measuring the similarity of a feature to predefined classes; and assigning class membership.
Claim 14
Dependent Claim
23 words
The pattern classification method of claim 12 , wherein said assigning step uses mutually exclusive classes and assigns each measurement to one class.
Claim 15
Dependent Claim
41 words
The pattern classification method of claim 12 , wherein said assigning step uses a fuzzy classification that allows membership in more than one class simultaneously and provides a number between zero and one indicating a degree of membership in each class.
Claim 16
Dependent Claim
22 words
The pattern classification method of claim 1 , further comprising the step of: assigning measurements in an exploratory data set to classes.
Claim 17
Dependent Claim
27 words
The pattern classification method of claim 15 , further comprising the step of; using measurements and class assignments to determine a mapping from features to class assignments.
Claim 18
Dependent Claim
138 words
The pattern classification method of claim 16 , further comprising the steps of: defining classes from said features in a supervised manner, wherein each set of features is divided into two or more regions, and wherein classes are defined by combination of feature divisions; performing a cluster analysis on the spectral data to determine groups of said defined classes that can be combined, wherein the final number of class definitions is significantly reduced; designing a classifier subsequent to class definition through supervised pattern recognition by determining an optimal mapping or transformation from the feature space to a class estimate that minimizes the number of misclassifications; and creating a model based on class definitions that transforms a measured set of features to an estimated classification, wherein said class definitions are optimized to satisfy the specifications of the measurement system.
Claim 19
Dependent Claim
25 words
The pattern classification method of claim 17 , wherein said optimal mapping utilizes any of linear discriminant analysis, SIMCA, k nearest-neighbor, and artificial neural networks.
Claim 20
Dependent Claim
55 words
The pattern classification method of claim 18 , wherein a classification function maps said feature to a class c, according to c=f ( z ), where c is an integer on an interval [1, P], where P equals the number of classes, and wherein said class is used to select or adapt a calibration model.
Claim 21
Dependent Claim
69 words
The pattern classification method of claim 19 , further comprising the step of: passing said classification to a nonlinear model that provides a blood analyte prediction based on said classification and spectral measurement, wherein said blood analyte prediction for a measurement x is given by: ŷ=g ( c,x ), where g(•) is a nonlinear calibration model that maps x and c to an estimate of blood analyte concentration, y.
Claim 22
Dependent Claim
50 words
The pattern classification method of claim 20 , wherein a different calibration is realized for each class and wherein an estimate of blood analyte concentration for a measurement is given by: ŷ=g k ( x ), where g k (•) is a calibration model associated with the k th class.
Claim 23
Dependent Claim
90 words
The pattern classification method of claim 17 , wherein a membership function maps said feature space into an interval [0,1] for each class, wherein membership is defined by a continuum of grades, and wherein a mapping from feature space to a vector of class memberships is given by: c k =f k ( z ), where k=1,2, . . . P,f k (•) is the membership function of the k th class, c k ε[0,1] for all k and the vector cεR P is the set of all class memberships.
Claim 24
Dependent Claim
27 words
The pattern classification method of claim 22 , further comprising the step of predicting a blood analyte by application of a calibration model to a preprocessed measurement.
Claim 25
Dependent Claim
25 words
The pattern classification method of claim 23 , wherein said calibration model comprises any of nonlinear regression, nonlinear partial least squares, and artificial neural networks.
Claim 26
Dependent Claim
47 words
The pattern classification method of claim 24 , wherein the calibration model is passed a vector of class memberships, where a vector, c, is used to determine an adaptation of said calibration model suitable for blood analyte prediction or an optimal combination of several blood analyte predictions.
Claim 27
Dependent Claim
57 words
The pattern classification method of claim 25 , wherein a membership vector and preprocessed absorbance spectrum are both used by the calibration model for blood analyte prediction where the calculation is given by: ÿ=g ( c,x ), where g(•) is a nonlinear mapping determined through any of nonlinear regression, nonlinear partial least squares, and artificial neural networks.
Claim 28
Dependent Claim
38 words
The pattern classification method of claim 26 , wherein separate calibrations are used for each class; and wherein each calibration is generated using all measurements in a calibration set by exploiting a membership vector assigned to each measurement.
Claim 29
Dependent Claim
29 words
The pattern classification method of claim 27 , wherein said membership vector is used to determine an optimal combination of p blood analyte predictions from all classes through defuzzification.
Claim 30
Dependent Claim
22 words
The pattern classification method of claim 28 , wherein each of the p calibration models is developed using an entire calibration set.
Claim 31
Dependent Claim
56 words
The pattern classification method of claim 29 , wherein calibration measurements are weighted by their respective membership in a k th class when a k th calibration model is calculated, where weighted least squares is applied to calculated regression coefficients in a linear case, and wherein a covariance matrix is used in a factor-based methods case.
Claim 32
Dependent Claim
83 words
The pattern classification method of claim 30 , wherein said defuzzification is a mapping from a vector of blood analyte predictions and a vector of class memberships to a single analyte prediction, wherein said defuzzifier can be denoted as a transformation such that: ŷ=d ( c,└y 1 y 2 y 3 . . . y p ┘), where d(•) is the defuzzification function, c is a class membership vector and y k is a blood analyte prediction of a k th calibration model.
Claim 33
Dependent Claim
53 words
A pattern classification method for estimating a level of a target blood analyte comprising the steps of: providing a measured tissue absorbance spectrum from a subject; in at least one tier, classifying said measured spectrum into previously defined classes; and extracting at least one feature from said measured spectrum for still further classification.
Claim 34
Dependent Claim
53 words
A pattern classification method for estimating a level of a target blood analyte comprising the steps of: providing a measured tissue absorbance spectrum from a subject; in at least one tier, classifying said measured spectrum into previously defined classes; and extracting at least one feature from said measured spectrum for still further classification.
Claim 35
Dependent Claim
21 words
The pattern classification method of claim 32 , wherein said classifying step is based on any of: abstract and simple features.
Claim 36
Dependent Claim
32 words
The pattern classification method of claim 32 , further comprising the step of mapping said measured spectrum to an estimate of said analyte based on either a linear or a nonlinear model.
Claim 37
Dependent Claim
43 words
The pattern classification method of claim 32 , wherein said classifying step is based on any of: a priori information; and at least one instrumental measurement at a tissue measurement site at which an optical sample was taken for said tissue absorbance spectrum.
Claim 38
Dependent Claim
15 words
The pattern classification method of claim 32 , wherein said classifying step comprises multiple tiers.
Claim 39
Dependent Claim
81 words
The pattern classification method of claim 36 , wherein said classifying step comprises any of the steps of: classifying said measured spectrum into previously defined classes based on subject's age; classifying said measured spectrum into previously defined classes based on subject's sex; classifying said measured spectrum into previously defined classes based on an estimation of stratum corneum hydration at said tissue measurement site; and classifying said measured spectrum into previously defined classes based on skin temperature at said tissue measurement site.
Claim 40
Dependent Claim
67 words
A pattern classification method for estimating a level of a target blood analyte comprising the steps of: providing a measured tissue absorbance spectrum from a subject; in at least one tier, classifying said measured spectrum into previously defined classes; extracting at least one feature from said measured spectrum for still further classification; and estimating said blood analyte through application of a calibration model to said measured spectrum.
Claim 41
Dependent Claim
67 words
A pattern classification method for estimating a level of a target blood analyte comprising the steps of: providing a measured tissue absorbance spectrum from a subject; in at least one tier, classifying said measured spectrum into previously defined classes; extracting at least one feature from said measured spectrum for still further classification; and estimating said blood analyte through application of a calibration model to said measured spectrum.
Claim 42
Dependent Claim
21 words
The pattern classification method of claim 38 , wherein said classifying step is based on any of: abstract and simple features.
Claim 43
Dependent Claim
16 words
The pattern classification method of claim 38 , wherein said model is either linear or nonlinear.
Claim 44
Dependent Claim
43 words
The pattern classification method of claim 38 , wherein said classifying step is based on any of: a priori information; and at least one instrumental measurement at a tissue measurement site at which an optical sample was taken for said tissue absorbance spectrum.
Claim 45
Dependent Claim
15 words
The pattern classification method of claim 38 , wherein said classifying step comprises multiple tiers.
Claim 46
Dependent Claim
81 words
The pattern classification method of claim 42 , wherein said classifying step comprises any of the steps of: classifying said measured spectrum into previously defined classes based on subject's age; classifying said measured spectrum into previously defined classes based on subject's sex; classifying said measured spectrum into previously defined classes based on an estimation of stratum corneum hydration at said tissue measurement site; and classifying said measured spectrum into previously defined classes based on skin temperature at said tissue measurement site.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2006-01-27 | 2006-07-29 | 2007-01-28 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2010-01-27 | 2010-07-29 | 2011-01-28 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2014-01-27 | 2014-07-29 | 2015-01-28 | $7700.00 | Window Closed / Lapsed |