Method and apparatus for chronic care treatment control with custom named-type factors and user estimation error correction

• US 8,185,412 B1
• Filed: 01/02/2009
• Issued: 05/22/2012
• Est. Priority Date: 03/28/2008
• Status: Active Grant

• Current Assignee: Mahesh Harpale
• Original Assignee: Mahesh Harpale
• Inventors: Harpale, Mahesh
• Primary Examiner(s): Cobanoglu, Dilek B
• Application Number:
  US12/319,175
• Time in Patent Office: 1,236 Days
• Field of Search: 702/19, 128/898
• US Class Current: 705/3
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/4842 Monitoring progression or stage of a disease
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 20/10 relating to drugs or medications, e.g. for ensuring correct administration to patients

Abstract

A method and apparatus to record and track patient'"'"'s estimation of arbitrary factor types, to analyze response errors utilizing discrete measurements, to isolate errors in various factor types and their response correlations, to enable patient in refining factor mix to reduce estimated outcome variations, and to improve patient estimation with corrections using a continuous feedback system. The input factors for the treatment in case of a Diabetic patient may be food intake, medication, activity, stress level etc, while the treatment outcome or response may be blood glucose level that the patient needs to keep within specific limits. Present invention enables a chronic care patient, such as a Diabetic patient, to make better and informed decisions about their treatment, reduce input factor estimation errors, reduce outcome parameter variations, and improve the patient well being by better treatment control.

Claims

1. A method for improving a chronic care treatment outcome, comprising the steps of:

(a) recording identification information for a plurality of users;

(b) recording for each of said users, a treatment outcome and, a plurality of arbitrary factors, where said arbitrary factors are relevant for each of said users and are correlated with said treatment outcome;

(c) recording for each of said users, a plurality of arbitrary types of said factors relevant for said user and recording for each said arbitrary type, an arbitrary name, a unit, and a correlation with said treatment outcome, where said correlation is as estimated by user;

(d) recording for each of said users, a plurality of arbitrary events impacting said treatment outcome and recording for each said arbitrary event, a plurality of said arbitrary types identified by said arbitrary type name and for each said arbitrary type, a relative strength as compared to said arbitrary type unit, where said relative strength is as estimated by user;

(e) computing for each of said users, a change estimate in said treatment outcome at any arbitrary time and computing an error in said outcome change estimate, where said outcome change estimate is due to said correlation of said arbitrary types relevant at said arbitrary time, and where said error in outcome change estimate is result of an error in change estimate by said arbitrary type when said outcome change estimate is compared to an observed change at said arbitrary time;

(f) computing for each of said arbitrary types for each of said users, an error in said correlation, where said correlation is as estimated by said user, and where said error attributable to said arbitrary type is isolated by correlating a plurality of said treatment estimation errors where said arbitrary type is relevant;

wherein the chronic care treatment may be a blood glucose control treatment for a Diabetic patient and the treatment outcome is a resulting acceptable value of blood glucose level for said patient;

wherein said user for the step of recording said identification information may be a patient, or a healthcare advisor, or an assistant, where said healthcare advisor, and said assistant may be permitted by said patient to access information about said patient, and may assist said patient in configuring, analyzing and recording said patient'"'"'s information;

wherein the step of recording a plurality of said factors includes recording for each factor a plurality of factor parameters, and for each said factor parameter a name, a unit, and a correlation with said treatment outcome, where said plurality of factor parameter may be correlated with said treatment outcome, and where said correlation may be as estimated by user, and wherein the step of computing said error in said correlation for said arbitrary type includes computing for each of said factor parameters of said arbitrary type, an error in said correlation of said factor parameter, where said error in said correlation of said factor parameter may be isolated by correlating a plurality of said treatment estimation errors where said arbitrary type may be relevant.

2. A method according to claim 1 wherein the step of recording of said correlation of said arbitrary type includes a confidence value, where said confidence value indicates estimated confidence of accuracy of said arbitrary type correlation, and where said confidence value is used to isolate said error in said correlation of said arbitrary type.

3. A method according to claim 1 wherein the step of recording of said correlation for each said arbitrary type includes recording of correlation at a plurality of discrete time intervals.

4. A method according to claim 1 comprising the step of:

recording for said user, a plurality of common types of said factors relevant for a general user population and recording for each said common type, a name, a unit, and a correlation with said treatment outcome, and wherein the step of recording for each said arbitrary event, includes a plurality of said common types identified by said common type name and for each said common type, a relative strength compared to said type unit.

5. A method according to claim 4 wherein the step of recording for each said arbitrary type includes a correlation to a plurality of said common types, where said correlation to a plurality of said common types is used to determine said correlation of said arbitrary type.

6. A method according to claim 4 wherein the step of recording of plurality of common types includes recording for each an identification of an entity, where said entity provides said recording of plurality of common types, and comprising the step of:

allowing said user to select said common type associated with said entity.

7. A method according to claim 6 wherein the step of recording of plurality of common types includes recording for each said common type, an identification of a brand associated with said common type and comprising the step of:

allowing said user to select common type associated with said brand.

8. A method according to claim 7 comprising the step of:

associating said common type identified with said brand with a unique code and identifying said common type in said arbitrary event by a means to recognize said unique code for said common type identified with said brand.

9. A method according to claim 1 comprising the step of:

recording said arbitrary event as a preset event for repetitive use and recording a time schedule for repetitive occurrence of plurality of said preset events.

10. A method according to claim 1 wherein the step of computing said error in said correlation includes computing an error in said relative strength of said arbitrary type, where said error attributable to said arbitrary type is isolated by correlating a plurality of said treatment estimation errors where said arbitrary type is relevant.

11. A method according to claim 1 comprising the step of:

recording a plurality of said estimation errors in said correlation and selecting most relevant of said plurality of said estimation errors to compute a correction in said user estimated correlation.

12. A method according to claim 11 comprising the step of:

allowing said user to selectively accept said error in said correlation.

13. A system for improving a chronic care treatment outcome comprising a non-transitory computer processor usable medium accessible comprising:

(a) a computer processor readable program embodied therein recording an identification information for a plurality of users;

(b) a computer processor readable program embodied therein recording for each of said users, a treatment outcome and, a plurality of arbitrary factors, where said arbitrary factors is relevant for each of said users and is correlated with said treatment outcome;

(c) a computer processor readable program embodied therein recording for each of said users, a plurality of arbitrary types of said factors relevant for said user and recording for each said arbitrary type, an arbitrary name, a unit, and a correlation with said treatment outcome, where said correlation is as estimated by user;

(d) a computer processor readable program embodied therein recording for each of said users, a plurality of arbitrary events impacting said treatment outcome and recording for each said arbitrary event, a plurality of said arbitrary types identified by said arbitrary type name and for each said arbitrary type, a relative strength as compared to said arbitrary type unit, where said relative strength is as estimated by user;

(e) a computer processor readable program embodied therein computing for each of said users, a change estimate in said treatment outcome at any arbitrary time and computing an error in said outcome change estimate, where said outcome change estimate is due to said correlation of said arbitrary types relevant at said arbitrary time, and where said error in outcome change estimate is result of an error in change estimate by said arbitrary type when said outcome change estimate is compared to an observed change at said arbitrary time; and

(f) a computer processor readable program embodied therein computing for each of said arbitrary types for each of said users, an error in said correlation, where said correlation is as estimated by said user, and where said error attributable to said arbitrary type is isolated by correlating a plurality of said treatment estimation errors where said arbitrary type is relevant.