Tailoring Medication to Individual Characteristics

• US 20090132460A1
• Filed: 11/20/2008
• Published: 05/21/2009
• Est. Priority Date: 11/20/2007
• Status: Active Grant

• Current Assignee: George Mason Intellectual Properties, Inc.
• Original Assignee: George Mason Intellectual Properties, Inc.
• Inventors: Alemi, Farrokh
• Granted Patent: US 8,145,583 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• 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
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Disclosed is a medical outcome prediction tool that predicts an individual patient'"'"'s medical outcomes by identifying patients having a same disease; selecting a set of characteristics unique to an individual; determining the similarities between the individual and other cases; and calculating the expected outcome for the individual that is proportional to a weighted sum of outcomes of similar cases. The similarities can be determined by calculating the number of matches between the individual and cases over the set of characteristics, and using that result to determine a similarity score.

Claims

1. A medical outcome prediction tool for predicting an individual patient'"'"'s medical outcomes, the medical outcome prediction tool implementing a method comprising:

a. identifying patients having a same disease;

b. selecting a set of characteristics unique to an individual;

c. determining the similarities between the individual and other cases by;

i. calculating the number of matches between the individual and the cases over the set of characteristics; and

ii. using the result of the calculated matches to determine a similarity score; and

d. calculating the expected outcome for the individual that is proportional to a weighted sum of outcomes of similar the cases.

2. The medical outcome prediction tool according to claim 1, further including calculating outcomes from the cases that are compliant with medication.

3. The medical outcome prediction tool according to claim 1, wherein the number of matches between the individual and the cases over the set of characteristics are calculated by:

a. using a standardized and rounded scale (SRS) value, wherein the SRS value is the difference of an observed value of at least one of the characteristics and an average of at least one of the characteristics, and the difference being;

i. divided by a standard deviation of at least one of the characteristics; and

ii. rounded; and

wherein the individual and the cases have a matching characteristic if both the individual and the cases have the same the SRS value; and

b. using the result of the calculated matches to determine a similarity score, wherein the similarity score comprises;

dividing the number of the characteristics matched between the individual and the cases by the sum of the “

number of the characteristics matched between the individual and the cases”

plus a weighted sum of number of nonmatched the characteristics, wherein the weighted sum comprises;

i. a number of the characteristics in the individual but not in the cases; and

ii. a number of the characteristics in the cases but not in the individual.

4. The medical outcome prediction tool according to claim 1, wherein the expected outcome is an observed event for the cases and is calculated by:

a. summing the product of the similarity score and the outcome; and

b. dividing the “

summing the product”

by the sum of the similarity score.

5. A method for predicting an individual patient'"'"'s medical outcomes, the method comprising:

a. identifying patients having a same disease;

b. selecting a set of characteristics unique to an individual;

c. determining the similarities between the individual and other cases by;

i. calculating the number of matches between the individual and the cases over the set of characteristics; and

ii. using the result of the calculated matches to determine a similarity score; and

d. calculating the expected outcome for the individual that is proportional to a weighted sum of outcomes of similar the cases.

6. The method according to claim 5, further including calculating outcomes from the cases that are compliant with medication.

7. The method according to claim 5, wherein the number of matches between the individual and the cases over the set of characteristics is calculated by:

a. using a standardized and rounded scale (SRS) value, wherein the SRS value is the difference of an observed value of at least one of the characteristics and an average of at least one of the characteristics, and the difference being;

i. divided by a standard deviation of at least one of the characteristics; and

ii. rounded; and

wherein the individual and the cases have a matching characteristic if both the individual and the cases have the same the SRS value; and

b. using the result of the calculated matches to determine a similarity score, wherein the similarity score comprises;

dividing the number of the characteristics matched between the individual and the cases by the sum of the “

number of the characteristics matched between the individual and the cases”

plus a weighted sum of number of nonmatched the characteristics, wherein the weighted sum comprises;

i. a number of the characteristics in the individual but not in the cases; and

ii. a number of the characteristics in the cases but not in the individual.

8. The method according to claim 5, wherein the expected outcome is an observed event for the cases and is calculated by:

a. summing the product of the similarity score and the outcome; and

b. dividing the “

summing the product”

by the sum of the similarity score.

9. A system for predicting an individual patient'"'"'s medical outcomes, the system comprising:

a. a patient-disease identifier, configured for identifying patients having a same disease;

b. a characteristics identifier, configured for selecting a set of characteristics unique to an individual;

c. a similarities determiner, configured for determining the similarities between the individual and other cases by;

i. a matcher, configured for calculating the number of matches between the individual and the cases over the set of characteristics; and

ii. a similarity scorer, configured for determining a similarity score by using the result of the calculated matches; and

d. an expected outcome generator, configured for calculating the expected outcome for the individual that is proportional to a weighted sum of outcomes of similar the cases.

10. The system according to claim 9, further including an outcome calculator, configured for calculating outcomes from the cases that are compliant with medication.

11. The system according to claim 9, wherein the matcher uses a standardized and rounded scale (SRS) value to calculate the number of matches between the individual and the cases over the set of characteristics, wherein the SRS value is the difference of an observed value of at least one of the characteristics and an average of at least one of the characteristics, and the difference being:

a. divided by a standard deviation of at least one of the characteristics; and

b. rounded; and

wherein the individual and the cases have a matching characteristic if both the individual and the cases have the same the SRS value.

12. The system according to claim 9, wherein the similarity score is determined by:

dividing the number of the characteristics matched between the individual and the cases by the sum of the “

number of the characteristics matched between the individual and the cases”

plus a weighted sum of number of nonmatched the characteristics, wherein the weighted sum comprises;

a. a number of the characteristics in the individual but not in the cases; and

b. a number of the characteristics in the cases but not in the individual.

13. The system according to claim 9, wherein the expected outcome is an observed event for the cases and is determined by:

a. summing the product of the similarity score and the outcome; and

b. dividing the “

summing the product”

by the sum of the similarity score.