Medical diagnosis derived from patient drug history data

• US 8,579,811 B2
• Filed: 09/19/2006
• Issued: 11/12/2013
• Est. Priority Date: 09/19/2006
• Status: Expired due to Fees

• Current Assignee: 3M Innovative Properties Company (3M Company)
• Original Assignee: 3M Innovative Properties Company (3M Company)
• Inventors: Eisenhandler, Jon, Averill, Richard F., Goldfield, Norbert I.
• Primary Examiner(s): Thomson, Bill
• Assistant Examiner(s): Archer, Marie
• Application Number:
  US11/532,919
• Publication Number:
  US 20080081955A1
• Time in Patent Office: 2,611 Days
• Field of Search: 600/300, 600/301, 128903-905, 128/920
• US Class Current: 600/300
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/72 Signal processing specially adapted for physiological signals or for diagnostic purposes character recognition, recognising digital ink, document-oriented image-based pattern recognition G06V30/00; recognition or understanding of postal images G06V30/424
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics
• CPC Class Codes: Y10S 707/99941 Database schema or data structure

Abstract

In general the invention is directed to systems, methods, and/or software modules which may analyze a patient'"'"'s drug history, and optionally other data, and derive a probable diagnosis for the patient based on rules.

Claims

1. A non-transitory computer-readable medium having computer-executable instructions operable to cause a computer to;

receive patient data indicative of a patient'"'"'s age and sex;

receive drug history data that identities drugs taken by the patient;

apply one or more drug diagnosis rules to the patient data and the drug history data, the drug diagnosis rules defining relationships between drug history data, the patient'"'"'s sex, the patient'"'"'s age, and a diagnosis; and

,

infer the diagnosis for the patient based on the application of the one or more drug diagnosis rules.

2. The computer-readable medium of claim 1, wherein the drug history data includes information additionally defining time periods in which a drug was taken or received by a patient.

3. The computer-readable medium of claim 2, wherein the drug diagnosis rule includes a span rule, which defines a period of time for which the patient must have been taking a drug for a diagnosis to apply.

4. The computer-readable medium of claim 3, wherein the span rule includes gap rules, which define gaps in the period of time for which a patient must have been taking a drug for a diagnosis to apply.

5. The computer-readable medium of claim 1, wherein the drug diagnosis rules include an age rule, which defines the age of the patient at or near the time a drug was taken in order for a diagnosis to apply.

6. The computer-readable medium of claim 1, wherein the drug diagnosis rules include a sex rule, which defines the sex of the patient at the time a drug was taken in order for a diagnosis to apply.

7. The computer-readable medium of claim 1, wherein assigning a diagnosis to the patient comprises:

receiving a diagnosis hierarchy defining a plurality of possible diagnoses, the hierarchy a function of either disease severity or cost of treatment, or some combination thereof;

assigning the diagnosis to the patient based on selecting the highest diagnosis in the hierarchy that is consistent with the drug diagnosis rules in instances where there exists more than one diagnosis that is consistent with the drug diagnosis rules.

8. The computer-readable medium of claim 1, wherein the drug history data identifies more than one drug taken by the patient, and wherein applying the drug diagnosis rules further comprises applying the drug diagnosis rules to the second drug taken by the patient.

9. The computer-readable medium of claim 1, further comprising:

based on the diagnosis at least in part, estimating future financial expenditures related to the patient.

10. The computer-readable medium of claim 1, further comprising, repeating the steps in claim 1 against data from a plurality of patients, each associated with corresponding drug history data, so as to provide a diagnosis for each of the plurality of patients;

and,

based on the diagnosis at least in part, determining drug utilization patterns for groupings of patients, the groupings of patients based on age, sex, or commonalities in drug usage or patterns of drug usage.

11. The computer-readable medium of claim 1, further comprising:

repeating the steps in claim 1 against data from a plurality of patients, each associated with corresponding drug history data, so as to provide as diagnosis for each of the plurality of patients; and

aggregating a plurality of patients with the same diagnosis and determining past costs associated with that aggregate group of patients.

12. A computer-implemented system for determining a diagnosis for a patient based on at least the patient'"'"'s drug history comprising:

a database module containing at least;

(1) the age and sex of the patient, and (2) the patient'"'"'s drug history, the drug history including information defining at least two drugs the patient had previously received, and (3) a set of rules which define relationships between age and sex, drug history, and a diagnosis;

a rules module, which applies rules from the database module against information indicative of the patient'"'"'s age and sex data and the patient'"'"'s drug history; and

,

a diagnosis assignment module, which assigns a probable medical diagnosis to the patient based on the rules module'"'"'s application of rules.

13. The system of claim 12, wherein the database module additionally contains a hierarchy of diseases, the hierarchy based on either, or some combination of, the severity of the disease or the anticipated cost of treating the disease.

14. The system of claim 13, wherein the diagnosis assignment module assigns the probable medical diagnosis based on the hierarchy of diseases, such that the most severe disease, or the disease with the highest anticipated cost of treatment, is selected when there is more than one possible diagnosis based on the application of the rules.

15. A computer-based system having a memory and a processor which estimates a patient'"'"'s future demand for healthcare services, comprising a software module running on a computer which analyzes a patient'"'"'s drug history, and based on this analysis inters a current diagnosis based on the patient'"'"'s drug history;

wherein the analysis done by the software modules comprises applying at least one rule which defines a pattern of drug usage associated with a disease; and

,

wherein the at least one rule is applied to the patient'"'"'s drug history based on a hierarchy of diseases, the hierarchy being a function, at least in part, of the severity of the disease to the patient'"'"'s health, and the hierarchy of diseases is applied such that if the application of the rules yields a plurality of possible diseases, the most severe disease is associated with the patient.

16. A computer-implemented method comprising:

receiving drug history data that identifies a plurality drugs taken by a patient;

applying one or more drug diagnosis rules to the drug history data, the drug diagnosis rules defining relationships between drug history data and a possible diagnosis for the patient;

determining a probable diagnosis for the patient based on the application of the one or more drug diagnosis rules; and

,

receiving data indicative of the patient'"'"'s sex, and wherein the drug diagnosis rules additionally include relationships between the sex of a patient, drug history, and the possible diagnosis.

17. The computer-implemented method of claim 16, further comprising:

receiving data indicative of the patient'"'"'s age, and wherein the drug diagnosis rules additionally include relationships between the age of a patient, drug history, and the possible diagnosis.

18. The computer-implemented method of claim 16, wherein determining a probable diagnosis additionally includes receiving a diagnosis hierarchy, the hierarchy a function of either diseases severity or cost of treatment, or some combination thereof, and where, if there are more than one possible diagnosis based on the application of the one or more drug diagnosis rules, selecting the diagnosis based on the hierarchy.

19. A computer-implemented method for inferring a patient'"'"'s current diagnosis from a data set, comprising:

receiving patient indicative of age and sex data;

receiving drug history data that identities at least one drug taken by the patient;

applying one or more drug diagnosis rules to the patient age and sex data and the drug history data, the drug diagnosis rules defining relationships between drug history data, patient age and sex data, and a diagnosis;

receiving diagnosis hierarchy data that defines which disease should be inferred in the event that the application of the one or more drug diagnosis rules results in more than one possible current diagnosis; and

,

inferring the current diagnosis for the patient based on the application of the one or more drug diagnosis rules, and the application of the diagnosis hierarchy.