Method and system for analyzing drug adverse effects

• US 7,542,961 B2
• Filed: 05/02/2001
• Issued: 06/02/2009
• Est. Priority Date: 05/02/2001
• Status: Active Grant

• Current Assignee: Druglogic Incorporated
• Original Assignee: Victor Gogolak
• Inventors: Gogolak, Victor
• Primary Examiner(s): Vincent; David R
• Assistant Examiner(s): BUSS, BENJAMIN J
• Application Number:
  US09/681,585
• Publication Number:
  US 20020165852A1
• Time in Patent Office: 2,953 Days
• Field of Search: 706/11, 706/45, 706/924, 706/62, 705/2, 705/3, 707/3, 707/1, 707 9- 10, 707/102, 707/104.1, 424/10.1, 717/1, 717/3, 717 9- 10, 717/102, 717/104.1
• US Class Current: 706/62
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G16C 20/30 Prediction of properties of chemical compounds, compositions or mixtures
• CPC Class Codes: G16C 20/70 Machine learning, data mining or chemometrics
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 70/40 relating to drugs, e.g. their side effects or intended usage
• CPC Class Codes: Y10S 706/924 Medical
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

The system of the present invention for assessing and analyzing the risks of adverse effects resulting from the use of at least one substance of interest, comprises a selector for identifying at least one substance of interest; a profiler for selecting from multiple profiles related to the safety of the at least one substance of interest, using at least one filter; at least one data mining engine; and an output device for displaying the analytic results from the data mining engine. Preferably, the at least one data mining engine is selected from (1) a proportional analysis engine to assess deviations in a set of the reactions to the drug of interest; (2) a comparator to measure the reactions to the drug of interest against a user-defined backdrop, and (3) a correlator to look for correlated signal characteristics in drug/reaction/demographic information; and an output device whereby a user can receive analytic results from the selector, the proportional analysis engine, the comparator, and the correlator.

Claims

1. A computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest, comprising:

a selector for identifying at least one substance of interest;

a profiler for selecting from multiple profiles related to safety of the at least one substance of interest, using at least one filter to determine at least one set of cases;

at least one data mining engine for processing the at least one set of cases determined and submitted by the at least one filter; and

an output device for displaying analytic results from the data mining engine,

wherein the substance of interest is assessed in combination with other drugs, foodstuffs, beverages, nutrients, vitamins, toxins, chemicals, hormones, and supplements;

wherein the at least one data mining engine comprises a correlator to look for correlated signal characteristics in at least one of drug information, reaction information and demographic information;

wherein the correlator is configured to maintain a consistent vocabulary by processing a vector comprising a plurality of categorical terms; and

wherein the plurality of categorical terms sent to the correlator are therapeutic categories.

2. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 1, wherein the at least one data mining engine also comprises a proportional analysis engine to assess deviations in a set of reactions to the at least one substance of interest.

3. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 1, wherein the at least one data mining engine also comprises a comparator to measure reactions to the at least one substance of interest against a user-defined backdrop.

4. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 1, wherein the data mining engine is at least two members of the group consisting of a proportional analysis engine, a comparator, and a correlator.

5. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 1, wherein the system permits assessment and analysis of risks of adverse effects resulting from use of at least one substance of interest in any of multiple dimensions of risk assessment and analysis.

6. A computer system for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest, comprising:

a selector for identifying at least one drug of interest;

a profiler for selecting from multiple profiles related to safety of the at least one drug of interest, using at least one filter to determine at least one set of cases;

at least one data mining engine for processing the at least one set of cases determined and submitted by the at least one filter; and

an output device for displaying analytic results from the data mining engine,

wherein the drug of interest is assessed in combination with other drugs, foodstuffs, beverages, nutrients, vitamins, toxins, chemicals, hormones, and supplements;

wherein the at least one data mining engine comprises a correlator to look for correlated signal characteristics in at least one of drug information, reaction information and demographic information;

wherein the correlator is configured to maintain a consistent vocabulary by processing a vector comprising a plurality of categorical terms; and

wherein the plurality of categorical terms sent to the correlator are therapeutic categories.

7. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 6, wherein the at least one data mining engine also comprises a proportional analysis engine to assess deviations in a set of the reactions to the drug of interest.

8. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 6, wherein the at least one data mining engine also comprises a comparator to measure reactions to the drug of interest against a user-defined backdrop.

9. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 6, wherein the data mining engine is at least two members of the group consisting of a proportional analysis engine, a comparator, and a correlator.

10. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 6, wherein the system permits assessment and analysis of risks of adverse effects resulting from use of at least one drug of interest in any of multiple dimensions of risk assessment and analysis.

11. The computer system of claim 6, wherein the proportional analysis further comprises comparing the drug of interest to a second drug of interest in a same therapeutic category for the drug of interest selected.

12. The computer system of claim 6, wherein the proportional analysis further comprises comparing the drug of interest to a second drug of interest in a second therapeutic category.

13. The computer system of claim 6, further comprising:

a Bayesian filtering, wherein the Bayesian filtering includes providing a statistical cut-off threshold to reduce the effect of drugs or reactions accounting for less than a certain percentage of cases of adverse drug events.

14. The computer system of claim 6, further comprising:

comparing clinical trial data, wherein the comparison includes comparing the potential and actual adverse effects of the drug of interest in a pre-market environment to that of the potential and actual adverse effects of the drug of interest in a post-market environment.

15. A computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest, comprising:

identifying the at least one substance of interest;

selecting a profile of the at least one substance of interest related to safety of the at least one substance of interest, using at least one filter to determine at least one set of cases;

analyzing risks of adverse effects resulting from use of the at least one substance of interest using at least one data mining engine for processing the at least one set of cases determined and submitted by the at least one filter, wherein the at least one data mining engine comprises a correlator to look for correlated signal characteristics in at least one of drug information, reaction information and demographic information;

maintaining a consistent vocabulary by using the correlator to process a vector comprising a plurality of categorical terms; and

displaying results from analyzing risks of adverse effects resulting from the use of the at least one substance of interest,

wherein the plurality of categorical terms sent to the correlator are therapeutic categories.

16. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 15, wherein the at least one data mining engine also comprises a proportional analysis engine to assess deviations in a set of the reactions to the at least one substance of interest.

17. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 15, wherein the at least one data mining engine also comprises a comparator to measure reactions to the at least one substance of interest against a user-defined backdrop.

18. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 15, wherein the data mining engine is at least two members of the group consisting of a proportional analysis engine, a comparator, and a correlator.

19. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 15, wherein the at least one substance of interest is assessed in combination with other drugs, foodstuffs, beverages, nutrients, vitamins, toxins, chemicals, hormones, and supplements.

20. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 15, wherein the method permits assessment and analysis of risks of adverse effects resulting from use of at least one substance of interest in any of multiple dimensions of risk assessment and analysis.

21. A computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest, comprising:

identifying the at least one drug of interest, as well any other drugs, nutrients, supplements, and other substances;

selecting a profile of the at least one drug of interest related to safety of the at least one drug of interest, using at least one filter to determine at least one set of cases;

analyzing risks of adverse effects resulting from use of the at least one drug of interest using at least one data mining engine for processing the at least one set of cases determined and submitted by the at least one filter, wherein the at least one data mining engine comprises a correlator to look for correlated signal characteristics in at least one of drug information, reaction information and demographic information;

maintaining a consistent vocabulary by using the correlator to process a vector comprising a plurality of categorical terms; and

displaying results from analyzing risks of adverse effects resulting from the use of the at least one drug of interest,

wherein the at least one drug of interest is assessed in combination with other drugs, foodstuffs, beverages, nutrients, vitamins, toxins, chemicals, hormones, and supplements; and

wherein the plurality of categorical terms sent to the correlator are therapeutic categories.

22. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 21, wherein the at least one data mining engine also comprises a proportional analysis engine to assess deviations in a set of the reactions to the at least one drug of interest.

23. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 21, wherein the at least one data mining engine also comprises a comparator to measure reactions to the at least one drug of interest against a user-defined backdrop.

24. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 21, wherein the data mining engine is at least two members of the group consisting of a proportional analysis engine, a comparator, and a correlator.

25. The computer-implemented method for assessing and analyzing risks of adverse effects resulting from use of at least one drug of interest according to claim 21, wherein the method permits assessment and analysis of risks of adverse effects resulting from use of at least one drug of interest in any of multiple dimensions of risk assessment and analysis.

26. A computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest, comprising:

a selector for identifying at least one substance of interest;

a profiler for selecting from multiple profiles related to safety of the at least one substance of interest, using at least one filter to determine at least one set of cases;

at least one data mining engine for processing the at least one set of cases determined and submitted by the at least one filter; and

an output device for displaying analytic results from the data mining engine,

wherein the substance of interest is assessed in combination with other drugs, foodstuffs, beverages, nutrients, vitamins, toxins, chemicals, hormones, and supplements,

wherein the assessment of the substance of interest includes comparing the potential and actual adverse effects of a substance of interest in a pre-market environment to that of the potential and actual adverse effects of a substance of interest in a post-market environment;

wherein the at least one data mining engine comprises a correlator to look for correlated signal characteristics in at least one of drug information, reaction information and demographic information;

wherein the correlator is configured to maintain a consistent vocabulary by processing a vector comprising a plurality of categorical terms; and

wherein the plurality of categorical terms sent to the correlator are therapeutic categories.

27. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 26,

wherein the substance of interest identified by the selector is a target drug;

wherein the target drug is profiled in relation to a one or more concomitant drugs;

wherein the profiler identifies one or more concomitant drug dimensions;

wherein the one or more concomitant drugs were prescribed in one or more cases where the target drug was also prescribed;

wherein the one or more prescriptions are configured to result in an adverse drug reaction report; and

wherein the adverse drug reaction is configured so as to be reported in an adverse effects reporting database.

28. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 27,

wherein the profiler is configured to label each of the one or more drugs as a suspect drug or a non-suspect drug;

wherein the profiler is configured to analyze a patient information, the patient information further comprising a plurality of categories for patients whose information is reported in an adverse drug effects reporting database;

wherein the plurality of categories analyzed includes a plurality of age groups, a male gender, a female gender, and a plurality of ages between 16 years old and 75 years old.

29. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 28,

wherein the display is configured to show the one or more drugs labeled as a suspect drug or a non-suspect drug;

wherein the display is configured to present a report showing the number of adverse drug effect event reports in each year during a decade;

wherein a drug detail section of the report involves paging and sorting;

wherein the report is configured to be broken down into individual years of birth of a patient who experienced an adverse drug effect reported in an adverse drug effects reporting database;

wherein the report is configured to show a plurality of serious outcomes;

wherein the report is configured to show serious outcomes in the report in a plurality of colors;

wherein the report is configured to provide a table of outcomes, a count, and percentages of the outcomes in each category;

wherein the report is configured to present a total number of serious outcomes and a total number of non-serious outcomes.

30. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 26,

wherein the filtering is configured to be applied individually, as a group, and globally;

wherein the filtering is configured to be retained for later use;

wherein the filtering is configured to be applied repeatedly;

wherein two or more filters are configured to be merged;

wherein the filter is configured to be overwritten; and

wherein the filter is configured to be saved as an incremental filter.

31. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 26, further comprising:

a pre-filter, wherein the pre-filter is configured in a first state to switch on an indication-related adverse drug reaction and

wherein the pre-filter is configured in a second state to switch off an indication-related adverse drug reaction.

32. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 26,

wherein the analysis is configured to search for a signal;

wherein the signal is selected from among the group consisting of an anomaly in a random population reported in an adverse effects reporting database, a change against a known background, or a coherent target in a noise background; and

wherein the signal is detected by a proportional analysis engine, a differencing engine, and the correlator.

33. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 32,

wherein the correlator is configured to measure a degree of an association according to a correlation algorithm;

wherein the correlator is configured to rank a first pair of terms relative to a second pair of terms;

wherein the correlator is configured to calculate a strength of the association for a known factor and for a rare adverse drug effect; and

wherein the display presents the results of a correlated search.

34. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 33, wherein the association is a drug and a reaction or a patient age and an outcome.

35. The computer system for assessing and analyzing risks of adverse effects resulting from use of at least one substance of interest according to claim 26, wherein the correlator is configured to use the Pearson product-moment correlation.