US 2020/0051670 A1 · DATA-DRIVEN PREDICTION OF DRUG COMBINATIONS THAT MITIGATE ADVERSE DRUG REACTIONS

Abstract

Predicting beneficial drug combinations mitigating adverse drug reactions identifies drug combinations and associated target adverse drug reaction from a spontaneous reporting system containing case reports of drugs and associated adverse drug reactions. Each drug combination comprises a first drug and a second drug, and a propensity score is computed for each drug in each group. This propensity score expresses a probability of being exposed to a given drug based on other co-prescribed drugs and reported indications, which reflect patient characteristics. Associations are computed for each drug as well as drug interaction. Among the associations, the sum of the associations of the second drug and the interaction effect represents the predicted beneficial score expressing whether the second drug alters the chance of developing the target adverse drug reaction for patients on the first drug. The interaction effect is referred to as predicted interaction score, and represents antagonistic or synergistic drug interactions.

Claims21

Dependent claims

1-20. (canceled)

A method for generating beneficial drug combinations that mitigate adverse drug reactions, the method comprising:

identifying a candidate set of drug combinations and target adverse drug reaction triples, each drug reaction triple comprising a first drug associated with increasing a rate of occurrence of a given target adverse drug reaction and a second drug capable of reducing the rate of occurrence of the given target adverse drug reaction induced by the first drug, wherein identifying the candidate set of drug combinations and adverse drug reaction triples comprises:
identifying an initial set of first drug and adverse drug reaction pairs having at least a threshold number of entries in a database of adverse drug events;
generating a filtered set of first drug and adverse drug reaction pairs by identifying first drug and adverse drug reactions pairs in the initial set of first drug and adverse drug reaction pairs having an associated odds ratio of developing the adverse drug reaction from the first drug over a background level of developing the adverse reaction that is greater than one by a statistically significant amount;
removing first drug and adverse drug reaction pairs from the filtered set that are not mentioned in at least one database of known drug side effects;
and
selecting for each remaining first drug and adverse drug reaction pair in the filtered set at least one second drug to generate the candidate set of drug combinations and adverse drug reaction triples;
and
co-prescribing to a patient a given first drug and a given second drug from one of the drug reaction triples in the candidate set of drug combinations and target adverse drug reaction triples.

5 more elements

A computer-readable storage medium containing a computer-readable code that when read by a computer causes the computer to perform a method for generating beneficial drug combinations that mitigate adverse drug reactions, the method comprising:

identifying a candidate set of drug combinations and target adverse drug reaction triples, each drug reaction triple comprising a first drug associated with increasing a rate of occurrence of a given target adverse drug reaction and a second drug capable of reducing the rate of occurrence of the given target adverse drug reaction induced by the first drug, wherein identifying the candidate set of drug combinations and adverse drug reaction triples comprises:
identifying an initial set of first drug and adverse drug reaction pairs having at least a threshold number of entries in a database of adverse drug events;
generating a filtered set of first drug and adverse drug reaction pairs by identifying first drug and adverse drug reactions pairs in the initial set of first drug and adverse drug reaction pairs having an associated odds ratio of developing the adverse drug reaction from the first drug over a background level of developing the adverse reaction that is greater than one by a statistically significant amount;
removing first drug and adverse drug reaction pairs from the filtered set that are not mentioned in at least one database of known drug side effects;
and
selecting for each remaining first drug and adverse drug reaction pair in the filtered set at least one second drug to generate the candidate set of drug combinations and adverse drug reaction triples;
and
co-prescribing to a patient a given first drug and a given second drug from one of the drug reaction triples in the candidate set of drug combinations and target adverse drug reaction triples.

5 more elements

A computing system for generating beneficial drug combinations, the computing systems comprising:

a hardware memory comprising a database comprising at least one spontaneous reporting system comprising a plurality of case reports of drugs and associated adverse drug reactions;
a processing unit in communication with the memory;
a selection module to identifying a candidate set of drug combinations and target adverse drug reaction triples, each drug reaction triple comprising a first drug associated with increasing a rate of occurrence of a given target adverse drug reaction and a second drug capable of reducing the rate of occurrence of the given target adverse drug reaction induced by the first drug, wherein the selection modules comprises:
a first drug and linked adverse drug reaction pair identification module to identify an initial set of first drug and adverse drug reaction pairs having at least a threshold number of entries in the database;
a filtering module to generate a filtered set of first drug and adverse drug reaction pairs by identifying first drug and adverse drug reactions pairs in the initial set of first drug and adverse drug reaction pairs having an associated odds ratio of developing the adverse drug reaction from the first drug over a background level of developing the adverse reaction that is greater than one by a statistically significant amount;
and
a known side effects comparison module to remove first drug and adverse drug reaction pairs from the filtered set that are not mentioned in at least one database of known drug side effects;
and
a second drug identification module to select for each remaining first drug and adverse drug reaction pair in the filtered set at least one second drug to generate the candidate set of drug combinations and adverse drug reaction triples.

6 more elements

Dependencies are inferred from the claim text.

Data-driven prediction of drug combinations that mitigate adverse drug reactions

Life of this patent

Data-driven prediction of drug combinations that mitigate adverse drug reactions

Life of this patent

Abstract

Claims21