Predicting Side Effect Attributes
Abstract
A method and system for predicting attribute side effects of predisposition modification are presented in which a set of attributes for predisposition modification of an individual is used to modify the individual's attribute profile to generate a modified attribute profile. A set of attribute combinations is compared against the modified attribute profile in order to identify those attribute combinations from the set that also occur in the modified attribute profile. Candidate side effect attributes that are statistically associated with the identified attribute combinations, but not present in the modified attribute profile, are stored as predicted side effect attributes that would result from the intended predisposition modification of the individual.
Claims
exact text as granted — not AI-modified1 . A computer based method for predicting side effect attributes, comprising:
a) accessing an attribute profile of an individual and a set of attributes for predisposition modification of the individual; b) updating the attribute profile of the individual with the set of attributes for predisposition modification of the individual, to generate a modified attribute profile; c) identifying, from a set containing attribute combinations and associated statistical results which indicate the strength of association of the attribute combinations with one or more candidate side effect attributes, one or more of the attribute combinations that occur in the modified attribute profile; and d) storing one or more of the candidate side effect attributes that are statistically associated with the identified attribute combinations, as indicated by the associated statistical results, to generate a set of predicted side effect attributes.
2 . The computer based method of claim 1 , further comprising:
e) including the set of predicted side effect attributes in the set of attributes for predisposition modification of the individual; and f) repeating steps (a)-(e) until no attribute combinations can be identified in step (c).
3 . The computer based method of claim 1 , further comprising:
e) transmitting one or more of the predicted side effect attributes as output.
4 . The computer based method of claim 1 , further comprising:
e) tabulating the predicted side effect attributes as a rank ordered list based on their strength of association with the identified attribute combinations.
5 . The computer based method of claim 1 , further comprising:
e) compiling the predicted side effect attributes into at least two subgroups corresponding to desirable and undesirable side effects.
6 . The computer based method of claim 1 , further comprising:
e) compiling the predicted side effect attributes into at least two subgroups corresponding to desirable and undesirable side effects, and rank ordering the predicted side effect attributes in each subgroup based on the strength of association of the predicted side effect attributes with the identified attribute combinations.
7 . The computer based method of claim 1 , wherein the candidate side effect attributes do not occur in the modified attribute profile.
8 . The computer based method of claim 1 , wherein the candidate side effect attributes are filtered to exclude designated attributes.
9 . The computer based method of claim 1 , wherein the identity of the individual is masked or anonymized.
10 . The computer based method of claim 1 , wherein the strength of association of a candidate side effect attribute with an identified attribute combination must meet at least one statistical requirement in order for the candidate side effect attribute to be stored as a predicted side effect attribute.
11 . The computer based method of claim 10 , wherein the at least one statistical requirement is selected from the group comprising: a minimum statistical value, and a value of statistical significance.
12 . The computer based method of claim 1 , wherein storing one or more candidate side effect attributes that are statistically associated with the identified attribute combinations further comprises storing one or more of the associated statistical results which indicate the strength of association.
13 . The computer based method of claim 12 , wherein the stored statistical results indicate the individual's potential for association with each of the predicted side effect attributes following predisposition modification.
14 . The computer based method of claim 13 , further comprising:
e) transmitting the predicted side effect attributes and the stored statistical results to create a report indicating the individual's potential for association with each of the predicted side effect attributes following predisposition modification.
15 . The computer based method of claim 13 , further comprising:
e) associating the set of predicted side effect attributes with the individual, and storing the association.
16 . The computer based method of claim 15 , wherein storing the association comprises storing a link between the set of predicted side effect attributes and at least one of: an identifier of the individual, the attribute profile of the individual, and the set of attributes for predisposition modification of the individual.
17 . A computer based method for predicting side effect attributes, comprising:
a) accessing a modified attribute profile, wherein the modified attribute profile comprises an attribute profile of an individual and a set of attributes for predisposition modification of the individual; b) identifying, from a set containing attribute combinations and associated statistical results which indicate the strength of association of the attribute combinations with one or more candidate side effect attributes, one or more of the attribute combinations that occur in the modified attribute profile; and c) storing one or more candidate side effect attributes that are statistically associated with the identified attribute combinations, as indicated by the associated statistical results, to generate a set of predicted side effect attributes.
18 . A computer based system for predicting side effect attributes, comprising:
a) a first data accessing subsystem for accessing an attribute profile of an individual and a set of attributes for predisposition modification of the individual; b) a second data accessing subsystem for accessing a set containing attribute combinations and associated statistical results which indicate the strength of association of the attribute combinations with one or more candidate side effect attributes; c) a data processing subsystem comprising:
i) a data updating subsystem for updating the attribute profile of the individual with the set of attributes for predisposition modification of the individual, to generate a modified attribute profile;
ii) a data comparison subsystem for identifying one or more of the attribute combinations that occur in the modified attribute profile; and
d) a data storage subsystem for storing one or more of the candidate side effect attributes that are statistically associated with the identified attribute combinations, as indicated by the associated statistical results, to generate a set of predicted side effect attributes.
19 . The computer based system of claim 18 , wherein the data processing subsystem further comprises:
iii) a data tabulating subsystem for tabulating the predicted side effect attributes as a rank ordered list based on the strength of association of the predicted side effect attributes with the identified attribute combinations.
20 . The computer based system of claim 18 , further comprising:
e) a communications subsystem for transmitting the predicted side effect attributes and a portion of the associated statistical results as output to indicate the individual's potential for association with the predicted side effect attributes following predisposition modification.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.