Machine-learning based efficacy predictions based on genetic and biometric information
Examples disclosed herein may involve a computing system that is configured to (i) identify a cannabinoid formulation for which to model efficacy for a given health condition shared by a plurality of individuals, (ii) receive respective efficacy information indicating the efficacy of the cannabinoid formulation for the plurality of individuals, (iii) receive respective genetic information for the plurality of individuals, (iv) receive respective biometric information for the plurality of individuals, (v) apply machine learning techniques to group the plurality of individuals into one or more groups based on their (a) respective efficacy information and (b) similarities in their respective genetic information and respective biometric information, and (vi) embody the one or more groups into a machine learning model that functions to (a) receive, as input data, information for a given individual and (ii) based on an evaluation of the received input data, output an efficacy prediction for the given individual.
1 . A computational platform for treating a particular health condition for a user, wherein the computational platform comprises:
one or more processors;
a machine learning model; and
a tangible, non-transitory computer-readable medium storing program instructions that, when executed by the one or more processors, cause performance of a set of operations comprising:
prior to receiving a request to provide an efficacy prediction for a particular cannabinoid formulation to treat the particular health condition of the user, training the machine learning model, wherein training the machine learning model comprises:
identifying the particular health condition shared by a plurality of individuals;
receiving respective efficacy information indicating efficacy of the particular cannabinoid formulation for treating the particular health condition shared by the plurality of individuals; and
receiving respective genetic information for the plurality of individuals, wherein dimensionality of the respective genetic information has been reduced prior to training the machine learning model; and
in response to receiving a request to provide the efficacy prediction for the particular cannabinoid formulation to treat the particular health condition of the user, applying the machine learning model to:
(i) group the plurality of individuals into a plurality of groups based on their respective efficacy information and similarities in their respective genetic information; and
(ii) output the efficacy prediction for the particular cannabinoid formulation to treat the particular health condition of the user, wherein the efficacy prediction is based on the trained machine learning model and the genetic information for the user; and
receiving an updated indication of whether the particular cannabinoid formulation was effective in treating the particular health condition for the user; and
retraining the machine learning model based on the updated indication.
2 . The computational platform of claim 1 , wherein the genetic information comprises genotype information.
3 . The computational platform of claim 2 , wherein the genotype information comprises a genome for each of the plurality of individuals, and wherein the genetic information for the user comprises a genome for the user.
4 . The computational platform of claim 1 , wherein the genetic information comprises phenotype information.
5 . The computational platform of claim 1 , wherein the set of operations further comprises receiving respective biometric information for the plurality of individuals.
6 . The computational platform of claim 5 , wherein receiving respective biometric information for the plurality of individuals comprises receiving respective biometric information for each of the plurality of individuals.
7 . The computational platform of claim 5 , wherein receiving the respective biometric information comprises receiving at least a portion of the biometric information from a biometric device.
8 . The computational platform of claim 1 , wherein the machine learning model comprises a k-nearest neighbor machine learning technique.
9 . The computational platform of claim 1 , wherein the machine learning model comprises a k-means machine learning technique.
10 . A tangible, non-transitory computer-readable medium storing program instructions that, when executed by one or more processors, cause performance of a set of operations comprising:
prior to receiving a request to provide an efficacy prediction for a particular cannabinoid formulation to treat a particular health condition of a user, training a machine learning model, wherein training the machine learning model comprises:
identifying the particular health condition shared by a plurality of individuals;
receiving respective efficacy information indicating efficacy of the particular cannabinoid formulation for treating the particular health condition shared by the plurality of individuals; and
receiving respective genetic information for the plurality of individuals, wherein dimensionality of the respective genetic information has been reduced prior to training the machine learning model; and
in response to receiving a request to provide the efficacy prediction for the particular cannabinoid formulation to treat the particular health condition of the user, applying the machine learning model to:
(i) group the plurality of individuals into a plurality of groups based on their respective efficacy information and similarities in their respective genetic information; and
(ii) output the efficacy prediction for the particular cannabinoid formulation to treat the particular health condition of the user, wherein the efficacy prediction is based on the trained machine learning model and the genetic information for the user; and
receiving an updated indication of whether the particular cannabinoid formulation was effective in treating the particular health condition for the user; and
retraining the machine learning model based on the updated indication.
11 . The tangible, non-transitory computer-readable medium of claim 10 , wherein the genetic information comprises genotype information.
12 . The tangible, non-transitory computer-readable medium of claim 11 , wherein the genotype information comprises a genome for each of the plurality of individuals, and wherein the genetic information for the user comprises a genome for the user.
13 . The tangible, non-transitory computer-readable medium of claim 10 , wherein the genetic information comprises phenotype information.
14 . The tangible, non-transitory computer-readable medium of claim 10 , wherein the set of operations further comprises receiving respective biometric information for the plurality of individuals.
15 . The tangible, non-transitory computer-readable medium of claim 14 , wherein receiving respective biometric information for the plurality of individuals comprises receiving respective biometric information for each of the plurality of individuals.
16 . The tangible, non-transitory computer-readable medium of claim 14 , wherein receiving the respective biometric information comprises receiving at least a portion of the biometric information from a biometric device.
17 . The tangible, non-transitory computer-readable medium of claim 10 , wherein the machine learning model comprises a k-nearest neighbor machine learning technique.
18 . The tangible, non-transitory computer-readable medium of claim 10 , wherein the machine learning model comprises a k-means machine learning technique.
19 . A computer-implemented comprising:
prior to receiving a request to provide an efficacy prediction for a particular cannabinoid formulation to treat a particular health condition of a user, training a machine learning model, wherein training the machine learning model comprises:
identifying the particular health condition shared by a plurality of individuals;
receiving respective efficacy information indicating efficacy of the particular cannabinoid formulation for treating the particular health condition shared by the plurality of individuals; and
receiving respective genetic information for the plurality of individuals, wherein dimensionality of the respective genetic information has been reduced prior to training the machine learning model; and
in response to receiving a request to provide the efficacy prediction for the particular cannabinoid formulation to treat the particular health condition of the user, applying the machine learning model to:
(i) group the plurality of individuals into a plurality of groups based on their respective efficacy information and similarities in their respective genetic information; and
(ii) output the efficacy prediction for the particular cannabinoid formulation to treat the particular health condition of the user, wherein the efficacy prediction is based on the trained machine learning model and the genetic information for the user; and
receiving an updated indication of whether the particular cannabinoid formulation was effective in treating the particular health condition for the user; and
retraining the machine learning model based on the updated indication.