Methods to estimate effectiveness of a medical treatment

A computer-implemented method executed by one or more processors, the method comprising:

• receiving, from a database, a first dataset comprising:
• a set of covariate vectors, each covariate vector including clinical covariates of a respective patient, and
• a set of response indicators, each response indicator being associated with a respective covariate vector, wherein response indicators of the set of response indicators vary over a range;
• receiving, from the database, multiple partitions on the range of the response indicators to define a plurality of response classes for the response indicator;
• training a neural network model (NNM) with the first dataset to obtain a first NNM;
• bootstrapping the first dataset for n times to obtain n second datasets;
• training the NNM with each second dataset in the n second datasets to obtain n sets of second NNMs;
• for each covariate vector:
• obtaining, from the first NNM and the n second NNMs, n+1 predicted responses for the covariate vector, each predicted response being obtained by applying a respective one of the first NNM and the n second NNMs to the covariant vector, and
• for each response class:
• estimating an association probability indicating that the covariate vector is associated with the response class by:
• applying, for the response class, an indicator function to each of the n+1 predicted responses to obtain n+1 outputs for the response class, and
• calculating the association probability by normalizing an aggregation of the obtained n+1 outputs for the response class;
• estimating a treatment effect of a medical treatment by:
• determining a first subset of covariate vectors for patients who received the medical treatment, and a second subset of covariate vectors for patients who did not receive the medical treatment, and
• comparing, for one or more response classes, (i) a first normalized aggregation of association probabilities for the first subset, with (ii) a second normalized aggregation of association probabilities of the second subset;
• and
• providing the estimated treatment effect for display on a graphical user interface of a computing device.

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

• receiving a dataset comprising:
• a set of covariate vectors, each covariate vector including clinical covariates of a respective patient, and
• a set of response indicators, each response indicator being associated with a respective covariate vector, wherein response indicators of the set of response indicators vary over a range;
• receiving multiple partitions on the range of the response indicators to define a plurality of response classes for the response indicator;
• converting each response indicator to a respective one-hot encoded vector based on response classes indicated by the multiple partitions;
• training a neural network model based on each covariate vector and a respective one-hot encoded vector associated with the covariate vector, the neural network model utilizing a non-linear activation function and a loss function;
• and
• estimating a treatment effect of a medical treatment by:
• determining a first subset of covariate vectors for patients who received the medical treatment, and a second subset of covariate vectors for patients who did not receive the medical treatment, and
• comparing, for one or more response classes, (i) a first probability to (ii) a second probability, the first probability being a normalized aggregation of respective probabilities that covariate vectors of the first subset of covariate vectors are associated with the one or more response classes, the second probability being a normalized aggregation of respective probabilities that covariate vectors of the second subset of covariate vectors are associated with the one or more response class,
• wherein the respective probabilities are calculated by using the trained neural network model;
• and
• providing the estimated treatment effect for display on a graphical user interface of a computing device.