Claim analysis with deep learning

A claim analysis system stored on a computer readable storage medium, wherein the claim analysis system is manufactured by a process comprising:

• accessing claim data associated with a set of claims, each claim in the set of claims including a label representing a payer response;
• for each claim in the set of claims:
• identifying claim features of the claim data, and
• generating an input vector with at least a portion of the claim features;
• initializing weights of a neural network with initial values;
• applying the input vectors of the set of claims to the neural network to generate predictions of payer responses to the claims;
• and
• updating the weights of the neural network based, at least in part, on the predictions and corresponding labels for the set of claims.

A method comprising:

• training a first portion of one or more neural networks implemented on computer, the first portion of the one or more neural networks to generate an embedding based on a first vector of claim features, the first vector comprising at least features of a claim, the embedding comprising a second vector having a lower dimensionality than the first vector, the second vector comprising at least a first sub-vector to express one or more diagnosis tokens and a second sub-vector to express one or more procedure tokens;
• and
• training a second portion of one or more neural networks to generate a prediction of a payer's response to the claim based, at least in part, on the embedding, the prediction of the payer's response to the claim comprising at least a likelihood that the claim would be denied,
• wherein training the first portion of the one or more neural networks and training the second portion of the one or more neural networks comprises determining weights for the first and second portions of the one or more neural networks based, at least in part, on a computed prediction of payer's response and a label representing a payer's response.