# US 2021/0342949 A1 · Claim analysis with deep learning

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0342949 A1
- Document ID: US20210342949A1
- Status: Published application
- Kind: A1
- Application number: 17/362,820
- Filed: 2021-06-29
- Published: 2021-11-04
- Earliest claimed: 2019-12-20
- Assignees: AKASA, Inc.
- Applicants: Akasa
- Inventors: Byung-Hak Kim; Hariraam Varun Ganapathi; Andrew Atwal
- Web page: https://patentgrep.com/patent/US20210342949A1

## CPC

- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06F 16/313: {Selection or weighting of terms for indexing}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06F 18/24: Classification techniques
- G06N 3/045: Combinations of networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06Q 10/10: Office automation; Time management
- G06Q 40/08: Insurance
- G06N 3/048: Activation functions
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Embodiments relate to system for automatically predicting payer response to claims. In an embodiment, the system receives claim data associated with a claim. The system identifies a set of claim features of the claim data, and generates an input vector with at least a portion of the set of claim features. The system applies the input vector to a trained model. A first portion of the neural network is configured to generate an embedding representing the input vector with a lower dimensionality than the input vector. A second portion of the neural network is configured to generate a prediction of whether the claim will be denied based on the embedding. The system provides the prediction for display on a user interface of a user device. The prediction may further include denial reason codes and a response date estimation to indicate if, when, and why a claim will be denied.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A method of analyzing claims, the method comprising:
identifying a set of claim features of a claim;
generating an embedding of tokens based, least in part, on application of a tokenization process to the identified set of claim features, the tokenization process comprising one or more machine-learning models having been trained based, at least in part, on a history of claims;
computing one or more suspiciousness scores based, at least in part, on the embedding of tokens;
communicating at least one of the suspiciousness scores to an operator/user; and
receiving inputs from the operator/user to modify at least a portion of the claim to thereby affect a prediction of a payer response to the at least a portion of the claim.

### Claim 22 (depends on 21)

The method of claim 21, wherein at least one of the inputs comprises a correction to a previously incorrectly entered claim feature.

### Claim 23 (depends on 21)

The method of claim 21, wherein the at least one of the one or more machine-learning models has been trained according to a loss function, the loss function being based, at least in part, on a binary cross-entropy loss for a denial probability prediction, a categorical cross-entropy loss for a set of service-level denial reason code classifications or a categorical cross-entropy loss for a set of claim-level denial reason code classifications, or a combination thereof.

### Claim 24 (depends on 21)

The method of claim 21, wherein generating the embedding of tokens further comprises generating a claim sequence comprising:
a sequence of procedure tokens with numeric values;
a sequence of diagnoses tokens with numeric values; or
a sequence of single unique feature tokens with binary values, or a combination thereof.

### Claim 25 (depends on 21)

The method of claim 21, wherein the one or more machine learning models comprise one or more neural networks, and wherein generating the embedding of tokens further comprises:
receiving an input vector comprising a portion of the set of claim features; and
generating the embedding of tokens to comprise a higher dimensionality than a dimensionality of the input vector.

### Claim 26 (depends on 21)

The method of claim 21, wherein computing the one or more suspiciousness scores further comprises:
computing a gradient of a contribution of at least one of the identified set of claim features to the prediction of the payer response.

### Claim 27 (depends on 21)

The method of claim 21, and wherein generating the embedding of tokens further comprises determining a first set of token sequences representing procedure tokens, a second set of token sequences representing diagnosis tokens or a third set of tokens representing demographic tokens, or a combination thereof, based, at least in part on the identified set of claim features of the claim.

### Claim 28 (depends on 21)

The method of claim 21, and further comprising determining the prediction of the payer response based, at least in part, on a first reason code sequence, a second reason code sequence and a response date estimation, wherein the first reason code sequence includes likelihood scores for claim-level reason codes in a set of claim-level reason codes, and wherein the second reason code sequence includes likelihood scores for service-level reason codes in a set of service-level reason codes.

### Claim 29 (depends on 28)

The method of claim 28, wherein the machine learning model comprises:
a first set of task-specific output layers to generate the first reason code sequence,
a second set of task-specific output layers to generate the second reason code sequence, and
a third set of task-specific layers to generate the response date estimation.

### Claim 30

A non-transitory computer-readable storage medium comprising computer program code comprising computer-readable instructions that are executable by a processor to:
identify a set of claim features of a claim;
generate an embedding of tokens based, least in part, on application of a tokenization process to the identified set of claim features, the tokenization process comprising one or more machine-learning models to be determined based, at least in part, on a history of claims;
compute one or more suspiciousness scores based, at least in part, on the embedding of tokens;
communicate at least one of the suspiciousness scores to an operator/user; and
process inputs from the operator/user to modify at least a portion of the claim to thereby affect a prediction of a payer response to the at least a portion of the claim.

### Claim 31 (depends on 30)

The non-transitory computer-readable storage medium of claim 30, wherein at least one of the inputs comprises a correction to a previously incorrectly entered claim feature.

### Claim 32 (depends on 30)

The non-transitory computer-readable storage medium of claim 30, wherein the at least one of the neural network is determined according to a loss function, the loss function being based, at least in part, on a binary cross-entropy loss for a denial probability prediction, a categorical cross-entropy loss for a set of service-level denial reason code classifications or a categorical cross-entropy loss for a set of claim-level denial reason code classifications, or a combination thereof.

### Claim 33 (depends on 30)

The non-transitory computer-readable storage medium method of claim 30, wherein the embedding of tokens to be determined based, at least in part, on:
a sequence of procedure tokens with numeric values;
a sequence of diagnoses tokens with numeric values; or
a sequence of single unique feature tokens with binary values, or a combination thereof.

### Claim 34 (depends on 30)

The non-transitory computer-readable storage medium method of claim 30, wherein the one or more machine learning models comprise one or more neural networks, and wherein the instructions are further executable by the processor to:
obtain an input vector comprising a portion of the set of claim features; and
generate the embedding of tokens to comprise a higher dimensionality than a dimensionality of the input vector.

### Claim 35 (depends on 30)

The non-transitory computer-readable storage medium method of claim 30, wherein the instructions are further executable by the processor to:
determine at least one of the suspiciousness scores based, at least in part, on a computed gradient of a contribution of at least one of the identified set of claim features to the prediction of the payer response.

### Claim 36 (depends on 30)

The non-transitory computer-readable storage medium method of claim 30, and wherein the instructions are further executable by the processor to:
determine a first set of token sequences representing procedure tokens, a second set of token sequences representing diagnosis tokens or a third set of tokens representing demographic tokens, or a combination thereof, based, at least in part on the identified set of claim features of the claim.

### Claim 37 (depends on 30)

The non-transitory computer-readable storage medium method of claim 30, wherein the instructions are further executable by the processor to determine the prediction of the payer response based, at least in part, on a first reason code sequence, a second reason code sequence and a response date estimation, wherein the first reason code sequence includes likelihood scores for claim-level reason codes in a set of claim-level reason codes, and wherein the second reason code sequence includes likelihood scores for service-level reason codes in a set of service-level reason codes.

### Claim 38 (depends on 37)

The non-transitory computer-readable storage medium of claim 37, wherein the machine learning model comprises:
a first set of task-specific output layers to generate the first reason code sequence,
a second set of task-specific output layers to generate the second reason code sequence, and
a third set of task-specific layers to generate the response date estimation.

### Claim 39

A method comprising:
training a machine learning model based, at least in part on a history of claims;
generating a computer program product comprising a non-transitory computer-readable storage medium comprising non-transitory computer-readable storage medium comprising computer program code that is executable by a processor to:
identify a set of claim features of a claim;
generate an embedding of tokens based, least in part, on application of a tokenization process to the identified set of claim features, the tokenization process comprising one or more machine-learning models having been trained based, at least in part, on a history of claims;
compute one or more suspiciousness scores based, at least in part, on the embedding of tokens;
communicate at least one of the suspiciousness scores to an operator/user; and
process inputs from the operator/user to modify at least a portion of the claim to thereby affect a prediction of a payer response to the at least a portion of the claim.

### Claim 40 (depends on 39)

The method of claim 39, wherein training the machine learning model comprises training the machine learning model according to a loss function, the loss function being based, at least in part, on a binary cross-entropy loss for a denial probability prediction, a categorical cross-entropy loss for a set of service-level denial reason code classifications or a categorical cross-entropy loss for a set of claim-level denial reason code classifications, or a combination thereof.
