Patent Issued for Systems and methods for insurance fraud detection (USPTO 11055789)

2021 JUL 28 (NewsRx) -- By a News Reporter-Staff News Editor at Health Policy and Law Daily -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Alammar, Mustafa (Los Angeles, CA, US), Annigeri, Rohit Sanjay (Los Angeles, CA, US), Carter, Cambron Neil (Los Angeles, CA, US), Tabak, Joshua Alexander (Los Angeles, CA, US), Wilbert, Adam Michael (Los Angeles, CA, US), filed on September 4, 2020, was published online on July 6, 2021.

The patent’s assignee for patent number 11055789 is Pearl Inc. (Beverly Hills, California, United States).

News editors obtained the following quote from the background information supplied by the inventors: “A given health insurance carrier, which may also be referred to as an insurance company or insurance provider, may receive thousands of insurance claims each day. Each insurance claim may be provided to the insurance carrier from a healthcare provider (such as a doctor’s or dentist’s office, a hospital, etc.), where the claim may indicate a healthcare service rendered by the healthcare provider for a patient who is insured by the given insurance carrier. Given the large volume of claims, it would be prohibitively time consuming for carriers to ensure each claim is thoroughly reviewed by experienced examiners. Instead, the majority of claims submitted to many insurance carriers are not fully evaluated for signs of fraud, waste or abuse.

“Healthcare providers may commit health insurance fraud in a number of ways. Such fraud may include billing for services or procedures that were never rendered, charging for a more expensive procedure than what was actually performed, falsifying a patient’s diagnosis to justify unnecessary tests or procedures, etc. Insurance fraud is a pervasive problem across medicine and dentistry alike. Dental adjudicators review evidence to evaluate medical necessity with the goal of limiting waste and abuse, but suspicious cases often fail to be flagged.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “Generally described, aspects of the present disclosure relate to computer-implemented processes and system architectures for automatically identifying fraud, waste or abuse in health insurance claims submitted to insurance companies by healthcare providers (such as by hospitals, doctors, dentists, etc.). Health insurance carriers often receive insurance claims (which may refer to requests for reimbursement submitted to the insurance carrier for health services that the submitter provided to a patient insured by the insurance carrier) that are fraudulent or do not represent a real treatment or service that was actually performed on a patient by the provider. The automated methods of fraud, waste and/or abuse detection described herein may replace or supplement manual review by an examiner of an insurance company, as will be further described below. For example, aspects of the present disclosure for enable the focus of an examiner to be directed to the claims with a highest likelihood of fraud. Given that the volume of claims may prohibit manual review of each and every submitted claim (e.g., a majority of claims may be approved without review due to shortage of examiner or other reviewing personnel), ensuring that the claims reviewed are those most likely to have fraud or abuse issues may result in a significantly higher number of fraudulent claims being identified relative to prior art methods. In some embodiments of the present disclosure, certain insurance claims may be automatically approved or denied without manual review based on an automatically determined confidence value, as will be discussed below.

“Aspects of the present disclosure relate to machine learning-based approaches to analyzing images that are provided in health insurance reimbursement claims for evidence of insurance fraud. These images may be image files that a healthcare provider attaches or includes in their insurance claim as evidence of the health service that they claim they performed for a patient. In some embodiments, a machine learning model may be trained to learn to detect that a very similar x-ray, radiograph, medical form, doctor’s note scan, practice management software screenshot, or other image has been submitted in multiple health insurance claims, which would be a sign of fraud (e.g., a doctor took one radiograph for one patient, but has re-submitted the same radiograph or a modified version of the same radiograph to support a claim for a second patient). A machine learning model may be trained to identify similar images that are not exactly the same, but where it appears that the submitter edited one image to make the second image (e.g., placed a different patient name over the same medical image). As will be further discussed below, the detection of identical images or near-identical images that may be associated with fraudulent claims may be based in part on generating a signature for each image submitted to one or more insurance carriers, such that images likely to be considered nearly identical from a fraud perspective will share the same or similar signature as each other.

“In some embodiments, the machine learning approaches to fraud detection discussed herein may further include utilizing computer vision techniques to identify any of various pathologies, conditions, anatomies, anomalies or other medical issues depicted in a radiograph image, such as using systems and methods disclosed in U.S. patent application Ser. No. 16/562,286, entitled SYSTEMS AND METHODS FOR AUTOMATED MEDICAL IMAGE ANALYSIS, filed Sep. 5, 2019 (hereinafter “the ‘286 application”), the entirety of which is hereby incorporated by reference herein. In some embodiments, the presence of potential fraud, waste or abuse in a claim may be based at least in part on a determination that conditions or features associated with one or more treatment codes submitted in an insurance claim are not identified in the claim’s supporting radiograph image(s) using machine learning models such as those disclosed in the ‘286 application.

“Fraud detection solutions described herein may include creating a fingerprint or signature for each claim that enables the system to identify where and when a duplicate or near-duplicate claim was last seen. In some embodiments, by automatically flagging or identifying such similar previously submitted claims, insurance carriers can more easily recognize or be alerted to both clerical errors and potential fraud, waste or abuse present in submitted claims. This may occur as claims are submitted (e.g., before the submitter is reimbursed or paid out by the carrier), or may occur on a batch basis for previously submitted claims as part of an audit or other claim review process.”

The claims supplied by the inventors are:

“1. A computer system comprising: memory; and a processor in communication with the memory and configured with processor-executable instructions to perform operations comprising: obtaining, for a first insurance claim, insurance claim information and at least a first radiograph image associated with the first insurance claim, wherein the first radiograph image has been submitted by a healthcare provider to an insurance carrier as supporting evidence of a medical service indicated in the insurance claim information as having been performed by the healthcare provider; generating a digital signature representing the first radiograph image, wherein the digital signature is generated based at least in part on image data within the first radiograph image, wherein generating the digital signature representing the first radiograph image comprises: implementing a feature extraction process with respect to the image data within the first radiograph image to extract a plurality of features of the image data, wherein the feature extraction process comprises at least one of: (i) providing the image data within the first radiograph image as input to a convolutional neural network and extracting the plurality of features of the image data from one or more layers of the convolutional neural network, or (ii) applying mathematical transformations to image intensity data within the first radiograph image; and applying a hashing function to at least a subset of the plurality of features of the image data to generate the digital signature representing the first radiograph image; comparing the digital signature generated for the first radiograph image to previously generated digital signatures of other images that have been submitted in association with insurance claims other than the first insurance claim, wherein the previously generated digital signatures have been generated using the feature extraction process and the hashing function with respect to image data of the other images; identifying a match between the digital signature generated for the first radiograph image submitted for the first insurance claim and one or more of the previously generated digital signatures of other images submitted in association with the insurance claims other than the first insurance claim; determining, based on the match identified between the digital signature and the one or more of the previously generated digital signatures, that the first radiograph image submitted for the first insurance claim is a duplicate of at least one radiograph image previously submitted to the insurance carrier for a different insurance claim other than the first insurance claim; determining that the first insurance claim is associated with potential fraud based at least in part on the identified match between the digital signature and the one or more of the previously generated digital signatures; and based at least in part on the determining that the first insurance claim is associated with potential fraud, generating at least one of (a) a recommendation for the insurance carrier to deny the first insurance claim, or (b) user interface data that enables a user to review whether to approve or deny the first insurance claim.

“2. The computer system of claim 1, wherein the operations further comprise: using one or more machine learning models, detecting one or more medical conditions present in the first radiograph image; and comparing the one or more medical conditions present in the first radiograph image with one or more treatment codes included in the insurance claim information, wherein the recommendation for the insurance carrier to deny the first insurance claim is based in further part on whether the one or more treatment codes are associated with the one or more medical conditions detected in the first radiograph image.

“3. The computer system of claim 1, wherein the first insurance claim is determined by the computer system to be associated with potential fraud regardless of whether any previous images having the one or more previously generated digital signatures have been identified as associated with fraud prior to the comparing of the digital signature generated for the first radiograph image to the previously generated digital signatures.

“4. The computer system of claim 1, wherein the feature extraction process comprises providing the image data within the first radiograph image as input to the convolutional neural network and extracting the plurality of features of the image data from the one or more layers of the convolutional neural network.

“5. The computer system of claim 1, wherein the comparing of wherein the operations further comprise: determining that the first insurance claim is associated with potential fraud based at least in part on the comparing of the digital signature generated for the first radiograph image to the previously generated digital signatures indicating that a radiograph depicted in the first radiograph image is not a radiograph first captured in association with the first insurance claim.

“6. The computer system of claim 1, wherein determining that the first insurance claim is associated with potential fraud includes determining a likelihood that the first insurance claim is associated with one or more types of fraud associated with one or more of: (a) the healthcare provider billing for services or procedures that were not rendered by the healthcare provider, (b) the healthcare provider billing for a more expensive procedure than was actually performed by the healthcare provider, or © the healthcare provider falsifying a diagnosis of a patient to justify unnecessary tests or procedures.

“7. A computer-implemented method comprising: as implemented by one or more computing devices configured with specific executable instructions, obtaining, for a first insurance claim, insurance claim information and at least a first image associated with the first insurance claim, wherein the first image has been submitted by a healthcare provider to an insurance carrier as supporting evidence of a medical service indicated in the insurance claim information as having been performed by the healthcare provider; generating a digital signature representing the first image, wherein the digital signature is generated based at least in part on image data within the first image, wherein generating the digital signature representing the first image comprises: implementing a feature extraction process with respect to the image data within the first image to extract a plurality of features of the image data, wherein the feature extraction process comprises at least one of: (i) providing the image data within the first image as input to a convolutional neural network and extracting the plurality of features of the image data from one or more layers of the convolutional neural network, or (ii) applying mathematical transformations to image intensity data within the first image; and applying a hashing function to at least a subset of the plurality of features of the image data to generate the digital signature representing the first image; comparing the digital signature generated for the first image to previously generated digital signatures of other images that have been submitted in association with insurance claims other than the first insurance claim, wherein the previously generated digital signatures have been generated using the feature extraction process and the hashing function with respect to image data of the other images; identifying a match between the digital signature generated for the first image submitted for the first insurance claim and one or more of the previously generated digital signatures of other images submitted in association with the insurance claims other than the first insurance claim; determining, based on the match identified between the digital signature and the one or more of the previously generated digital signatures, that the first image submitted for the first insurance claim is a duplicate of at least one image previously submitted to the insurance carrier for a different insurance claim other than the first insurance claim; determining that the first insurance claim is associated with potential fraud based at least in part on the identified match between the digital signature and the one or more of the previously generated digital signatures; and based at least in part on the determining that the first insurance claim is associated with potential fraud, generating at least one of (a) a recommendation for the insurance carrier to deny the first insurance claim, or (b) user interface data that enables a user to review whether to approve or deny the first insurance claim.

“8. The computer-implemented method of claim 7, wherein the first image depicts at least one radiograph.

“9. The computer-implemented method of claim 7, wherein the first image depicts at least a first radiograph, and wherein the method further comprises: using one or more machine learning models, detecting one or more medical conditions present in the first radiograph; and comparing the one or more medical conditions present in the first radiograph with one or more treatment codes included in the insurance claim information, wherein the recommendation for the insurance carrier to deny the first insurance claim is based in further part on whether the one or more treatment codes are associated with the one or more medical conditions detected in the first radiograph.

“10. The computer-implemented method of claim 7, wherein the first image depicts one or more of: a medical form, a doctor’s note, a screenshot or export from practice management software, a prescription, a patient chart, medical test results, or a filled-in medical form.”

There are additional claims. Please visit full patent to read further.

For additional information on this patent, see: Alammar, Mustafa. Systems and methods for insurance fraud detection. U.S. Patent Number 11055789, filed September 4, 2020, and published online on July 6, 2021. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=11055789.PN.&OS=PN/11055789RS=PN/11055789

(Our reports deliver fact-based news of research and discoveries from around the world.)