# US 2022/0277167 A1 · Real-time documentation verification using artificial intelligence and machine learning

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

- Number: US 2022/0277167 A1
- Document ID: US20220277167A1
- Status: Published application
- Kind: A1
- Application number: 17/188,195
- Filed: 2021-03-01
- Published: 2022-09-01
- Earliest claimed: 2021-03-01
- Assignees: Orbit Healthcare, Inc.
- Applicants: Orbit Healthcare, Inc.
- Inventors: Krishna VELAGA
- Web page: https://patentgrep.com/patent/US20220277167A1

## CPC

- G06V 10/40: Extraction of image or video features
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06N 20/00: Machine learning
- G06Q 10/10: Office automation; Time management
- G06Q 20/085: {involving remote charge determination or related payment systems}
- G06Q 20/14: specially adapted for billing systems
- G06V 30/418: Document matching, e.g. of document images
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06V 30/10: Character recognition
- G06V 30/147: {Determination of region of interest}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A method to verify documentation, such as healthcare documentation, in real-time is described. An image of a first document and demographic information is received from a patient. Optical character recognition (OCR) or QR code, barcode, or machine readable zone (MRZ) reading is performed on the image of the first document and a patient identifier is extracted from the first document. The patient identifier is compared to content in a database to identify a second document related to the first document that shares the patient identifier with the first document. The first document and the second document are verified as being associated with the patient based on the comparison and predefined business rules. OCR errors are identified in the first document and corrected using content from the second document. The method occurs prior to and allows the patient to pay for a healthcare appointment prior to attending the appointment.

## Claims

### Claim 1

A system configured to verify documentation in real-time, the system comprising:
a computing device;
an application executable on the computing device, the application being configured to:
receive an image of a first document from a patient; and
transfer the image of the first document to a verification system; and
the verification system being configured to:
receive the image of the first document from the application;
perform optical character recognition (OCR) on the image of the first document;
extract a patient identifier and information from the first document;
compare the patient identifier to content in a database to identify a second document related to the first document and sharing the patient identifier with the first document; and
verify the first document and the second document as being associated with the patient based on the comparison and predefined business rules.

### Claim 2 (depends on 1)

The system of claim 1, wherein each of the first document and the second document are selected from the group consisting of: an invoice, a receipt, a bill, a sales order document, an insurance claim document, a driver's license, a passport, an explanation of benefits document, and a medical insurance document.

### Claim 3 (depends on 1)

The system of claim 1, wherein performance of the OCR on the image of the first document comprises:
pre-processing the first document;
utilizing one or more text recognition algorithms; and
post-processing the first document.

### Claim 4 (depends on 3)

The system of claim 3, wherein the pre-processing of the first document comprises: de-skewing the first document, cropping the image of the first document, reducing noise for the first document, de-speckling the first document, binarisating the first document, removing lines from the first document, analyzing a layout of the first document, detecting lines in the first document, detecting words in the first document, recognizing script in the first document, and/or isolating characters in the first document.

### Claim 5 (depends on 3)

The system of claim 3, wherein the pre-processing of the first document occurs via one or more machine learning algorithms and artificial intelligence algorithms.

### Claim 6 (depends on 3)

The system of claim 3, wherein each of the one or more text recognition algorithms are selected from the group consisting of: a matrix matching algorithm and a feature extraction algorithm.

### Claim 7 (depends on 3)

The system of claim 3, wherein the post-processing of the first document comprises:
identifying one or more OCR errors in the first document; and
correcting the one or more OCR errors in the first document using the content from the second document.

### Claim 8 (depends on 1)

The system of claim 1, wherein the verification system is further configured to:
utilize a weighted average mechanism to assign a confidence score to the match between the first document and the second document.

### Claim 9 (depends on 1)

The system of claim 1, wherein the database is selected from the group consisting of: a healthcare provider database and a third party insurer database.

### Claim 10

A method executed by a system to verify documentation in real-time, the method comprising:
receiving an image of a first document from a patient via a website associated with the system;
receiving information from the patient via the website associated with the system;
performing optical character recognition (OCR) on the image of the first document;
extracting a patient identifier from the first document;
comparing the patient identifier to content in a database to identify a second document related to the first document and sharing the patient identifier with the first document;
verifying the first document and the second document as being associated with the patient based on the comparison and predefined business rules;
identifying one or more OCR errors in the first document; and
correcting the one or more OCR errors in the first document using the content from the second document.

### Claim 11 (depends on 10)

The method of claim 10, wherein the first document comprises a medical insurance document, and wherein the method further comprises transmitting an inquiry to the database to confirm a status of health insurance benefits associated with the medical insurance document prior to the patient attending an appointment.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
identifying the status of the health insurance benefits as being current; and
reducing a payment for the appointment based on the current status of the health insurance benefits in real-time.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
transmitting the modified payment to the website for display to the patient;
prompting the patient to pay the modified payment via the website; and
in response to receiving the payment, processing the payment for the appointment.

### Claim 14 (depends on 10)

The method of claim 10, wherein, in response to failing to verify the first document and the second document as being associated with the patient based on the comparison and predefined business rules, the method further comprises:
generating an alert; and
transmitting the alert to a human for reconciliation.

### Claim 15

A computer system comprising one or more processors, one or more memories, and one or more computer-readable hardware storage devices, the one or more computer-readable hardware storage devices containing program code executable by the one or more processors via the one or more memories to implement a method to verify documentation in real-time, the method comprising:
receiving an image of a first document from a patient;
performing optical character recognition (OCR) on the image of the first document;
extracting a patient identifier and information from the first document;
comparing the patient identifier to content in a database to identify a second document related to the first document and sharing the patient identifier with the first document;
verifying the first document and the second document as being associated with the patient based on the comparison and predefined business rules; and
utilizing a weighted average mechanism to assign a confidence score to the match between the first document and the second document.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein the method further comprises:
identifying one or more OCR errors in the first document; and
correcting the one or more OCR errors in the first document using the content from the second document.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein the first document comprises a medical insurance document, and wherein the method further comprises transmitting an inquiry to the database to confirm a status of health insurance benefits associated with the medical insurance document prior to the patient attending an appointment.

### Claim 18 (depends on 17)

The method of claim 17, wherein the method further comprises:
identifying the status of the health insurance benefits as being current;
reducing a payment for the appointment based on the current status of the health insurance benefits in real-time;
displaying the modified payment to the patient;
prompting the patient to pay the modified payment; and
in response to receiving the payment, processing the payment for the appointment.

### Claim 19 (depends on 15)

The computer system of claim 15, wherein, in response to failing to verify the first document and the second document as being associated with the patient based on the comparison and predefined business rules, the method further comprises:
generating an alert; and
transmitting the alert to a human for reconciliation.

### Claim 20 (depends on 19)

The computer system of claim 19, wherein the alert is selected from the group consisting of: an audio alert, a textual alert, and a graphical alert.
