# US 11,004,565 B2 · Data aggregation, integration and analysis system and related devices and methods

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

- Number: US 11,004,565 B2
- Document ID: US11004565B2
- Status: Granted
- Kind: B2
- Application number: 16/362,174
- Filed: 2019-03-22
- Published: 2019-09-26
- Granted: 2021-05-11
- Earliest claimed: 2018-03-22
- Assignees: Digital Diagnostics Inc.
- Applicants: Digital Diagnostics Inc.
- Inventors: Michael D. Abramoff
- Web page: https://patentgrep.com/patent/US11004565B2

## CPC

- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G06F 16/2379: {Updates performed during online database operations; commit processing}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06V 30/19147: {Obtaining sets of training patterns; Bootstrap methods, e.g. bagging or boosting}
- G06V 30/19173: {Classification techniques}
- G16H 30/40: for processing medical images, e.g. editing
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A system for recording, storing and processing diagnostic information, including: a computer implementing a computer-readable media including digital data and ground truth; a registry constructed and arranged to store and associate transactions or accesses on the data; and a machine learning system that considers each learning step modification a microtransaction for the data used in that step and which is recorded in the transaction registry. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods.

## Claims

### Claim 1

A non-transitory computer-readable medium comprising memory with instructions encoded thereon for attribution of data to an algorithm, the instructions, when executed, causing one or more processors to perform operations, the instructions comprising instructions to:
(a) register a pool of images on a ledger;
(b) attribute each image of the pool of images with an image-specific truth data set on the ledger;
(c) train a machine learning algorithm to one or more of the images and registering the training of the machine learning algorithm a plurality of parameters to the one or more images on the ledger;
(d) register each modification made to the machine learning algorithm on the ledger and attributing its modification to image that resulted in the modification; and
(e) assess performance of the machine learning algorithm with each modification on a test data set and attributing any change to the image that resulted in the change.

### Claim 2 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the machine learning algorithm is a n-layer neural network.

### Claim 3 (depends on 1)

The non-transitory computer-readable medium of claim 1, further comprising back propagating the training of the machine learning algorithm.

### Claim 4 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein assessing performance is measured by test data AUC, sensitivity, or specificity.

### Claim 5 (depends on 4)

The non-transitory computer-readable medium of claim 4, wherein assessing performance is measured by test data AUC.

### Claim 6 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the ledger is a distributed registry.

### Claim 7 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the steps (a)-(e) are repeated until a predetermined threshold of performance is reached.

### Claim 8 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the image-specific data for each image comprises patient health data.

### Claim 9 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the patient health data is selected from a group consisting of: genetic data, patient history data, electronic health record data, behavioral data, clinical outcome data, life history data.

### Claim 10 (depends on 1)

The non-transitory computer-readable medium of claim 1, wherein the image-specific data for each image comprises image source data.

### Claim 11

A method for attribution of data to an algorithm comprising:
(a) registering a pool of images on a ledger;
(b) attributing each image of the pool of images with an image-specific truth data set on the ledger;
(c) training a machine learning algorithm to one or more of the images and registering the training of the machine learning algorithm a plurality of parameters to the one or more images on the ledger;
(d) registering each modification made to the machine learning algorithm on the ledger and attributing its modification to image that resulted in the modification; and
(e) assessing performance of the machine learning algorithm with each modification on a test data set and attributing any change to the image that resulted in the change.

### Claim 12 (depends on 11)

The method of claim 11, further comprising back propagating the training of the machine learning algorithm.

### Claim 13 (depends on 11)

The method of claim 11, wherein assessing performance is measured by test data AUC, sensitivity, or specificity.

### Claim 14 (depends on 13)

The method of claim 13, wherein assessing performance is measured by test data AUC.

### Claim 15 (depends on 11)

The method of claim 11, wherein the ledger is a distributed registry.

### Claim 16 (depends on 11)

The method of claim 11, wherein the steps (a)-(e) are repeated until a predetermined threshold of performance is reached.

### Claim 17 (depends on 11)

The method of claim 11, wherein the image-specific data for each image comprises patient health data.

### Claim 18 (depends on 17)

The method of claim 17, wherein the patient health data is selected from a group consisting of: genetic data, patient history data, electronic health record data, behavioral data, clinical outcome data, life history data.

### Claim 19 (depends on 11)

The method of claim 11, wherein the image-specific data for each image comprises image source data.

### Claim 20 (depends on 11)

The method of claim 11, wherein the image-specific data for each image comprises image acquisition data.

### Claim 21 (depends on 11)

The method of claim 11, wherein the machine learning algorithm is a n-layer neural network.