# US 2026/0094705 A1 · Systems and methods for computer vision fault detection in dialysis apparatus

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

- Number: US 2026/0094705 A1
- Document ID: US20260094705A1
- Status: Published application
- Kind: A1
- Application number: 19/251,077
- Filed: 2025-06-26
- Published: 2026-04-02
- Earliest claimed: 2024-06-27
- Assignees: Mozarc Medical US LLC
- Applicants: Mozarc Medical US LLC
- Inventors: Murugavel SWAMINATHAN; Bindhu ANJANEYA; Sharath NAGENDRA
- Web page: https://patentgrep.com/patent/US20260094705A1

## CPC

- G16H 40/60: for the operation of medical equipment or devices
- G06T 7/0012: {Biomedical image inspection}
- G06V 10/255: {Detecting or recognising potential candidate objects based on visual cues, e.g. shapes}
- G06T 2207/20081: Training; Learning
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Systems and methods of the present disclosure enable fault risk detection in renal care systems and/or devices, by receiving, from an image sensor, an image of a component of the renal care system/device and using a fault risk detection machine learning model to output a detected fault risk in the component based at least in part on trained machine learning model parameters configured, through training, to classify the detected fault risk as matching to one or more known fault risks. An alert is generated to an operator or technician of the renal care system/device, including an indication of the detected fault risk.

## Claims

### Claim 1

A method comprising:
receiving, by at least one processor from at least one image sensor positioned on a renal care device, at least one image of at least one component of the renal care device;
inputting, by the at least one processor, the at least one image into a fault risk detection machine learning model to output at least one detected fault risk in the at least one component based at least in part on trained machine learning model parameters;
wherein the trained machine learning model parameters are configured, through training, to classify the at least one detected fault risk as matching to at least one known fault risk;
wherein the training comprises:
inputting a plurality of training images into the fault risk detection machine learning model, the plurality of training images comprising known fault risks to the at least one component of the renal care device, and
updating a plurality of machine learning model parameters based at least in part on the plurality of training images and the known fault risks so as to produce the trained machine learning model parameters;
generating, by the at least one processor, at least one alert to at least one operator of the renal care device, the at least one alert comprising an indication of the at least one detected fault risk; and
controlling, by the at least one processor, the renal care device to terminate operation of the at least one component in response to the at least one detected fault risk.

### Claim 2 (depends on 1)

The method of claim 1, further comprising generating, by the at least one processor, at least one control signal to the renal care device based at least in part on the at least one detected fault risk, the at least one control signal being configured to modify operation of the renal care device to mitigate the at least one detected fault risk.

### Claim 3 (depends on 2)

The method of claim 2, wherein the at least one control signal comprising a power control signal configured to switch the at least one component off.

### Claim 4 (depends on 1)

The method of claim 1, wherein the fault risk detection machine learning model comprises at least one clustering algorithm.

### Claim 5 (depends on 1)

The method of claim 1, wherein the fault risk detection machine learning model comprises at least one neural network classifier.

### Claim 6 (depends on 1)

The method of claim 1, wherein the at least one detected fault risk comprises at least one fault risk classification identifying a type of fault risk.

### Claim 7 (depends on 6)

The method of claim 6, wherein the at least one fault risk classification comprises condensation on the at least one component.

### Claim 8 (depends on 6)

The method of claim 6, wherein the at least one fault risk classification comprises corrosion on the at least one component.

### Claim 9 (depends on 1)

The method of claim 1, further comprising transmitting, by the at least one processor, the at least one alert to at least one service technician, the at least one alert comprising renal care device data for identifying the renal care device for service.

### Claim 10 (depends on 1)

The method of claim 1, wherein the fault risk detection machine learning model is configured to determine a similarity measure between the at least one image and each training image of the plurality of training images, and output the at least one detected fault risk where the similarity measure exceeds a predetermined threshold.

### Claim 11

A system comprising:
a renal care device comprising at least one component;
at least one image sensor, and
at least one processor, wherein the at least one processor is configured to perform steps to:
receive, from at least one image sensor positioned on a renal care device, at least one image of at least one component of the renal care device;
input the at least one image into a fault risk detection machine learning model to output at least one detected fault risk in the at least one component based at least in part on trained machine learning model parameters;
wherein the trained machine learning model parameters are configured, through training, to classify the at least one detected fault risk as matching to at least one known fault risk;
wherein the training comprises:
inputting a plurality of training images into the fault risk detection machine learning model, the plurality of training images comprising known fault risks to the at least one component of the renal care device, and
updating a plurality of machine learning model parameters based at least in part on the plurality of training images and the known fault risks so as to produce the trained machine learning model parameters;
generate at least one alert to at least one operator of the renal care device, the at least one alert comprising an indication of the at least one detected fault risk; and
control the renal care device to terminate operation of the at least one component in response to the at least one detected fault risk.

### Claim 12 (depends on 11)

The system of claim 11, wherein the at least one processor is further configured to perform steps to generate at least one control signal to the renal care device based at least in part on the at least one detected fault risk, the at least one control signal being configured to modify operation of the renal care device to mitigate the at least one detected fault risk.

### Claim 13 (depends on 12)

The system of claim 12, wherein the at least one control signal comprising a power control signal configured to switch the at least one component off.

### Claim 14 (depends on 11)

The system of claim 11, wherein the fault risk detection machine learning model comprises at least one clustering algorithm.

### Claim 15 (depends on 11)

The system of claim 11, wherein the fault risk detection machine learning model comprises at least one neural network classifier.

### Claim 16 (depends on 11)

The system of claim 11, wherein the at least one detected fault risk comprises at least one fault risk classification identifying a type of fault risk.

### Claim 17 (depends on 16)

The system of claim 16, wherein the at least one fault risk classification comprises condensation on the at least one component.

### Claim 18 (depends on 16)

The system of claim 16, wherein the at least one fault risk classification comprises corrosion on the at least one component.

### Claim 19 (depends on 11)

The system of claim 11, wherein the at least one processor is further configured to perform steps to transmit the at least one alert to at least one service technician, the at least one alert comprising renal care device data for identifying the renal care device for service.

### Claim 20 (depends on 11)

The system of claim 11, wherein the fault risk detection machine learning model is configured to determine a similarity measure between the at least one image and each training image of the plurality of training images, and output the at least one detected fault risk where the similarity measure exceeds a predetermined threshold.
