Method and apparatus for machine error detection by combining multiple sensor inputs

Patent metadata

Field	Value
Publication number	US-9717840-B2
Application number	US-201414156901-A
Country	US
Kind code	B2
Filing date	Jan 16, 2014
Priority date	Jan 4, 2002
Publication date	Aug 1, 2017
Grant date	Aug 1, 2017

Abstract

One of the most significant safety concerns in the automation of extracorporeal blood treatments such as dialysis is the risk of blood leakage. Extracorporeal blood treatment systems draw blood at such a high rate that a loss of integrity in the blood circuit can be serious. There are a number of mechanisms for detecting and preventing leaks, but none is perfect. This tends to limit the use of such equipment in unsupervised settings, such as the home will be limited. Some leak detection schemes can be made sensitive enough to detect the barest of leaks, but when this is done, they result in too many false positives. The invention combines information from multiple inputs to enhance sensitivity in leak detection and reduce the problem of false positives.

First claim

What is claimed is:

1. A leak detection system for detecting a leak in a medical treatment system, comprising:
a camera adapted to gather video or image data; and
a medical treatment system with a controller or classifier and at least one of a flow controller, a pump, and an alarm output;
the controller or classifier having a video-image processor adapted to recognize blood in said video or image data and output state data indicating states recognized;
the controller or classifier being connected to control the at least one of the flow controller, the pump, and the alarm output responsively to said state data;
wherein the video-image processor is adapted to detect blood flowing from a leak into an open environment including one of blood staining a patient's clothes, blood pooling on a surface, and blood pooling on a floor, said state data being responsive to the detection by the video-image processor.

2. The system of claim 1 , wherein the video-image processor is adapted to recognize blood by detecting one or more blobs in a field of view of the camera.

3. The system of claim 1 , wherein the controller or classifier is connected to control the flow controller responsively to the state data.

4. The system of claim 1 , wherein the controller or classifier is connected control the pump responsively to the state data.

5. The system of claim 1 , wherein the controller or classifier is connected to control the alarm output responsively to the state data.

6. The system of claim 1 , wherein the video-image processor is adapted to recognize blood by detecting a color of a blob in a field of view of said camera.

7. A leak detection system for detecting a leak in a medical treatment system, comprising:
a camera adapted to gather video or image data; and
a medical treatment system with a controller or classifier and at least one flow controller, a pump, and an alarm output;
the controller or classifier having a video-image processor adapted to recognize blood flowing from a leak into an open environment in said video or image data and output state data indicating states recognized;
the controller or classifier being connected to apply the state data to the at least one flow controller, the pump, and the alarm output;
the controller or classifier being further adapted to control the at least one flow controller, the pump, and the alarm output responsively to the state data,
the system further comprising at least one other type of blood leak detector that outputs a second leak detection signal,
wherein the controller or classifier is configured to combine the second leak detection signal with the state data and control the at least one flow controller, pump, and alarm output responsively to a resulting combination.

8. The system of claim 7 , wherein the controller or classifier implements a Bayesian classifier or neural network.

9. The system of claim 7 , wherein the video-image processor is adapted to recognize blood staining a patient's clothes.

10. The system of claim 7 , wherein the video-image processor is adapted to recognize blood by detecting one or more blobs in a field of view of the camera.

Assignees

• Nxstage Medical Inc

Inventors

• Burbank Jeffrey H
• Brugger James M

Classifications

• A61M1/3656 Primary

  Monitoring patency or flow at connection sites; Detecting disconnections · CPC title

• A61M1/3624 Primary

  Level detectors; Level control · CPC title

• A61M1/3639

  Blood pressure control, pressure transducers specially adapted therefor · CPC title

• A61M2205/15

  Detection of leaks · CPC title

• A61M1/367

  Circuit parts not covered by the preceding subgroups of group A61M1/3621 · CPC title