System and method for machine learning application for providing medical test results using visual indicia
A method for providing diagnostic test results is provided. The method comprises providing a software application to be stored on a mobile device, the mobile device having a camera and a viewing screen, initiating operation of the camera, aligning the camera with a visual trigger associated with the diagnostic test, capturing an image of the diagnostic test, sending the image to a server, creating a pixel value array from the pixel values in the image, providing the pixel value array as inputs in a trained neural network, and providing either a positive or negative result from the trained neural network in response to the pixel value array.
1. A system for providing diagnostic test results, the system comprising:
a software application configured to be stored on a mobile device that includes a camera and a viewing screen, wherein the software application provides executable instructions that, when executed, cause the mobile device to:
initiate operation of the camera of the mobile device,
present on the viewing screen of the mobile device an alignment graphic to be aligned with an alignment target of a testing device, wherein the testing device includes a plurality of immunoassay test strips,
detect when an alignment of the alignment graphic and the alignment target has taken place,
capture an image of the testing device,
process the image to determine pixel count and line intensity of a test line of each of the plurality of immunoassay test strips,
compare one or more results of processing the image to a control for the test line of each of the plurality of immunoassay test strips, and
present results on the viewing screen; and
a server configured to:
receive, from the mobile device, the image of the testing device,
store the received image,
create a pixel value array from pixel values in the image,
provide the pixel value array as inputs in a trained neural network, and
determine diagnostic test results by the trained neural network using the pixel value array.
2. The system of claim 1 , wherein the test line of one of the plurality of immunoassay test strips includes Zika virus antigen and the test line of another one of the plurality of immunoassay test strips includes an antibody suitable for binding with hCG.
3. The system of claim 1 , wherein the control is a dataset from previously conducted tests stored on a database and accessed by the software application.
4. The system of claim 1 , wherein a control line on at least one of the plurality of immunoassay test strips is the control.
5. The system of claim 1 , wherein the diagnostic test results include a quantitative result.
6. The system of claim 5 , wherein the quantitative result includes a reaction rating.
7. The system of claim 1 , wherein the diagnostic test results include a qualitative result.
8. The system of claim 1 , wherein the diagnostic test results include either a positive or negative result.
9. A method for providing diagnostic test results, the method comprising:
initiating, by a software application stored on a mobile device that includes a camera and a viewing screen, operation of the camera of the mobile device;
presenting, by the software application on the viewing screen of the mobile device, an alignment graphic to be aligned with an alignment target of a testing device, wherein the testing device includes a plurality of immunoassay test strips;
detecting, by the software application, when an alignment of the alignment graphic and the alignment target has taken place;
capturing, by the software application using the camera of the mobile device, an image of the testing device;
processing, by the software application, the image to determine pixel count and line intensity of a test line of each of the plurality of immunoassay test strips;
comparing, by the software application, one or more results of processing the image to a control for the test line of each of the plurality of immunoassay test strips; and
presenting, by the software application, results on the viewing screen of the mobile device;
receiving, by a server from the mobile device, the image of the testing device;
storing, by the server, the received image;
creating, by the server, a pixel value array from pixel values in the image;
providing, by the server, the pixel value array as inputs in a trained neural network; and
determining, by the server, diagnostic test results by the trained neural network using the pixel value array.
10. The method of claim 9 , wherein the test line of one of the plurality of immunoassay test strips includes Zika virus antigen and the test line of another one of the plurality of immunoassay test strips includes an antibody suitable for binding with hCG.
11. The method of claim 9 , wherein the control is a dataset from previously conducted tests stored on a database and accessed by the software application.
12. The method of claim 9 , wherein a control line on at least one of the plurality of immunoassay test strips is the control.
13. The method of claim 9 , wherein the diagnostic test results include a quantitative result.
14. The method of claim 13 , wherein the quantitative result includes a reaction rating.
15. The method of claim 9 , wherein the diagnostic test results include a qualitative result.
16. The method of claim 9 , wherein the diagnostic test results include either a positive or negative result.