System and method for machine learning application for providing medical test results using visual indicia

1. A system for providing diagnostic test results, the system comprising:

a trained neural network having a plurality of inputs and at least two outputs for determining a diagnostic test result responsive to an input array; and

a server associated with the trained neural network and configured to:

receive, from a mobile device, an image of a testing device including one or more immunoassay test strips,

process the image to determine pixel count and pixel values for each pixel of each of the one or more immunoassay test strips,

create a pixel value array from the determined pixel values in the image,

provide the pixel value array as inputs in the trained neural network, and

determine diagnostic test results by the trained neural network responsive to the pixel value array provided as the inputs to the trained neural network.

2. The system of claim 1 , wherein the one or more immunoassay test strips further include a test line of one of the one or more immunoassay test strips includes Zika virus antigen and the test line of another one of the one or more immunoassay test strips includes an antibody suitable for binding with hCG.

3. The system of claim 1 , wherein the diagnostic test results include a quantitative result.

4. The system of claim 3 , wherein the quantitative result includes a reaction rating.

5. The system of claim 1 , wherein the diagnostic test results include a qualitative result.

6. The system of claim 1 , wherein the diagnostic test results include either a positive or negative result.

7. The system of claim 1 , wherein the trained neural network determines the diagnostic test results by performing a weighting function and a summing function on the pixel value array provided as the inputs to the trained neural network.

8. The system of claim 1 , wherein the trained neural network comprises:

an input layer having a plurality of input nodes for receiving the pixel value array;

at least one hidden layer having a plurality of nodes for providing a weighted sum of the inputs provided by the pixel value array; and

an output layer having a plurality of nodes providing the at least two outputs for determining the diagnostic test results responsive to the weighted sum of the inputs provided by the at least one hidden layer.

9. The system of claim 1 , wherein the server is further configured to:

create a plurality of pixel arrays from the determined pixel values in the image,

provide each of the plurality of pixel arrays as separate inputs in the trained neural network, and

determine the diagnostic test results by the trained neural network responsive to the plurality of pixel arrays provided as the inputs to the trained neural network.

10. The system of claim 1 , wherein the server is further configured to:

create a plurality of pixel arrays from the determined pixel values in the image,

downsample the plurality of pixel arrays to determine a subset of the plurality of pixel arrays,

provide each of the subset of the plurality of pixel arrays as separate inputs in the trained neural network, and

determine the diagnostic test results by the trained neural network responsive to the subset of the plurality of pixel arrays provided as the inputs to the trained neural network.

11. A method for providing diagnostic test results, the method comprising:

training a neural network having a plurality of inputs and at least two outputs for determining a diagnostic test result responsive to an input array;

receiving, by a server from a mobile device, an image of a testing device including one or more immunoassay test strips;

processing the image to determine pixel count and pixel values for each pixel of each of the one or more immunoassay test strips;

creating, by the server, a pixel value array from the determined pixel values in the image;

providing, by the server, the pixel value array as inputs in the trained neural network; and

determining, by the server, diagnostic test results by the trained neural network responsive to the pixel value array provided as the inputs to the trained neural network.

12. The method of claim 11 , wherein the one or more immunoassay test strips further include a test line of one of the one or more immunoassay test strips includes Zika virus antigen and the test line of another one of the one or more immunoassay test strips includes an antibody suitable for binding with hCG.

13. The method of claim 11 , 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 11 , wherein the diagnostic test results include a qualitative result.

16. The method of claim 11 , wherein the diagnostic test results include either a positive or negative result.

17. The method of claim 11 , wherein the step of creating further comprises the step of creating a plurality of pixel arrays from the determined pixel values in the image.

18. The method of claim 17 , wherein the step of providing further comprises the step of providing each of the plurality of pixel arrays as separate inputs in the trained neural network.

19. The method of claim 18 , wherein the step of determining further comprises the step of determining the diagnostic test results by the trained neural network responsive to the plurality of pixel arrays provided as the inputs to the trained neural network.

20. A system for providing diagnostic test results, the system comprising:

a plurality of trained neural network each associated with a different immunoassay test strip and each having a plurality of inputs and at least two outputs for determining a diagnostic test result responsive to an input array; and

a server associated with the plurality of trained neural network and configured to:

receive, from a mobile device, an image of a testing device including one or more immunoassay test strips;

process the image to determine pixel count and pixel values for each pixel of each of the one or more immunoassay test strips;

create a pixel value array from the determined pixel values for each of the one or more immunoassay test strips in the image;

provide the pixel value array as inputs in a trained neural network associated with the one or more immunoassay test strips in the image; and

determine diagnostic test results by the trained neural network responsive to the pixel value array provided as the inputs to the trained neural network.