Testing a biological sample based on sample spectrography and machine learning techniques

1. A computer-implemented method comprising:

receiving, by a computing device, data corresponding to a dynamic speckle spectrum image associated with a biological sample;

comparing, by the computing device, the dynamic speckle spectrum image with a plurality of training images;

classifying, by the computing device, a contaminant present in the biological sample, based on the comparing; and

executing, by the computing device, an instruction based on the classifying the contaminant,

further comprising receiving metadata associated with the biological sample, wherein the classifying the contaminant is further based on the metadata,

wherein the classifying compromises matching the dynamic speckle spectrum image and the metadata with a closet one of the plurality of training images and an associated metadata set.

2. The computer-implemented method of claim 1 , further comprising building a repository of the plurality of training images to be used for the classifying, the building the repository comprising:

receiving respective dynamic speckle spectrum images of samples having known contaminants; and

storing information associating the respective dynamic speckle spectrum images with corresponding known contaminants.

3. The computer-implemented method of claim 2 , further comprising storing the dynamic speckle spectrum image of the biological sample and information regarding the classification of the contaminant present in the biological sample in the repository to aid in classification of future biological samples.

4. The computer-implemented method of claim 1 , wherein the biological sample is a fluid.

5. The computer-implemented method of claim 1 , further comprising selecting the instruction from a plurality of instructions, based on the classification of the contaminant.

6. The computer-implemented method of claim 1 , wherein the instruction includes at least one selected from the group consisting of:

controlling the operations of a treatment device;

providing an alert having information regarding the contaminant;

outputting information regarding the classification of the contaminant;

executing a smart contract; and

scheduling an appointment with a medical provider.

7. A computer-implemented method comprising:

storing, by a computing device, a plurality of training images in a blockchain;

storing, by the computing device, metadata associated with the plurality of training images in the blockchain;

receiving, by the computing device, data corresponding to a dynamic speckle spectrum image associated with a biological sample;

comparing, by the computing device, the dynamic speckle spectrum image with the plurality of training images;

classifying, by the computing device, a contaminant present in the biological sample, based on the comparing; and

executing, by the computing device, an instruction based on the classifying the contaminant.

8. The computer-implemented method of claim 1 , wherein the data corresponding to the dynamic speckle spectrum image is received from a portable sampling apparatus.

9. The computer-implemented method of claim 1 , wherein a service provider at least one of creates, maintains, deploys and supports the computing device.

10. The computer-implemented method of claim 1 , wherein the receiving the data corresponding to the dynamic speckle spectrum image, the comparing the dynamic speckle spectrum image, and the classifying the contaminant are provided by a service provider on a subscription, advertising, and/or fee basis.

11. The computer-implemented method of claim 1 , wherein the computing device includes software provided as a service in a cloud environment.

12. The computer-implemented method of claim 1 , further comprising deploying a system, wherein the deploying the system comprises providing a computer infrastructure operable to perform the receiving the data corresponding to the dynamic speckle spectrum image, the comparing the dynamic speckle spectrum image, and the classifying the contaminant.

13. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a sampling device to cause the computing device to:

perform a speckle analysis on a biological sample by passing a laser through the biological sample and detecting a dynamic speckle pattern using a photodiode array, wherein the photodiode array takes a composite of plural images in a time domain to produce the dynamic speckle pattern; and

provide data from the speckle analysis to a server device to cause the server device to:

classify a contaminant present within the biological sample by comparing a dynamic speckle spectrum image associated with the speckle analysis with a plurality of training images, and

execute an instruction based on the classifying the contaminant.

14. The computer program product of claim 13 , further comprising providing metadata associated with the biological sample to cause the server device to classify the contaminant further based on the metadata.

15. The computer program product of claim 13 , further comprising providing data for respective dynamic speckle spectrum images of samples having known contaminants to cause the server device to store information associating the respective dynamic speckle spectrum images with corresponding known contaminants for classifying the biological sample.

16. The computer program product of claim 13 , wherein the biological sample is a fluid.

17. The computer program product of claim 13 , wherein data corresponding to the plurality of training images is stored in a blockchain and the information regarding the classification of the contaminant is stored in the blockchain.

18. The computer program product of claim 13 , wherein the providing data from the speckle analysis to the server device to causes the server device to filter the data from the speckle analysis using a Fast Fourier Transforms (FFT).

19. The computer-implemented method of claim 1 , wherein the metadata is received from one or more Intent of Things (IoT) devices.

20. The computer-implemented method of claim 1 , further comprising:

tracking deviations in dynamic speckle spectrum images from previous classifications; and

updating the training images, based on the tracking, as the dynamic speckle spectrum of the contaminant evolves.