Method for diagnosing latent tuberculosis infection
AssigneeOxford Immunotec Limited
InventorDaniel Cochrane
Life of this patent
Estimating the term…
Abstract
The disclosure concerns a method of obtaining information about the disease status of an individual by processing input data using a trained machine learning algorithm model to generate an output representing the information. The disclosure also concerns a related computer program, data processing apparatus, and system, as well as a method for training a machine learning algorithm model to generate information about the disease status of an individual. The information may, for example, relate to the presence, absence or type of M. tuberculosis complex infection in the individual.
Claims11
A method to characterise a Mycobacterium tuberculosis (M. tuberculosis) complex infection present in an individual as active or latent, using a trained machine learning algorithm model stored on one or more computer-readable medium, the method comprising:
- (a) receiving from an image capture device image data of each of at least two wells of an enzyme-linked immunospot (ELISpot) assay for M. tuberculosis complex infection performed on a cell sample obtained from the individual;
- (b) generating input data by formatting the image data for conformity to be input to the trained machine learning algorithm model;
- and
- (c) processing the input data using the trained machine learning algorithm model to generate an output representing information which characterises the M. tuberculosis complex infection as active or latent.
Dependencies are inferred from the claim text.