Method of diagnosing biological states through the use of a centralized, adaptive model, and remote sample processing
Inventors
Chen, Tzong-Hao • Hitt, Ben A. • Levine, Peter J.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-7761239-B2
Publication Date
2010-07-20
Expiration Date
Abstract
A model of a particular biological state can be developed. The model may be used to determine if an unknown biological sample exhibits a particular biological state. This can be done by receiving either a biological sample or data associated with the biological sample. After the data is received, the data may be input into the model. In one embodiment, the acquisition of the data associated with the biological sample is performed at a first location and the imputing of the data into the model is performed at a second location different than the first location. Unless the data maps identically to the model, the data would have an inherent effect on the position of the particular clusters within the discriminatory pattern, if it is allowed to affect the model. The modeling software can keep track of the net effect on the model that each sample received has on the position of the model. If the model has drifted outside of a predetermined tolerance, the model can be updated. Various business relationships may be developed to undertake various steps of the overall method for providing a diagnosis to a patient.
Core Innovation
The invention describes methods for determining whether a diagnostic model is accurately applicable to, or sufficiently representative of, a population of subjects. The model determines a subject's biological state and is based on data streams obtained from biological samples associated with known biological states. The methods assess whether data from subjects of an unknown biological state correspond to a diagnostic cluster in a vector space.
The methods update a diagnostic cluster's centroid using data that map to the cluster, determine the distance between the initial and updated centroid locations, and compare that distance with a predetermined threshold. An output indicating that the threshold is exceeded indicates that the diagnostic model is not accurately applicable or not sufficiently representative of the relevant population. The background section and its stated problem are not included in the supplied patent content.
Claims Coverage
The supplied relevant claims identify two independent claims: claim 1 covers determining whether a diagnostic model is accurately applicable to a population, and claim 5 covers determining whether a model is sufficiently representative of a first population distinct from the population used to form the model. The claims contain two main inventive features.
Assessing diagnostic model applicability through centroid drift
Claim 1 maps a vector set from a biological sample of unknown biological state into a diagnostic model's vector space. If the vector set maps into a diagnostic cluster, the method updates the cluster centroid using the new vectors and the data streams associated with that cluster, measures the distance from the initial centroid location, and provides an output indicating when that distance exceeds a predetermined threshold.
Assessing model representation of a different population
Claim 5 assesses whether a diagnostic model based on data streams from a second population of known biological states is sufficiently representative of a first population. It maps data streams from two subjects of unknown biological state in the first population into the vector space, updates the centroid if both map into the diagnostic cluster, and provides an output when the distance between the initial and updated centroid locations exceeds a predetermined threshold.
Both independent claims evaluate a diagnostic model by measuring changes in a diagnostic cluster's centroid after data from the population to which the model is applied map into that cluster. They use a predetermined threshold to indicate whether the model is accurately applicable or sufficiently representative.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Determining a biological state of a subject using a diagnostic model, and assessing whether that model is accurately applicable to or sufficiently representative of a population of subjects.
The supplied description also documents remote collection of biological assay data and transmission to a central model server for diagnosis.
Interested in licensing this patent?