Methods for processing or analyzing a sample of thyroid tissue
Inventors
Kennedy, Giulia C. • Chudova, Darya I. • Wang, Eric T. • Wilde, Jonathan I.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10236078-B2
Publication Date
2019-03-19
Expiration Date
Abstract
The present disclosure provides methods for processing or analyzing a sample of tissue of a subject, to generate a classification of the sample of tissue as positive or negative for thyroid cancer. The present disclosure also provides algorithms and methods of classifying cancer, for example, thyroid cancer, methods of determining molecular profiles, and methods of analyzing results.
Core Innovation
The invention provides a method for processing or analyzing a sample of tissue of a subject having or suspected of having thyroid cancer. A first portion of the tissue is subjected to cytological testing that indicates that the first portion is indeterminate, and after indeterminate cytology is identified, gene expression products from a second portion are assayed to yield a data set corresponding to levels of said gene expression products.
The assay is performed by sequencing, array hybridization, or nucleic acid amplification. The resulting data set does not include a plurality of technical factor variables, and the data including the levels of the gene expression products is input to a trained algorithm in a programmed computer to generate a classification of the sample as positive or negative for the thyroid cancer, with an accuracy of at least 90%.
The method concludes by electronically outputting a report that identifies the classification of the sample as positive or negative for thyroid cancer. The document also describes Trident Analysis, defined as a union of three discovery sub-analyses including Repeatable, Bayes, and Tissue, which supports the generation of marker information distinguishing thyroid cancer subtypes and benign versus malignant cases.
Claims Coverage
The partial content provides one independent claim. The inventive features revolve around indeterminate-cytology triage, gene-expression measurement without technical factor variables, application of a trained algorithm achieving at least 90% accuracy, and electronic reporting of a positive/negative classification for thyroid cancer.
Indeterminate cytological testing followed by gene expression products assaying
Subjecting a first portion of the tissue to cytological testing indicating that the first portion is indeterminate, and after identifying the tissue as indeterminate, assaying gene expression products from a second portion to yield a data set including data corresponding to levels of said gene expression products.
Gene-expression data set lacking technical factor variables
Generating and using a data set that does not include a plurality of technical factor variables.
Trained algorithm classification with at least 90% accuracy
Inputting the data including said levels of said gene expression products to a trained algorithm to generate a classification of the sample as positive or negative for said thyroid cancer with an accuracy of at least 90%.
Electronic output report identifying the classification
Electronically outputting a report that identifies the classification of the sample of tissue as positive or negative for said thyroid cancer.
Across the independent claim, the classification system is grounded in first identifying indeterminate cytology, then assaying gene expression products to form a technical-factor-free data set, and using a trained algorithm to output an electronic positive/negative thyroid cancer classification with at least 90% accuracy.
Stated Advantages
Provides classification of thyroid cancer as positive or negative with accuracy of at least 90%.
Documented Applications
Thyroid cancer diagnosis/diagnostic classification of tissue when cytology is indeterminate, producing an electronically output report indicating positive or negative for thyroid cancer.
Interested in licensing this patent?