Methods for determining disease risk combining downsampling of class-imbalanced sets with survival analysis

Abstract

A method for downsampling class-imbalanced sets with survival analysis comprising: acquiring a class-imbalanced data set, wherein the class-imbalanced data set comprises biological data from a plurality of subjects, wherein the biological data of each subject includes an observation, a time value, and a plurality of clinical measurements, and wherein the biological data is categorized as being part of a majority data class or a minority data class, wherein the majority data class has a greater number of observations than the minority data class; downsampling the class-imbalanced data set, wherein the downsampling results in the majority data class having an equivalent or substantially equivalent number of observations as the minority data class; and performing cross-validation on the downsampled data set with a survival analysis to generate a survival model, wherein the observation comprises an event or no event at a specific time value.

Description

[0001] Cross References to Related Applications

[0002] This application claims priority to U.S. Provisional Patent Application No. 62 / 773,028, filed November 29, 2018, and U.S. Provisional Patent Application No. 62 / 783,733, filed December 21, 2018, which are incorporated by reference in their entirety into this article. technical field

[0003] The present disclosure relates generally to the field of disease risk determination, and more particularly, to systems and methods for processing electronic data to determine disease risk. Background technique

[0004] Methods for identifying biomarkers associated with the risk of various disease-related conditions or events (e.g., cardiovascular events, diabetes diagnoses, various cancer types, etc.) have improved, mainly due to the discovery of high-throughput techniques , such as gene sequencing, transcriptomics, proteomics, and metabolomics. However, these techniques also complicate matters by providing high-dimensional data r...

Images