MACHINE LEARNING CLASSIFICATION OF LUNG NODULES BASED ON GENE EXPRESSION

摘要

The present disclosure provides systems and methods for machine learning classification of lung nodules based on gene expression data and clinical characteristics data. The method can include, a) obtaining a data set containing gene expression measurements of a biological sample from a patient of at least two lung disease-associated genes, and clinical characteristics data of one or more clinical characteristics of the patient; b) providing the data set as an input to a machine-learning model trained to generate an inference of whether the data set is indicative of a malignant lung nodule or a benign lung nodule; c) receiving, as an output of the machine-learning model, the inference indicating whether the data set is indicative of the malignant lung nodule or the benign lung nodule; and d) electronically outputting a report classifying the lung nodule of the patient as the malignant lung nodule or the benign lung nodule.