Human body aging degree intelligent evaluation method based on physical examination data

The invention provides a physical examination data-based human body aging degree intelligent evaluation method. The method comprises the following steps of: obtaining physical examination data of an individual without age-related diseases and performing quality control; eliminating irrelevant and collinear variables through an LASSO method; dividing the data set into a training set and a test set, and training the data set by using a generalized linear model (GLM), a support vector machine (SVM) and a generalized linear model (DeepGLM) based on a feedforward neural network to obtain a human body biological age prediction model; evaluating the prediction model by using the test set data, and calculating the difference (delta age) between the prediction age and the time sequence age; and constructing empirical distribution of delta age corresponding to each time sequence age by taking the time sequence age +/-5 years as an analysis interval. The delta age of an individual needing to be detected is calculated, t