Disease predicting model construction method and device based on gradient iterative tree

Abstract

The invention discloses a disease predicting model construction method based on a gradient iterative tree. The disease predicting model construction method comprises the steps of preprocessing collected clinical data, adopting basic information and blood routine examination indexes to construct features; constructing a first predicting model based on a GBDT algorithm, labeling a data set of the first predicting model, adopting a training set to train the first predicting model, adopting grid search to adjust and optimize the parameters, and optimizing the first predicting model, wherein the first predicting model is used for predicting diseases and health conduction; constructing a second predicting model based on the GBDT algorithm, labeling a data set of the second predicting model, adopting the training set to train the second predicting model, adopting grid search to adjust and optimize the parameters, and optimizing the second predicting model, wherein the second predicting modelis used for predicting specific disease categories. By the adoption of the disease predicting model construction method, data can be rapidly labeled, the obtained disease predicting models have high predicting accuracy rate, and the predicting time is short.

Description

technical field [0001] The invention relates to the technical field of data processing of machine learning algorithms, in particular to a method for establishing a disease prediction model based on a gradient iterative tree. Background technique [0002] Disease prediction is a very important topic at present. By analyzing medical data and obtaining a prediction model, disease data can be better utilized to help doctors and individuals make disease judgments. The data modeling methods currently adopted are mainly supervised learning methods, that is, data modeling is performed according to known use cases, and unlabeled data is labeled by the model. However, there are mainly following defects: [0003] 1. Supervised learning methods generally perform data modeling on labeled data, but now the amount of effective data is very limited, and the massive amount of unlabeled data is huge, resulting in many data models that do not fit the data well or even overfit data. [0004]...

AI Technical Summary

Problems solved by technology

[0003] 1. Supervised learning methods generally perform data modeling on labeled data, but now the amount of effective data is very limited, and the massive amount of unlabeled data is huge, resulting in many data models that do not fit the data well or even overfit data

[0004] 2. Existing prediction models have low accuracy in predicting diseases

Images