PICC thrombus risk prediction method based on machine learning

Abstract

The invention discloses a PICC thrombus risk prediction method based on machine learning, and the method comprises the steps: collecting 30 features affecting PICC thrombus of each patient, and carrying out the filling of the missing values of the features; preprocessing the filled features; constructing a plurality of risk prediction models based on machine learning, and respectively calculating an F1 index, an accuracy rate, a recall rate and an AUC of each risk prediction model; determining the effect of each risk prediction model according to the F1 index, the accuracy rate, the recall rate and the AUC of each risk prediction model; selecting two risk prediction models with optimal effects; and based on the AUC values of the two risk prediction models with the optimal effects and the probability of predicting the AUC values to be 1, fusing the two risk prediction models with the optimal effects, and outputting a PICC thrombus risk prediction result. Precise recognition of thrombus occurrence risks is achieved, treatment or nursing measures are taken in advance to conduct medicine or physical intervention on high-risk patients, and therefore the probability of thrombus occurrence of the patients is reduced.

Description

technical field [0001] The invention belongs to the technical field of machine learning and computer application, in particular to a PICC thrombosis risk prediction method based on machine learning. Background technique [0002] Machine learning is a general term for a class of algorithms that aim to mine hidden laws from a large amount of data and use them for prediction or classification. More specifically, machine learning can be seen as looking for a function whose input is sample data , the model is constructed through different algorithms, and the output obtained is the expected result. [0003] Random forest is widely used to fill in missing values. It can handle very high-dimensional (many features) data without feature selection (feature column sampling); after training, it can return the importance of features; while training, trees and trees They are independent of each other and easy to parallelize; they can handle missing features. Principal Component Analysis...

AI Technical Summary

Problems solved by technology

Post-thrombosis syndrome (PTS) caused by the late stage of thrombosis hinders the function of the venous valve, leading to pain, swelling and dysfunction of the affected limb, which affects the quality of life of patients; The main reason of management, thus prolonging the hospitalization time of patients, increasing hospitalization expenses, etc.

Images