Model and system for predicting benign and malignant pulmonary nodules based on platelet parameters

Abstract

The invention discloses a model for predicting benign and malignant pulmonary nodules based on platelet parameters. The model comprises the following steps: S1, collecting clinical data, imaging data, blood routine result data and pathological examination data of operations and postoperative tissues of pulmonary nodule patients; s2, sorting the clinical data, the imaging data, the blood routine result data and the pathological examination data of operation and postoperative tissues, and establishing a diagnosis model for distinguishing benign and malignant pulmonary nodules through XGBoost i ng according to the sorted data; s3, making the diagnosis model into a webpage; s4, inputting clinical data information of a pulmonary nodule patient, iconography data information obtained by LDCT, platelet parameter information in a blood routine result, surgical pathological examination information and standard index information into the diagnosis model webpage; and S5, the diagnosis model webpage calculates and outputs the malignant probability of the pulmonary nodules of the pulmonary nodule patient according to the input information.

Description

technical field [0001] The invention relates to the technical field of lung cancer diagnosis, in particular to a model and system for predicting benign and malignant pulmonary nodules based on platelet parameters. Background technique [0002] At present, lung cancer has become the malignant tumor with the highest morbidity and mortality in my country. Screening and early diagnosis and early treatment are effective ways for secondary prevention of tumors. Low-dose spiral CT (LDCT) is currently a commonly used method for lung cancer screening. Studies have confirmed that LDCT screening for high-risk groups can reduce the mortality rate by 20%. However, LDCT is not easy to distinguish benign nodules with small diameter from malignant nodules, and the diagnosis is prone to false positives. Usually when encountering such small nodules that cannot be judged, clinicians will choose surgical resection, but some of the resected patients are pathologically diagnosed as benign after ...

AI Technical Summary

Problems solved by technology

However, LDCT is not easy to distinguish benign nodules with small diameters from malignant nodules, and the diagnosis is prone to false positives.

Usually when encountering such small nodules that cannot be judged, clinicians will choose surgical resection, but some of the resected patients are pathologically diagnosed as benign after surgery, which brings unnecessary treatment to patients with benign nodules

Moreover, LDCT has high requirements for instruments and personnel, and its role in remote areas is limited

Images