Method and system for predicting pathological complete remission probability after breast cancer neoadjuvant chemotherapy

Abstract

The invention discloses a pathological complete remission probability prediction method after breast cancer neoadjuvant chemotherapy. The method comprises the following steps: S1, forming a training set; S2, screening out independent prediction factors; S3, obtaining a weight score; S4, analyzing and calculating a probability prediction value of pathological complete remission after breast cancerneoadjuvant chemotherapy. The invention further discloses a computer readable storage medium, a computer program is stored on the computer readable storage medium, and when the program is executed bythe processor, the step S1-S4 is achieved. The invention further discloses a system for predicting the pathological complete remission probability after breast cancer neoadjuvant chemotherapy. The system comprises a training set generation module, a multi-factor regression analysis screening module, a column diagram model construction and display module, a weight score generation module and a netincome analysis module. According to the invention, patients with low profit possibility can be screened out, and the patients are finally free from neoadjuvant chemotherapy.

Description

technical field [0001] The present invention relates to the field of medical information technology, in particular to a method for predicting the probability of pathological complete remission after neoadjuvant chemotherapy for breast cancer, a prediction system, a computer-readable storage medium equipped with a program for executing the prediction method, and neoadjuvant chemotherapy for breast cancer. A method for constructing a predictive model for the probability of pathological complete remission after chemotherapy. Background technique [0002] Breast cancer is one of the main malignant tumors threatening women's health around the world, and about 70% of breast cancers are hormone receptor positive. Neoadjuvant chemotherapy can reduce the size of the tumor so as to achieve the purpose of breast-conserving surgery and drug sensitivity monitoring in breast cancer. However, unlike hormone receptor-negative breast cancer, hormone receptor-positive breast cancer has a rel...

AI Technical Summary

Problems solved by technology

[0003] The above multigene models predicting the probability of NAC-induced pCR in HR+ breast cancer has not been widely used in clinical practice, and the use of multigene models such as Oncotype DX and PAM50 to predict the probability of NAC-induced pCR still has some shortcomings

First, few models in current studies have shown strong predictive value for pCR after NAC, with low diagnostic power

Second, polygenic model testing is expensive, and is mostly used to assist in the decision-making of postoperative adjuvant therapy, and it is difficult to promote

Third, current polygenic models do not include individualized information such as imaging

Images