Innovation of Precision Medical Service Model Driven by Big Data

Main Article Content

Fujun Wan
Xingyao Zhou
Chongbao Ren
Yuchen Zhang

Abstract

This paper proposes a precision medical service system driven by big data. The PCA-GRA-BK algorithm, which combines principal component analysis (PCA), grey association analysis (GRA) and Bayesian classifier (BK), is adopted. The algorithm extracts critical information from massive medical data, identifies patient characteristics, predicts disease risk, and provides personalized treatment plans. First, the system uses PCA technology to reduce the dimensionality of the original medical data and extract the most representative principal components to reduce data redundancy and retain critical information. Then GRA method was used to analyze the correlation between different medical indicators to determine the main factors affecting health status. Finally, the BK algorithm updates the probability model based on prior knowledge and current data to predict patients’ disease risk accurately. A simulation modeling environment is constructed and the PCA-GRA-BK algorithm is tested in this environment to verify the effectiveness of the system. The experimental results show that the algorithm has excellent performance in the accuracy of disease prediction and personalized treatment recommendation. Compared with traditional medical decision support systems, this system has shown significant advantages in extensive data processing capabilities and precision medical services.

Article Details

Section
Speciai Issue - Deep Learning in Healthcare