Related Experiment Video
Updated: Jun 28, 2026
05:49
Use of Magnetic Resonance Imaging and Biopsy Data to Guide Sampling Procedures for Prostate Cancer Biobanking
Published on: October 10, 2019
6.8K
Based on biomedical index data: Risk prediction model for prostate cancer
Hanxu Guo1, Xianjie Jia2, Hao Liu3
1School of Clinical Medicine, Bengbu Medical College.
Medicine
|April 28, 2021
Summary
This study developed a prostate cancer risk prediction model using biochemical markers. High Apo lipoprotein E indicates increased risk, while high triglycerides suggest a protective effect, aiding preliminary diagnosis.
Area of Science:
- Biomedical Informatics
- Oncology
- Medical Diagnostics
Background:
- Prostate cancer diagnosis relies on various factors, necessitating improved risk stratification tools.
- Accurate prediction models can assist clinicians in preliminary diagnosis and treatment planning.
Purpose of the Study:
- To identify key influencing factors for prostate cancer occurrence.
- To establish a robust risk prediction model for prostate cancer.
- To provide a diagnostic reference for clinical doctors.
Main Methods:
- Utilized data from prostate cancer and hyperplasia patients from the National Clinical Medical Science Data Center.
- Employed propensity score matching (PSM) to balance group biases.
- Applied stepwise logistic regression and artificial neural network (ANN) analysis to identify relevant factors and build models.
- Evaluated model accuracy using receiver operating characteristic (ROC) curves.
Main Results:
- After 1:2 PSM, 339 pairs were successfully matched.
- Developed a logistic regression model and an ANN model with high predictive accuracy (ROC: 0.963 and 0.983, respectively).
- Identified high Apo lipoprotein E (Apo E) as a significant risk factor (OR: 1.535) and high triglyceride (TG) as a protective factor (OR: 0.288).
Conclusions:
- Biochemical examination markers can effectively establish a prostate cancer risk prediction model.
- The developed model offers a valuable tool for preliminary risk assessment and clinical decision-making.
- Further research can refine these models for enhanced diagnostic capabilities.
