Related Experiment Video
Updated: Aug 5, 2025
06:46
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
313
A Clinical Prediction Model for Breast Cancer in Women Having Their First Mammogram
Piyanun Wangkulangkul1, Suphawat Laohawiriyakamol1, Puttisak Puttawibul1
1Department of Surgery, Faculty of Medicine, Prince of Songkla University, Songkhla 90110, Thailand.
Healthcare (Basel, Switzerland)
|March 29, 2023
Summary
This study developed a breast cancer prediction model to prioritize women awaiting mammograms. Key factors include age, BMI, family history, and symptoms like nipple discharge, improving access in underserved areas.
Area of Science:
- Oncology
- Radiology
- Biostatistics
Background:
- Digital mammography is crucial for breast cancer (BC) detection but faces accessibility issues in rural areas.
- Prioritizing patients on waiting lists is essential for timely diagnosis and treatment.
- A predictive model can help optimize resource allocation for mammography screening.
Purpose of the Study:
- To construct a predictive model for breast cancer (BC) risk in women undergoing their first mammogram.
- To identify key clinical factors for prioritizing patients on mammography waiting lists.
- To enhance BC screening efficiency in resource-limited settings.
Main Methods:
- Retrospective analysis of breast clinic data (January 2013 - December 2017).
- Stepwise multiple logistic regression used to build predictive models based on significant BC risk factors.
- Receiver operating characteristic (ROC) curves evaluated model discriminative capability (AUC).
Main Results:
- Analysis included 822 women using inverse probability weighting.
- Significant BC risk factors identified: age, BMI, family history, and symptoms (mass, nipple discharge).
- The predictive model achieved an AUC of 0.82 (95% CI: 0.76-0.87).
Conclusions:
- Prioritize patients with nipple discharge or mass for mammograms.
- Consider older patients, those with high BMI, and those with a family history of BC.
- This model aids in efficient patient prioritization for mammography in resource-limited settings.
