Risk Stratification for Screening Mammography: Benefits and Harms.

Area of Science:

• Oncology
• Medical Informatics

Background:

• Current breast cancer risk assessment models are often complex and difficult to use.
• Existing models utilize varied risk factors and weighting, leading to inconsistent patient results.
• Few models incorporate mammographic breast density, a key risk indicator.

Purpose of the Study:

• To compare prevalent breast cancer risk assessment models.
• To discuss the application of machine learning and big data in breast cancer risk prediction.
• To summarize the benefits and harms of risk-based breast cancer screening.

Main Methods:

• Comparative analysis of existing breast cancer risk assessment models.
• Review of machine learning and big data methodologies for risk prediction.
• Synthesis of literature on risk-based screening guidelines.

Main Results:

• Common breast cancer risk models present usability challenges and yield variable outcomes.
• Lack of standardization in risk factors and weighting across models.
• Limited inclusion of crucial factors like mammographic breast density in current models.

Conclusions:

• There is a need for more generalizable and user-friendly breast cancer risk prediction tools.
• Improved models are essential for effective clinical decision-making in breast cancer screening.
• Future research should focus on developing simpler, more inclusive risk assessment strategies.