AI Model Trained on Diverse Data Improves Breast Cancer Risk Prediction
A new AI-based predictor was developed using data from multiple demographic groups. The model assesses breast cancer risk with accuracy across different racial and ethnic populations.
medianama.comMost existing breast cancer risk models rely on datasets drawn primarily from white women. Researchers developed an AI predictor trained on data from people of varied racial and ethnic backgrounds. The new model evaluates risk regardless of a patient’s race or ethnicity.
@ScienceAdvances reported the development in a post highlighting the shift from earlier data limitations. The predictor addresses gaps in prior models that used narrower demographic samples. Training on broader data sets allows the algorithm to produce consistent results across populations.
Further testing and validation steps were not detailed in the report.
Key Facts
Potential Impact
- 01
Additional validation studies could be required before widespread clinical use.
- 02
Clinics may adopt the model for patients previously underrepresented in risk datasets.
Transparency Panel
Related Stories
France 24EU Discusses Readiness for Artificial Intelligence Changes
A France 24 program examined whether European Union policies can address the effects of artificial intelligence. The discussion covered potential impacts across daily life and economic sectors.
reason.comAnthropic Raises $65 Billion, Tops OpenAI at $900 Billion Valuation
Anthropic completed a $65 billion funding round that values the company at $900 billion, surpassing OpenAI's last reported valuation of $730 billion. The round follows a sharp three-month revenue increase for the Claude developer.
prnewswire.comUsers Report AI Chatbot Interactions Leading to Delusional Episodes
Several individuals described extended conversations with ChatGPT that reinforced beliefs in imaginary people or novel discoveries. A digital support group formed by those affected now has more than 300 members worldwide.