Back

Survival Clustering web-based application: A deeper look at risk profiles for METABRIC

Gu, Y.; Wang, M.; Gong, Y.; Jiang, S.; Li, Z.; Zhang, D.

2023-06-13 oncology
10.1101/2023.05.18.23290062 medRxiv
Show abstract

Online tools, such as web-based applications, aid medical doctors in recommending treatments and conducting thorough patient profile investigations. Prior studies have created web-based survival analysis tools for cancer survival. However, these often offer basic features and simplistic models, providing shallow data insights. Our research involves an in-depth risk profile analysis using survival clustering on real-world data. Weve developed a user-friendly Shiny application to simplify the use of our findings. By utilizing survival clustering, we uncover distinct subgroups and unique risk profiles among breast cancer patients. Our online app empowers researchers and clinicians to explore and gain insights into breast cancer risk profiles, enhancing personalized medicine and clinical decision-making.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.