Back

Breast Cancer Survival Prediction using Machine Learning and Gene Expression Profiles

Santos, D.

2022-01-25 health informatics
10.1101/2022.01.22.22269470 medRxiv
Show abstract

Breast cancer is one of the most common cancers with a high mortality rate among women. It is also the most frequent cause of cancer death in this population, with an estimated 684,996 deaths for that year (15.5% of cancer deaths in women) (IARC, 2020). In Brazil, breast cancer is also the most common type of cancer in women from all regions, after non-melanoma skin cancer. Therefore, an accurate and reliable system is needed for the early diagnosis of this cancer. Machine learning explores the study and construction of algorithms that can learn from their mistakes and make predictions about data. The results here are excellent with an accuracy and precision level of around 79%.

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.