Name
Abstract | ||
|---|---|---|
The use of machine learning and deep learning for cancer prediction has been proven to be relevant and promising in the past. In this work, we propose a machine learning modeling approach for breast cancer prognosis with primary information about the user, such as their age and race. One of the essential aspects of machine learning application to the health domain is the ability to robustly handle the uneven distribution of output classes in the data using resampling techniques. In this paper, we present the results before and after applying resampling and observe a significant improvement as a result of handling the imbalance in the data. We employ conventional and contemporary machine learning and deep learning algorithms to predict breast cancer in women and achieve an accuracy of 92.46% on real world datasets. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/ICHI54592.2022.00036 | 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI) |
Keywords | DocType | ISSN |
Neural network,Cancer prognosis,classification,machine learning,SVM,Random Forests,Decision Trees,Nearest neighbor,Naive Baiyes,Adaboost,class imbalance,SMOTE | Conference | 2575-2626 |
ISBN | Citations | PageRank |
978-1-6654-6846-6 | 0 | 0.34 |
References | Authors | |
0 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kanika Sood | 1 | 0 | 0.34 |
| Prathyusha Gundlapally | 2 | 0 | 0.34 |