Prediction of survival and metastasis in breast cancer patients using machine learning classifiers
Problem
Predicting survival and metastasis in breast cancer patients accurately enough to improve early diagnosis and treatment decisions.
Why it matters
Accurate prediction of survival and metastasis can guide treatment and increase patient survival.
What the AI did
Eight machine learning techniques (NB, RF, AdaBoost, SVM, LSSVM, Adabag, LR, LDA) were compared on records of 550 breast cancer patients to predict survival and metastasis.
Results
Average specificity of all techniques ≥94% for survival prediction; abstract truncated before further metrics.
Impact
Shows ML classifiers can predict breast cancer survival with high specificity on one 550-patient dataset.
Record
| Venue | Clinical Epidemiology and Global Health |
|---|---|
| Published | 2018 |
| Work type | article |
| Authors | Leili Tapak, Nasrin Shirmohammadi‐Khorram, Payam Amini, Behnaz Alafchi, Omid Hamidi, Jalal Poorolajal |
| Citations | 116 (OpenAlex, at import time) |
| References | 39 |
| Model or method | NB, RF, AdaBoost, SVM, LSSVM, Adabag, LR, LDA |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1016/j.cegh.2018.10.003 |
| Open access | hybrid |
| Keywords | machine learning, breast cancer, survival prediction, metastasis, classifiers |
Importance rating
major — millions of lives, an industry or a field
Abstract states breast cancer is one of the most common malignancies in women and that accurate early diagnosis/metastasis prediction can raise survival, implying large-scale patient benefit.