Using machine learning for healthcare treatment planning

Snigdha Dubey, Gaurav Tiwari, Sneha Singh, Saveli Goldberg, Eugene Pinsky

Abstract: We present a methodology for using machine learning for planning treatments. As a casestudy, we apply the proposed methodology to Breast Cancer. Most of the applications of MachineLearning to breast cancer has been on diagnosis and early detection. By contrast, our paperfocuses on applying Machine Learning to suggest treatment plans for patients with differentdisease severity. While the need for surgery and even its type is often obvious to a patient, theneed for chemotherapy and radiation therapy is not as obvious to the patient. With this in mind, thefollowing treatment plans were considered in this study: chemotherapy, radiation, chemotherapywith radiation, and none of these options (only surgery). We use real data from more than 10,000patients over five years, which includes detailed cancer information, treatment plans, and survivalstatistics. Using this data set, we construct Machine Learning classifiers to suggest treatmentplans. Our emphasis in this effort is not only on suggesting the treatment plan but on explainingand defending a particular treatment choice to the patient.

External IDs:dblp:journals/frai/DubeyTSGP23