Hormonal therapy is an effective, but challenging, long-term treatment for patients with hormone-receptor-positive breast cancer. Raising the rate of patients who initiate therapy may be possible by characterizing the factors that influence a patient’s decision. We hypothesized that online patient portal messages convey such factors. To investigate this hypothesis, we focused on breast cancer patients who were prescribed hormonal therapy at Vanderbilt University Medical Center and sent messages through the portal between diagnosis and therapy initiation. We first conducted a topic modeling analysis to generate the main themes of portal messages. We subsequently applied survival analysis to learn the association between the factors conveyed in messages, in term of semantic word groups, and the time elapsed from diagnosis to therapy initiation. We found that consulting with healthcare providers increased the probability of therapy initiation, while mentions of symptoms or negative emotions exhibited a reduced probability.

Learning Objective: 1. Learning how to generate interpretable factors from free text using Natural language processing techniques.
2. Learning how to apply survival analysis to study the association between the portal messages and the start of hormonal therapy for breast cancer patients.

Authors:

Zhijun Yin (Presenter)
Vanderbilt University

Jeremy Warner, Vanderbilt University
Qingxia Chen, Vanderbilt University
Bradley Malin, Vanderbilt University

Presentation Materials:

• Abstract/Manuscript - 1