Automatic summarization of medical interviews

• Main Author: Qiang Jipeng
• Format: Article
• Language: English
• Published: EDP Sciences 2018-01-01
• Series: MATEC Web of Conferences
• Online Access: https://doi.org/10.1051/matecconf/201818907002

Abstract. The genomic-based targeted therapy (Crizotinib) has been emerged as an alternative option for the treatment of patients with locally advanced or metastatic non-small cell lung cancer, comprising the 85\% of lung cancer. However, Crizotinib is not listed in VA drug formulary- and is not available for VA oncologists to treat lung cancer currently. Therefore, for understanding physicians’ views on using genomic services, semi-structured interviews were collected. In this paper, we will present an innovative method to extract summarization from medical interviews automatically. Different from keyword-based method, automatic summarization can help to understand the intention of physicians. Compared with the existing summarization methods, our work is based on latent Dirichlet allocation and recent results m word embeddings that learn seinantically meaningful representations for words from local cooccurrences in sentences. Experiments on medical interviews demonstrate that the proposed algorithm achieves good results compared with a gold standard file using manual extraction technique.