Using machine learning to parse breast pathology reports

详细信息    查看全文

• 作者：Adam Yala ; Regina Barzilay ; Laura Salama…
• 关键词：Machine learning ; Pathology reports ; Natural language processing ; Breast pathology ; Atypia ; Hyperplasia ; Carcinoma in situ
• 刊名：Breast Cancer Research and Treatment
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：161
• 期：2
• 页码：203-211
• 全文大小：
• 刊物类别：Medicine
• 刊物主题：Oncology;
• 出版者：Springer US
• ISSN：1573-7217
• 卷排序：161

文摘

Purpose Extracting information from electronic medical record is a time-consuming and expensive process when done manually. Rule-based and machine learning techniques are two approaches to solving this problem. In this study, we trained a machine learning model on pathology reports to extract pertinent tumor characteristics, which enabled us to create a large database of attribute searchable pathology reports. This database can be used to identify cohorts of patients with characteristics of interest.