RT Journal Article
SR Electronic
T1 Using Machine Learning to Parse Breast Pathology Reports
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 079913
DO 10.1101/079913
A1 Adam Yala
A1 Regina Barzilay
A1 Laura Salama
A1 Molly Griffin
A1 Grace Sollender
A1 Aditya Bardia
A1 Constance Lehman
A1 Julliette M. Buckley
A1 Suzanne B. Coopey
A1 Fernanda Polubriaginof
A1 Judy E. Garber
A1 Barbara L. Smith
A1 Michele A. Gadd
A1 Michelle C. Specht
A1 Thomas M. Gudewicz
A1 Anthony Guidi
A1 Alphonse Taghian
A1 Kevin S. Hughes
YR 2016
UL http://biorxiv.org/content/early/2016/10/10/079913.abstract
AB 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.Methods We collected a total of 91,505 breast pathology reports from three Partners hospitals: Massachusetts General Hospital (MGH), Brigham and Womens Hospital (BWH), and Newton-Wellesley Hospital (NWH), covering the period from 1978 to 2016. We trained our system with annotations from two datasets, consisting of 6,295 and 10,841 manually annotated reports. The system extracts 20 separate categories of information, including atypia types and various tumor characteristics such as receptors. We also report a learning curve analysis to show how much annotation our model needs to perform reasonably.Results The model accuracy was tested on 500 reports that did not overlap with the training set. The model achieved accuracy of 90% for correctly parsing all carcinoma and atypia categories for a given patient. The average accuracy for individual categories was 97%. Using this classifier, we created a database of 91,505 parsed pathology reports.Conclusions Our learning curve analysis shows that the model can achieve reasonable results even when trained on a few annotations. We developed a user-friendly interface to the database that allows physicians to easily identify patients with target characteristics and export the matching cohort. This model has the potential to reduce the effort required for analyzing large amounts of data from medical records, and to minimize the cost and time required to glean scientific insight from this data.