Classification of Oncology Treatment Responses from French Radiology Reports with Supervised Machine Learning.

The present study shows first attempts to automatically classify oncology treatment responses on the basis of the textual conclusion sections of radiology reports according to the RECIST classification. After a robust and extended manual annotation of 543 conclusion sections (5-to-50-word long), and after the training of several machine learning techniques (from traditional machine learning to deep learning), the best results show an accuracy score of 0.90 for a two-class classification (non-progressive vs. progressive disease) and of 0.82 for a four-class classification (complete response, partial response, stable disease, progressive disease) both with Logistic Regression approach. Some innovative solutions are further suggested to improve these scores in the future.

Comparing a Rule Based vs. Statistical System for Automatic Categorization of MEDLINE Documents According to Biomedical Specialty.

Automatic document categorization is an important research problem in Information Science and Natural Language Processing. Many applications, including Word Sense Disambiguation and Information Retrieval in large collections, can benefit from such categorization. This paper focuses on automatic categorization of documents from the biomedical literature into broad discipline-based categories. Two different systems are described and contrasted: CISMeF, which uses rules based on human indexing of the documents by the Medical Subject Headings(®) (MeSH(®)) controlled vocabulary in order to assign metaterms (MTs), and Journal Descriptor Indexing (JDI) based on human categorization of about 4,000 journals and statistical associations between journal descriptors (JDs) and textwords in the documents. We evaluate and compare the performance of these systems against a gold standard of humanly assigned categories for one hundred MEDLINE documents, using six measures selected from trec_eval. The results show that for five of the measures, performance is comparable, and for one measure, JDI is superior. We conclude that these results favor JDI, given the significantly greater intellectual overhead involved in human indexing and maintaining a rule base for mapping MeSH terms to MTs. We also note a JDI method that associates JDs with MeSH indexing rather than textwords, and it may be worthwhile to investigate whether this JDI method (statistical) and CISMeF (rule based) might be combined and then evaluated showing they are complementary to one another.