Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Mar 24;2022:baac019. doi: 10.1093/database/baac019

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022. Published by Oxford University Press.

This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.

PMC Copyright notice

Figure 2. — Performance improvement of the text mining channel. As shown in the ROC curves, text mining performs markedly better in the new version of DISEASES (Dict2,FullText2021) compared to the originally published one (Dict1,PubMed2013). To quantify the sources of improvements, we show two additional curves: one using the new dictionary on the latest abstract collection only (Dict2,PubMed2021) and another using the old dictionary on the same abstracts (Dict1,PubMed2021). Comparing the curves reveals that most of the improvement stems from the addition of full-text articles, but that the new disease and gene dictionaries also led to considerable improvement. By contrast, the growth in PubMed abstracts from 2013 to 2021 made only a minor difference. The insert shows a zoom of the high-confidence part of the plot.