Back

A corpus for differential diagnosis: an eye diseases use case

Jimeno Yepes, A.; Martinez Iraola, D.; Barnard, P.; Joy, T.

2021-05-10 bioinformatics
10.1101/2021.05.10.443343 bioRxiv
Show abstract

We have created a corpus for the extraction of information related to diagnosis from scientific literature focused on eye diseases. It was shown that the annotation of entities has a relatively large agreement among annotators, which translates into strong performance of the trained methods, mostly BioBERT. Furthermore it was observed that relation annotation in this domain has challenges, which might require additional exploration. When using the trained models on MEDLINE, we could identify confirmed knowledge about the diagnosis of eye diseases and relevant new information, which supports the developments in this work. The corpus that we have developed is publicly available, thus the scientific community is able to reproduce our work and reuse the corpus in their work.

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 19%
9.4%
Similar papers in this journal
2
Computers in Biology and Medicine
○ 128 papers in training set
Top 0.4%
6.5%
Similar papers in this journal
3
Database
◐ 61 papers in training set
Top 0.1%
6.1%
Similar papers in this journal
4
Bioinformatics
◐ 1204 papers in training set
Top 4%
5.4%
Similar papers in this journal
5
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 0.4%
5.3%
Similar papers in this journal
6
BioData Mining
○ 22 papers in training set
Top 0.1%
5.0%
7
Scientific Reports
○ 3612 papers in training set
Top 20%
4.7%
8
Artificial Intelligence in Medicine
○ 17 papers in training set
Top 0.1%
4.7%
9
BMC Bioinformatics
○ 457 papers in training set
Top 2%
3.9%
50% of probability mass above
10
Scientific Data
○ 209 papers in training set
Top 0.7%
3.3%
11
Journal of the American Medical Informatics Association
◐ 71 papers in training set
Top 1%
3.1%
12
Journal of Biomedical Informatics
○ 47 papers in training set
Top 0.5%
3.1%
13
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
3.0%
14
GigaScience
◐ 212 papers in training set
Top 2%
2.6%
15
Computer Methods and Programs in Biomedicine
○ 28 papers in training set
Top 0.3%
2.4%
16
IEEE Access
● 35 papers in training set
Top 0.6%
2.1%
17
JAMIA Open
◐ 42 papers in training set
Top 0.8%
2.1%
18
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 3%
2.1%
19
Frontiers in Bioinformatics
○ 49 papers in training set
Top 0.5%
1.6%
20
IEEE/ACM Transactions on Computational Biology and Bioinformatics
● 38 papers in training set
Top 0.6%
1.5%
21
Neuroinformatics
○ 46 papers in training set
Top 0.5%
1.4%
22
PLOS Digital Health
● 106 papers in training set
Top 3%
1.3%
23
JMIR Medical Informatics
◐ 18 papers in training set
Top 0.6%
1.1%
24
PLOS Computational Biology
● 1863 papers in training set
Top 17%
1.1%
25
Frontiers in Genetics
○ 230 papers in training set
Top 5%
1.0%
26
Informatics in Medicine Unlocked
○ 22 papers in training set
Top 1%
0.8%
27
Biology Methods and Protocols
◐ 61 papers in training set
Top 2%
0.8%
28
Genes
○ 144 papers in training set
Top 5%
0.6%
29
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 5%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.