BIOADI: a machine learning approach to identifying abbreviations and definitions in biological literature

BMC Bioinformatics

Table 7 Top 20 most frequent SF-LF pairs extracted from 17,551,165 PubMed abstracts

Rank	Short Form	Long Form	Frequency	Class
1	CI	confidence interval	36142	Statistical Measure
2	PCR	polymerase chain reaction	26951	Experimental Technique
3	NO	nitric oxide	25229	Medical Relevance
4	CT	computed tomography	20084	Experimental Technique
5	HIV	human immunodeficiency virus	20027	Virus Studied
6	LPS	lipopolysaccharide	20027	Experimental Technique
7	OR	odds ratio	19914	Statistical Measure
8	MRI	magnetic resonance imaging	19396	Experimental Technique
9	IL	interleukin	16934	Medical Relevance
10	CNS	central nervous system	15915	Medical Relevance
11	BMI	body mass index	15614	Clinical Observation
12	RA	rheumatoid arthritis	14221	Medical Relevance
13	AD	Alzheimer's disease	14103	Medical Relevance
14	PKC	protein kinase C	13958	Medical Relevance
15	ELISA	enzyme-linked immunosorbent assay	13946	Experimental Technique
16	CSF	cerebrospinal fluid	13815	Medical Relevance
17	DA	dopamine	11297	Medical Relevance
18	BP	blood pressure	10991	Clinical Observation
19	MR	magnetic resonance	10973	Experimental Technique
20	HCV	hepatitis C virus	10944	Virus Studied

ISSN: 1471-2105