Skip to main content

Table 6 MetaMap performance for the candidate terms from PMSB dataset

From: Exploring semantic deep learning for building reliable and reusable one health knowledge from PubMed systematic reviews and veterinary clinical notes

Target term (n-gram)Candidate terms (20 top-ranked n-grams) from CBOW neural embeddings for a target termCandidate terms (20 top-ranked n-grams) from Skip-gram neural embeddings for a target term
MetaMap Experiment 1MetaMap Experiment 2MetaMap Experiment 1MetaMap Experiment 2
PRFPRFPRFPRF
anaemia90.00100.0094.7485.00100.0091.8984.2194.1288.8994.7494.7494.74
arthritis88.8988.8988.8989.4794.4491.89100.00100.00100.0095.00100.0097.44
asthma76.4781.2578.7972.2286.6778.7963.1692.3175.0068.4292.8678.79
CKD100.00100.00100.00100.00100.00100.0090.00100.0094.7490.00100.0094.74
diabetes63.1692.3175.0068.4292.8678.7975.00100.0085.7180.00100.0088.89
epilepsy85.00100.0091.8995.00100.0097.4490.00100.0094.7495.00100.0097.44
glaucoma90.00100.0094.74100.00100.00100.0084.2194.1288.89100.00100.00100.00
heart_failure85.00100.0091.8990.00100.0094.7473.6893.3382.3590.00100.0094.74
hypertension95.00100.0097.44100.00100.00100.0084.2194.1288.8995.00100.0097.44
obesity100.0095.0097.44100.00100.00100.0094.7494.7494.7495.00100.0097.44
osteoarthritis90.00100.0094.74100.00100.00100.0090.00100.0094.74100.00100.00100.00
 87.5996.1391.4190.9297.6393.9684.4796.6189.8891.2098.8794.70
  1. The table shows the performance of MetaMap in Experiment 1 (applying MetaMap to the candidate terms) and Experiment 2 (short form detection and expansion into long form before applying MetaMap to the candidate terms) for each target term (n-gram for a well-known medical condition). The candidate terms are a list of the 20 top-ranked terms (highest cosine value) obtained from the created neural embeddings with CBOW or Skip-gram taking the vector for a target term. The last row shows the average of each evaluation measure over all 11 medical conditions under study to get an overall measure of performance (a.k.a. macro-averaging). Abbreviations: P = precision; R = recall; and F = F measure