Target term (n-gram) | Candidate terms (20 top-ranked n-grams) from CBOW neural embeddings for a target term | Candidate terms (20 top-ranked n-grams) from Skip-gram neural embeddings for a target term |
---|
MetaMap Experiment 1 | MetaMap Experiment 2 | MetaMap Experiment 1 | MetaMap Experiment 2 |
---|
P | R | F | P | R | F | P | R | F | P | R | F |
---|
anaemia | 90.00 | 100.00 | 94.74 | 85.00 | 100.00 | 91.89 | 84.21 | 94.12 | 88.89 | 94.74 | 94.74 | 94.74 |
arthritis | 88.89 | 88.89 | 88.89 | 89.47 | 94.44 | 91.89 | 100.00 | 100.00 | 100.00 | 95.00 | 100.00 | 97.44 |
asthma | 76.47 | 81.25 | 78.79 | 72.22 | 86.67 | 78.79 | 63.16 | 92.31 | 75.00 | 68.42 | 92.86 | 78.79 |
CKD | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 100.00 | 90.00 | 100.00 | 94.74 | 90.00 | 100.00 | 94.74 |
diabetes | 63.16 | 92.31 | 75.00 | 68.42 | 92.86 | 78.79 | 75.00 | 100.00 | 85.71 | 80.00 | 100.00 | 88.89 |
epilepsy | 85.00 | 100.00 | 91.89 | 95.00 | 100.00 | 97.44 | 90.00 | 100.00 | 94.74 | 95.00 | 100.00 | 97.44 |
glaucoma | 90.00 | 100.00 | 94.74 | 100.00 | 100.00 | 100.00 | 84.21 | 94.12 | 88.89 | 100.00 | 100.00 | 100.00 |
heart_failure | 85.00 | 100.00 | 91.89 | 90.00 | 100.00 | 94.74 | 73.68 | 93.33 | 82.35 | 90.00 | 100.00 | 94.74 |
hypertension | 95.00 | 100.00 | 97.44 | 100.00 | 100.00 | 100.00 | 84.21 | 94.12 | 88.89 | 95.00 | 100.00 | 97.44 |
obesity | 100.00 | 95.00 | 97.44 | 100.00 | 100.00 | 100.00 | 94.74 | 94.74 | 94.74 | 95.00 | 100.00 | 97.44 |
osteoarthritis | 90.00 | 100.00 | 94.74 | 100.00 | 100.00 | 100.00 | 90.00 | 100.00 | 94.74 | 100.00 | 100.00 | 100.00 |
| 87.59 | 96.13 | 91.41 | 90.92 | 97.63 | 93.96 | 84.47 | 96.61 | 89.88 | 91.20 | 98.87 | 94.70 |
- 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