CardioBERTa.ro_enriched / training_data_stats.json
fernandogd's picture
Release CardioBERTa-based clinical concept disambiguation model
8fd72f6 verified
Raw History Blame Contribute Delete
926 Bytes
{
"triplets": 70817,
"malformed_rows": 0,
"unique_triplets": 70817,
"duplicate_triplets": 0,
"unique_cuis": 70817,
"unique_anchors": 69316,
"unique_positives": 70439,
"unique_terms": 139248,
"unique_anchor_positive_pairs": 70725,
"ambiguous_terms_across_cuis": 2203,
"self_pairs_exact": 0,
"self_pairs_normalized": 104,
"cuis_with_multiple_terms": 70713,
"terms_per_cui_mean": 1.9985314260700113,
"terms_per_cui_median": 2,
"terms_per_cui_p95": 2.0,
"terms_per_cui_max": 2,
"triplets_per_cui_mean": 1,
"triplets_per_cui_median": 1,
"triplets_per_cui_p95": 1.0,
"triplets_per_cui_max": 1,
"anchor_words_mean": 5.957651411384272,
"positive_words_mean": 6.2761625033537145,
"cuis_common_with_synonyms": 70817,
"cuis_added_vs_synonyms": 0,
"cuis_missing_vs_synonyms": 0,
"terms_common_with_synonyms": 139248,
"terms_added_vs_synonyms": 0,
"terms_missing_vs_synonyms": 0
}