CardioBERTa.sv_translations_only / training_data_stats.json
fernandogd's picture
Release CardioBERTa-based clinical concept disambiguation model
2683fd0 verified
Raw
History Blame Contribute Delete
923 Bytes
{
"triplets": 71919,
"malformed_rows": 0,
"unique_triplets": 71919,
"duplicate_triplets": 0,
"unique_cuis": 71919,
"unique_anchors": 71096,
"unique_positives": 71328,
"unique_terms": 141369,
"unique_anchor_positive_pairs": 71821,
"ambiguous_terms_across_cuis": 2268,
"self_pairs_exact": 0,
"self_pairs_normalized": 37,
"cuis_with_multiple_terms": 71882,
"terms_per_cui_mean": 1.999485532334988,
"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": 4.662286739248321,
"positive_words_mean": 5.321333722660215,
"cuis_common_with_synonyms": 71919,
"cuis_added_vs_synonyms": 0,
"cuis_missing_vs_synonyms": 0,
"terms_common_with_synonyms": 141369,
"terms_added_vs_synonyms": 0,
"terms_missing_vs_synonyms": 0
}