{"id":"W2920239411","doi":"10.1007/s11036-019-01237-3","title":"Towards Using Scientific Publications to Automatically Extract Information on Rare Diseases","year":2019,"lang":"en","type":"article","venue":"Mobile Networks and Applications","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"National Institutes of Health","keywords":"Computer science; Statistic; Population; Information extraction; Scientific literature; Rare disease; Data science; Disease; Information retrieval; Medicine; Pathology; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009821377,0.00009399244,0.00009051499,0.00006213968,0.0002007791,0.0001538933,0.0001486525,0.0000991086,0.00003556129],"category_scores_gemma":[0.00003364437,0.00008120088,0.00003684844,0.0002452988,0.00009208763,0.00001069006,0.00008420167,0.00006169448,0.00004622688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001146907,"about_ca_system_score_gemma":0.00005577776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000354057,"about_ca_topic_score_gemma":0.000002185939,"domain_scores_codex":[0.9993014,0.00001543101,0.000168136,0.0002362189,0.0001071005,0.0001716907],"domain_scores_gemma":[0.9993436,0.00002134435,0.00005199492,0.0003623509,0.0000797997,0.000140851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000544023,0.0003803175,0.006369979,0.00007558802,0.00006337191,2.268719e-7,0.00008414553,0.06287832,0.009773101,0.007669876,0.02421721,0.8884335],"study_design_scores_gemma":[0.0002464693,0.0002199191,0.01808031,0.00002702819,0.00002128392,0.000005124598,0.0001497747,0.02797088,0.0003004597,0.0001697562,0.9525781,0.0002308961],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6710014,0.0006391606,0.3236825,0.0005790959,0.0001957653,0.001499426,0.0001147393,0.0001268928,0.002161071],"genre_scores_gemma":[0.9962162,0.00002788011,0.001896211,0.0004488746,0.0001509819,0.0005627177,0.0003302176,0.00000833237,0.0003585545],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9283609,"threshold_uncertainty_score":0.3311276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01024701181937999,"score_gpt":0.2734269573211845,"score_spread":0.2631799455018046,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}