{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.004070149,0.001303919,0.001217978,0.02705923,0.001063373,0.005299707,0.001278663,0.001863681,0.002089547],"category_scores_gemma":[0.01586774,0.0005096068,0.00184309,0.01278774,0.0006850751,0.00471257,0.002982818,0.001687651,0.003826873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041652,"about_ca_system_score_gemma":0.004739247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004292028,"about_ca_topic_score_gemma":0.006267574,"domain_scores_codex":[0.9970721,0.000579799,0.0006093825,0.000676117,0.0009110477,0.0001515134],"domain_scores_gemma":[0.9866871,0.007363678,0.001635836,0.001291546,0.002567873,0.0004539067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003839651,0.0007522377,0.05321916,0.005329306,0.0008185962,0.001873835,0.002019298,0.005338783,0.05175051,0.02332978,0.04658058,0.8086039],"study_design_scores_gemma":[0.0002475307,0.0004355242,0.0709427,0.003750678,0.002879479,0.005689137,0.004372144,0.1650093,0.09330125,0.1486825,0.5043572,0.0003326637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1118072,0.01661163,0.7345341,0.009714915,0.001076685,0.001424886,0.08857601,0.01814218,0.01811237],"genre_scores_gemma":[0.1265623,0.006207393,0.7805147,0.0009322962,0.0004230937,0.0004612162,0.08079524,0.0004974254,0.003606343],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9729408,"threshold_uncertainty_score":0.02152526,"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."}}