{"id":"W3016187590","doi":"10.2196/17787","title":"Modified Bidirectional Encoder Representations From Transformers Extractive Summarization Model for Hospital Information Systems Based on Character-Level Tokens (AlphaBERT): Development and Performance Evaluation","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medical diagnosis; Automatic summarization; Computer science; Security token; Encoder; Transformer; Artificial intelligence; Character (mathematics); Natural language processing; Machine learning; Medicine; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004947609,0.001049849,0.000531362,0.0005116055,0.0002538832,0.0005154236,0.0009904725,0.0006702819,0.002612231],"category_scores_gemma":[0.001434511,0.0003319919,0.0006724775,0.0004106453,0.0001856652,0.0009483005,0.0005355852,0.00119175,0.0009262409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001144556,"about_ca_system_score_gemma":0.001531641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01825011,"about_ca_topic_score_gemma":0.01716085,"domain_scores_codex":[0.9998254,0.00003514312,0.00001602721,0.0000570341,0.00003416188,0.00003223001],"domain_scores_gemma":[0.9995146,0.0002297832,0.00003854401,0.00003829307,0.0001543485,0.00002459663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004342858,0.0002654703,0.002186213,0.0002169222,0.0001378417,0.0002640239,0.0001291068,0.6398263,0.01303982,0.002583076,0.005464207,0.3354528],"study_design_scores_gemma":[0.000007599866,0.00004155058,0.0001871441,0.000004462697,0.00001643241,0.0000158441,0.000007700986,0.9966414,0.002431798,0.0003564786,0.0002849993,0.000004618999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1833575,0.001493798,0.7925208,0.00081996,0.0002539229,0.0004540834,0.002375333,0.01395685,0.00476785],"genre_scores_gemma":[0.829347,0.0006351923,0.1576496,0.0002018541,0.00005943835,0.0004277264,0.00432632,0.0002032738,0.007149594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01825011,"threshold_uncertainty_score":0.03628778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05674808063348856,"score_gpt":0.3199274783895715,"score_spread":0.263179397756083,"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."}}