{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006685351,0.0002072926,0.0002210421,0.000167579,0.000305015,0.0001999359,0.0003096796,0.0002010982,0.00001298101],"category_scores_gemma":[0.0004275024,0.000192691,0.00004630863,0.0002847562,0.0000417183,0.002534685,0.00005179529,0.0003646128,0.0000172455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001786099,"about_ca_system_score_gemma":0.0008253002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002598075,"about_ca_topic_score_gemma":0.00000413517,"domain_scores_codex":[0.9970373,0.00007505056,0.0009064627,0.0002020586,0.001510575,0.0002685597],"domain_scores_gemma":[0.9983321,0.0003348349,0.0003774018,0.0001922219,0.0004346574,0.0003287465],"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":[0.0002152571,0.0001785557,0.002418723,0.0008425289,0.00007718494,6.850815e-7,0.1084792,0.4174249,0.000008888459,0.003384589,0.0009902272,0.4659792],"study_design_scores_gemma":[0.001209461,0.0001558095,0.007501259,0.0001135122,0.00001203856,0.000001341968,0.0005020713,0.9892764,0.00006485105,0.00002362804,0.0009170247,0.0002225955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1466957,0.000007312462,0.8482716,0.0024087,0.0003171136,0.001506414,0.00007263655,0.0001406569,0.0005798189],"genre_scores_gemma":[0.9531666,0.00001223749,0.04306783,0.001877882,0.00009331868,0.0007723952,0.0009855496,0.00001075294,0.00001345341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8064708,"threshold_uncertainty_score":0.785771,"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."}}