{"id":"W2938914726","doi":"10.2196/11472","title":"A Facial Recognition Mobile App for Patient Safety and Biometric Identification: Design, Development, and Validation","year":2019,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Seoul National University Hospital; National Research Foundation of Korea; Korea Health Industry Development Institute; Seoul National University; National Research Foundation","keywords":"Identification (biology); Patient safety; Biometrics; Medicine; Health care; Medical emergency; Computer science; Artificial intelligence","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":[0.001079011,0.000125737,0.0001866532,0.0007157493,0.0003977277,0.0002039021,0.0001169525,0.00009781359,0.000006989002],"category_scores_gemma":[0.00004980635,0.0001232291,0.00001652804,0.001261311,0.00003587767,0.0003866799,0.00006610725,0.00008415311,0.00002306156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008103273,"about_ca_system_score_gemma":0.0002035433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001904704,"about_ca_topic_score_gemma":0.000002746988,"domain_scores_codex":[0.9983718,0.0001126903,0.0005022063,0.0005206601,0.0002148614,0.0002778066],"domain_scores_gemma":[0.9989311,0.000170981,0.0002854314,0.000204835,0.0001528716,0.0002547473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005908528,0.0000785902,0.0007257597,0.0005456535,0.000005511602,1.51129e-7,0.002374101,4.95085e-7,0.000108732,0.0007842534,0.0002479783,0.9950697],"study_design_scores_gemma":[0.008868512,0.003013641,0.4774223,0.0001809484,0.00008528058,0.0001145218,0.001616674,0.03592627,0.01036053,0.007287626,0.4532072,0.00191658],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6113188,0.001191447,0.3840714,0.0005864745,0.0004205565,0.002234451,0.00003858956,0.0000976921,0.00004069564],"genre_scores_gemma":[0.9669911,0.0009648192,0.03105874,0.0004085748,0.00003933702,0.0002632087,0.0001346369,0.000009510663,0.0001301312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9931531,"threshold_uncertainty_score":0.5025135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07627390721603412,"score_gpt":0.3389561442877376,"score_spread":0.2626822370717035,"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."}}