{"id":"W4205665338","doi":"10.2196/28199","title":"Improving Emergency Department Patient-Physician Conversation Through an Artificial Intelligence Symptom-Taking Tool: Mixed Methods Pilot Observational Study","year":2021,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Wellcome Trust","keywords":"Emergency department; Context (archaeology); Medicine; Likert scale; Observational study; Referral; Triage; Medical emergency; Family medicine; Nursing; Psychology","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":[0.002215971,0.0002217617,0.0003312924,0.0002159718,0.0007250189,0.0001082295,0.0001779566,0.0001026711,0.0004946241],"category_scores_gemma":[0.001066091,0.0002123445,0.00009768412,0.00134877,0.0001278191,0.001378978,0.0001559476,0.0006764759,0.0001689175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005821453,"about_ca_system_score_gemma":0.0008720574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006289748,"about_ca_topic_score_gemma":0.0002396558,"domain_scores_codex":[0.9949632,0.001475387,0.00111709,0.0005525774,0.001203234,0.0006885036],"domain_scores_gemma":[0.9958516,0.0005635072,0.000326271,0.0005346404,0.002529595,0.0001943519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004836086,0.00489458,0.008908691,0.0002514782,0.0001180716,0.00002366557,0.1169093,0.00006552845,0.01666592,0.009450474,0.0003578979,0.8418708],"study_design_scores_gemma":[0.000145138,0.01013274,0.06750806,0.0002066904,0.00007565656,0.00001979443,0.4259928,0.02479566,0.4351203,0.03451693,0.0008959749,0.0005902374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9680886,0.0001036135,0.02684868,0.001295927,0.001228641,0.0018045,0.00001404643,0.00007230134,0.0005436308],"genre_scores_gemma":[0.9913151,0.00005428283,0.007086088,0.0002156917,0.0004653501,0.0004949767,0.0003010208,0.0000311296,0.00003639777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8412805,"threshold_uncertainty_score":0.8659155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5566823996857291,"score_gpt":0.5856444321099818,"score_spread":0.02896203242425277,"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."}}