{"id":"W4283012421","doi":"10.1038/s41597-022-01423-1","title":"A dataset of simulated patient-physician medical interviews with a focus on respiratory cases","year":2022,"lang":"en","type":"article","venue":"Scientific Data","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Tellabs (Canada); University of Waterloo; Polytechnique Montréal; Western University","funders":"","keywords":"Computer science; Conversation; Artificial intelligence; Focus (optics); Natural language processing; Set (abstract data type); Converse; Machine learning; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002262719,0.0001424698,0.0002160371,0.0002403608,0.0004785713,0.0001457057,0.005586055,0.00002736722,0.0002695736],"category_scores_gemma":[0.0005342471,0.0001147929,0.00002572283,0.001331749,0.000217698,0.0004149446,0.005877414,0.0004588566,0.00004872155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005200759,"about_ca_system_score_gemma":0.0004790181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000431231,"about_ca_topic_score_gemma":0.0003128613,"domain_scores_codex":[0.9957798,0.0006688255,0.0004436217,0.001116507,0.001673703,0.0003175101],"domain_scores_gemma":[0.9940192,0.0002843504,0.0002982514,0.005138886,0.00008122846,0.0001780945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001289531,0.000821592,0.001147004,0.0001445706,0.00004736759,0.0008806485,0.002233394,0.003458274,0.0001080787,0.003119227,0.6102218,0.3776891],"study_design_scores_gemma":[0.0004240155,0.001302324,0.0002100418,0.0001293028,0.000009896291,0.00004903255,0.000217372,0.185934,0.0002006565,0.0002152867,0.8110432,0.0002648954],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6872517,0.002262319,0.02199775,0.01593386,0.01179512,0.003989983,0.2535408,0.0009937384,0.002234707],"genre_scores_gemma":[0.9844174,7.220165e-7,0.001884797,0.00239012,0.0000389664,0.0000191174,0.01117717,0.00001804383,0.00005363578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3774242,"threshold_uncertainty_score":0.9997942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0875093153622667,"score_gpt":0.3520148190788424,"score_spread":0.2645055037165757,"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."}}