{"id":"W4393335480","doi":"10.1038/s41746-024-01074-z","title":"Foundation metrics for evaluating effectiveness of healthcare conversations powered by generative AI","year":2024,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Topic Modeling","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Standards and Technology","keywords":"Health care; Computer science; Personalization; Set (abstract data type); Process (computing); Comprehension; Human–computer interaction; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.0007190111,0.00009546895,0.0001887214,0.0001656921,0.0000558382,0.00009499031,0.000193974,0.00004121173,0.000005268011],"category_scores_gemma":[0.001074929,0.00007897169,0.00003518252,0.0006558613,0.00004650534,0.0006293824,0.00004863327,0.00007975116,0.000004258157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167613,"about_ca_system_score_gemma":0.0001675937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004224028,"about_ca_topic_score_gemma":0.000001719501,"domain_scores_codex":[0.9988775,0.00006349319,0.0002746584,0.0003027073,0.0003423038,0.0001392939],"domain_scores_gemma":[0.9981952,0.00107551,0.00006371993,0.0002083879,0.0003974403,0.00005969213],"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":[0.00003440005,0.00005812024,0.0004030335,0.001288979,0.00011752,0.000003644637,0.003586556,0.0004523433,0.01315786,0.3387885,0.001405688,0.6407034],"study_design_scores_gemma":[0.0009983714,0.001034611,0.000177867,0.0006428447,0.00002829787,0.000006204324,0.0001852306,0.9561091,0.004610945,0.03350447,0.002539567,0.0001625081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01175328,0.0008953201,0.9804857,0.004921694,0.0008493374,0.0004737749,0.00002544723,0.0000911039,0.0005043769],"genre_scores_gemma":[0.9928108,0.00000645361,0.00667338,0.0001900956,0.00009345186,0.00004437426,0.00009691335,0.000008778631,0.00007578228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9810575,"threshold_uncertainty_score":0.3220372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05987682264453834,"score_gpt":0.3823261757586979,"score_spread":0.3224493531141596,"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."}}