{"id":"W4210804144","doi":"10.1038/s41746-021-00555-9","title":"PhenoPad: Building AI enabled note-taking interfaces for patient encounters","year":2022,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Hospital for Sick Children; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Hospital for Sick Children; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Handwriting; Computer science; Modalities; Human–computer interaction; Interface (matter); Variety (cybernetics); Clinical trial; User interface; Health care; Data science; Artificial intelligence; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001329883,0.0002627339,0.0005849678,0.0002393384,0.001263958,0.00001841774,0.0003609402,0.0001010121,0.0008895833],"category_scores_gemma":[0.001474118,0.0002194339,0.00006394368,0.0003655181,0.00007298033,0.000291502,0.0002806839,0.001081828,0.00004742627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001661384,"about_ca_system_score_gemma":0.0006732294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004378139,"about_ca_topic_score_gemma":0.00006804199,"domain_scores_codex":[0.996173,0.0002998652,0.001175468,0.0004919828,0.0006590796,0.001200569],"domain_scores_gemma":[0.9968375,0.001586947,0.0007463396,0.0003749822,0.0001932847,0.0002609441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002404288,0.0006220508,0.01923489,0.00609864,0.0003240762,0.00008634109,0.100539,0.0004942686,0.01904828,0.01794474,0.356282,0.4769215],"study_design_scores_gemma":[0.003320047,0.003744512,0.0001313374,0.001254936,0.0000351985,0.0000226095,0.02014711,0.001872384,0.0001548148,0.002185602,0.9667634,0.0003680524],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.856775,0.002305409,0.02336744,0.02160211,0.01611976,0.007894506,0.0002925244,0.00067183,0.07097137],"genre_scores_gemma":[0.9885601,0.000009776331,0.000137955,0.006825721,0.001015737,0.001521905,0.0000690715,0.00007396235,0.001785774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6104814,"threshold_uncertainty_score":0.9740313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04653920708181176,"score_gpt":0.4327038372870837,"score_spread":0.3861646302052719,"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."}}