{"id":"W4414670348","doi":"10.2196/80917","title":"Impact of Detailed Versus Generic Instructions on Fine-Tuned Language Models for Patient Discharge Instructions Generation: Comparative Statistical Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Statistical analysis; Statistical model; Key (lock); Language model; Patient discharge","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0004539649,0.0001806173,0.0003987883,0.00123022,0.0006259445,0.0001203893,0.0004988004,0.00008185466,0.00005520253],"category_scores_gemma":[0.0001750705,0.000146502,0.0002218117,0.003307086,0.0001662189,0.000539454,0.0002465362,0.0005066246,0.00001097417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004442361,"about_ca_system_score_gemma":0.0004420696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002759637,"about_ca_topic_score_gemma":0.0003232128,"domain_scores_codex":[0.9973229,0.0006709001,0.0005108755,0.0003991893,0.0006340242,0.0004620971],"domain_scores_gemma":[0.9973303,0.0008891881,0.0001612292,0.0006196888,0.0008553584,0.0001442061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008738692,0.0009019425,0.005130159,0.0002578183,0.002361197,0.000004085955,0.0554161,0.2243561,0.0009061539,0.6385334,0.007252324,0.06400687],"study_design_scores_gemma":[0.0009472556,0.001395554,0.02117172,0.00002000011,0.00002980921,0.000001046752,0.0008141112,0.9734733,0.0005232872,0.001412493,0.00007615668,0.0001352463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5541064,0.00003238925,0.4433503,0.0002503925,0.0002310701,0.0006993675,0.0002897895,0.00004301886,0.0009972706],"genre_scores_gemma":[0.9799089,0.00000481277,0.01918044,0.00001186016,0.0000435399,0.0005522805,0.0002082746,0.000007059601,0.00008280073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7491173,"threshold_uncertainty_score":0.597418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1212669366214506,"score_gpt":0.4831316172009676,"score_spread":0.361864680579517,"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."}}