{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03541555,0.001723835,0.001895726,0.001953042,0.0005817195,0.002444064,0.001496534,0.00171442,0.003111591],"category_scores_gemma":[0.1425459,0.0005196515,0.003405526,0.000998401,0.001640075,0.00296578,0.002186273,0.002996116,0.001223491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001152121,"about_ca_system_score_gemma":0.001454654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003034012,"about_ca_topic_score_gemma":0.002444293,"domain_scores_codex":[0.9790102,0.0122479,0.002125144,0.004468739,0.001605198,0.0005428493],"domain_scores_gemma":[0.6813141,0.2993095,0.004962669,0.008654592,0.004323808,0.00143535],"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":[0.05910233,0.002720258,0.3245595,0.004806785,0.01578322,0.0005827748,0.002405602,0.1364232,0.01547659,0.002332724,0.01635452,0.4194525],"study_design_scores_gemma":[0.002657926,0.01514854,0.2000504,0.00074033,0.01073332,0.0008918012,0.002173575,0.7246565,0.02700153,0.007668648,0.007627176,0.0006503045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9474059,0.004328973,0.03727996,0.0004696244,0.0004087833,0.0007065388,0.00508682,0.002268534,0.002044885],"genre_scores_gemma":[0.9788504,0.0003615898,0.01182549,0.0001683876,0.0001007225,0.0007158038,0.006927131,0.0005517189,0.0004988124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03541555,"threshold_uncertainty_score":0.1872975,"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."}}