{"id":"W4401612165","doi":"10.2196/51433","title":"Leveraging Open-Source Large Language Models for Data Augmentation in Hospital Staff Surveys: Mixed Methods Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Data science; Psychology; Natural language processing; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02795453,0.001122733,0.0006894765,0.0009708632,0.0006583836,0.001880385,0.001726678,0.001274961,0.001910805],"category_scores_gemma":[0.08142336,0.0007221279,0.00187523,0.0007930551,0.000794214,0.001398765,0.001858492,0.002056801,0.0009301256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007701779,"about_ca_system_score_gemma":0.001337212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002514453,"about_ca_topic_score_gemma":0.004833858,"domain_scores_codex":[0.9757386,0.02050907,0.00091917,0.001532749,0.0009921382,0.0003082759],"domain_scores_gemma":[0.8440105,0.1388976,0.003241799,0.008128582,0.005017444,0.0007041665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.006075568,0.01170875,0.2272214,0.004963749,0.003019297,0.0008725956,0.02166582,0.04798536,0.0133349,0.004964069,0.007921027,0.6502674],"study_design_scores_gemma":[0.001645901,0.01567457,0.1696861,0.002246724,0.003300468,0.001384152,0.02311049,0.6636603,0.04807808,0.02140084,0.04888299,0.0009293815],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8031306,0.001710084,0.185811,0.0007800069,0.0001405003,0.003064654,0.002065815,0.001052117,0.002245204],"genre_scores_gemma":[0.8306656,0.0003492386,0.1598711,0.0005938885,0.000114027,0.00437089,0.002576665,0.0002412953,0.001217198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02795453,"threshold_uncertainty_score":0.1478395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1988406375515109,"score_gpt":0.5689606831681521,"score_spread":0.3701200456166411,"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."}}