{"id":"W4406458424","doi":"10.1109/bigdata62323.2024.10825184","title":"GPT-4 on Clinic Depression Assessment: An LLM-Based Pilot Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Depression (economics); Computer science; Medicine","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":[0.001039258,0.0001651275,0.0001560275,0.000186715,0.0001726572,0.0003970899,0.0008809309,0.00003712363,0.0002867191],"category_scores_gemma":[0.00005429723,0.0001248955,0.00003770124,0.0004208616,0.00001369162,0.0003223744,0.0001856407,0.0005576267,0.0005547482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007338527,"about_ca_system_score_gemma":0.000232406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003251228,"about_ca_topic_score_gemma":0.0001042076,"domain_scores_codex":[0.9975423,0.0005802066,0.0002958539,0.0007848613,0.0005181924,0.0002786253],"domain_scores_gemma":[0.9981802,0.0005098467,0.00004507145,0.001051613,0.00004681131,0.0001664425],"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":[0.000120472,0.01023326,0.4391907,0.0003882177,0.00007844915,0.0006921627,0.001987002,0.009976553,0.0004179481,0.06014876,0.008553559,0.4682129],"study_design_scores_gemma":[0.0004304625,0.01198318,0.1295512,0.0001116023,0.000006731923,0.000003186542,0.00004991404,0.8541512,0.00003972304,0.0006838703,0.002758719,0.0002301962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4235596,0.0001565592,0.5305113,0.006552834,0.003156179,0.001298738,0.00000369913,0.003913166,0.03084795],"genre_scores_gemma":[0.9798633,9.770971e-7,0.01768495,0.001129224,0.0001226843,0.00004279322,0.000005247195,0.00002060129,0.001130199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8441746,"threshold_uncertainty_score":0.7130351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07709552278523243,"score_gpt":0.4349904886555108,"score_spread":0.3578949658702784,"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."}}