{"id":"W4404025732","doi":"10.2196/55067","title":"Screening for Depression Using Natural Language Processing: Literature Review","year":2024,"lang":"en","type":"review","venue":"Interactive Journal of Medical Research","topic":"Mental Health via Writing","field":"Psychology","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Toronto Metropolitan University; St. Michael's Hospital","funders":"","keywords":"Interpretability; Artificial intelligence; Computer science; Machine learning; Data science; Relevance (law); Sentiment analysis; Natural language processing; Political science","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":[0.004763082,0.0009582461,0.002179279,0.009526318,0.0005640663,0.002204543,0.001746138,0.001654132,0.005597816],"category_scores_gemma":[0.03674571,0.0006215462,0.002589529,0.007751469,0.001133499,0.003099778,0.001271612,0.001271626,0.0008521565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001889498,"about_ca_system_score_gemma":0.007570793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004848722,"about_ca_topic_score_gemma":0.008157861,"domain_scores_codex":[0.9966808,0.001017151,0.001096518,0.0003524214,0.0007691963,0.00008392356],"domain_scores_gemma":[0.935086,0.05692195,0.003655878,0.0005143775,0.003576807,0.0002449894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00009595418,0.00006432028,0.001388823,0.4582451,0.0008535636,0.0003160211,0.0006608663,0.0003053944,0.0002591265,0.001767095,0.01566456,0.5203791],"study_design_scores_gemma":[0.00004703402,0.0001509053,0.006242948,0.7953393,0.004373442,0.001549992,0.001008582,0.0003257947,0.0003636895,0.003533176,0.1869985,0.00006661793],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004529762,0.9967464,0.0003720016,0.001161204,0.0001460276,0.00007823417,0.0001799227,0.00001448824,0.0008486668],"genre_scores_gemma":[0.004541941,0.992888,0.001053385,0.0009668156,0.0001435573,0.0001187305,0.0001819537,0.000005938597,0.00009957221],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.009526318,"threshold_uncertainty_score":0.02518988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3105269665675473,"score_gpt":0.6770248126152839,"score_spread":0.3664978460477366,"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."}}