{"id":"W4378418071","doi":"10.1200/cci.22.00196","title":"Natural Language Processing Methods to Empirically Explore Social Contexts and Needs in Cancer Patient Notes","year":2023,"lang":"en","type":"article","venue":"JCO Clinical Cancer Informatics","topic":"Cancer survivorship and care","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Ethnic group; Odds; Actuarial science; Documentation; Medicine; Psychology; Computer science; Logistic regression; Sociology; Machine learning; Economics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007566954,0.0006019498,0.0003803014,0.005100772,0.0004937815,0.001490613,0.0008642479,0.0006608252,0.00159894],"category_scores_gemma":[0.04104769,0.0003011513,0.0008197072,0.002471411,0.0007369941,0.001808406,0.001262536,0.001186,0.0003952957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001332179,"about_ca_system_score_gemma":0.001454453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005164344,"about_ca_topic_score_gemma":0.00903881,"domain_scores_codex":[0.9955052,0.00280714,0.0005243557,0.0005975412,0.0004647318,0.0001010212],"domain_scores_gemma":[0.9505817,0.04110162,0.004961565,0.001225245,0.001843901,0.0002860408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005011321,0.0006317793,0.6104825,0.002051851,0.0006486684,0.0007951298,0.006960796,0.03277864,0.006853085,0.00623432,0.008850592,0.3232116],"study_design_scores_gemma":[0.0001636722,0.0005740889,0.3402624,0.001189855,0.000346904,0.001237087,0.01210485,0.5454496,0.006523567,0.07251942,0.01944595,0.0001826904],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6344078,0.003117527,0.3321288,0.007223556,0.0001703004,0.001694256,0.01520061,0.0008581697,0.005198969],"genre_scores_gemma":[0.8422671,0.0005705034,0.1481303,0.0006851204,0.0001392979,0.0008479453,0.006894937,0.00003682807,0.0004280478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007566954,"threshold_uncertainty_score":0.04001838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1494874202900557,"score_gpt":0.5228382271378647,"score_spread":0.373350806847809,"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."}}