{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007254395,0.0001970959,0.0005859858,0.0002329971,0.00008603146,0.00005626199,0.0001113125,0.0001866744,0.00006291989],"category_scores_gemma":[0.0005733683,0.0001594748,0.0001242089,0.001055649,0.0001030412,0.0001850398,0.0001626708,0.00055745,0.00001621637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001677629,"about_ca_system_score_gemma":0.0003489699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007118945,"about_ca_topic_score_gemma":0.002365472,"domain_scores_codex":[0.9979498,0.00008516332,0.001027921,0.0001637286,0.0003749627,0.000398364],"domain_scores_gemma":[0.9987933,0.0004273842,0.0001995909,0.0001635823,0.0001816772,0.0002344691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002803679,0.0000354744,0.03859374,0.0003969105,0.0000274014,0.00001008287,0.09311488,0.00001976991,0.00003403974,0.00001036638,0.002487601,0.8649893],"study_design_scores_gemma":[0.00968396,0.001712027,0.5653559,0.002883609,0.0004870729,0.00002192004,0.1748516,0.02486596,0.001475982,0.0001837123,0.2166333,0.001844922],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901442,0.00253123,0.0003025031,0.004646663,0.001063962,0.0005106175,0.0000481137,0.0001319186,0.0006208032],"genre_scores_gemma":[0.9838468,0.0004024431,0.001854506,0.01286426,0.0005110913,0.0002463468,0.00003194582,0.00002893176,0.0002136307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8631445,"threshold_uncertainty_score":0.6503193,"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."}}