{"id":"W4404754793","doi":"10.1182/bloodadvances.2024014929","title":"Generalized additive logit models for clinical prediction","year":2024,"lang":"en","type":"article","venue":"Blood Advances","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Government of Canada; Statistics Canada","funders":"","keywords":"Logit; Logistic regression; Generalized additive model; Econometrics; Mixed logit; Statistics; Mathematics; Computer science","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":[0.0004426315,0.000115062,0.0001712624,0.00006448365,0.0001098331,0.0001246108,0.0004018218,0.00007486287,0.00001030886],"category_scores_gemma":[0.0001695366,0.00009735912,0.0001162511,0.0001991124,0.00003951953,0.0008327101,0.00009191511,0.0002120248,0.0000182799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001489537,"about_ca_system_score_gemma":0.00009783919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009686375,"about_ca_topic_score_gemma":0.000007756468,"domain_scores_codex":[0.9985794,0.0001231529,0.0003301935,0.0005446746,0.0001844294,0.0002380817],"domain_scores_gemma":[0.9988629,0.000607891,0.00006245703,0.0002922374,0.00008883061,0.00008570743],"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":[0.00002633506,0.00011682,0.00253858,0.0002666262,0.00008844519,0.00003046401,0.0004762097,0.01146101,0.00002034234,0.3948759,0.006377558,0.5837218],"study_design_scores_gemma":[0.0003655521,0.0003362383,0.0004443207,0.00008316671,0.00002069137,0.00001454505,0.000009558145,0.7410269,0.000113857,0.06126641,0.196191,0.0001277992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003887917,0.0150691,0.9727744,0.00237884,0.002848258,0.0004734319,0.0001108212,0.0009769569,0.001480218],"genre_scores_gemma":[0.4267167,0.005158473,0.5613611,0.001289656,0.002831237,0.0005664516,0.00008970031,0.00005104415,0.001935604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7295659,"threshold_uncertainty_score":0.3970189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06752517926557867,"score_gpt":0.3967653649223084,"score_spread":0.3292401856567297,"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."}}