{"id":"W4289343326","doi":"10.21203/rs.3.rs-1875351/v1","title":"A comparison of machine learning methods to predict survival times for cancer patients: Incorporating time-varying covariates","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Institute for Clinical Evaluative Sciences; Cancer Care Ontario","keywords":"Covariate; Proportional hazards model; Artificial intelligence; Machine learning; Survival analysis; Lasso (programming language); Gradient boosting; Elastic net regularization; Hazard ratio; Statistics; Population; Random forest; Computer science; Econometrics; Mathematics; Medicine; Feature selection; Confidence interval","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.01521334,0.0008015304,0.001044372,0.001606159,0.0003050088,0.0008275928,0.0008969201,0.0009139329,0.000742659],"category_scores_gemma":[0.01881663,0.0002306015,0.001139612,0.001080168,0.0003192669,0.0008505073,0.0007016012,0.001348003,0.0002144215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009831351,"about_ca_system_score_gemma":0.001584826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01176837,"about_ca_topic_score_gemma":0.006225271,"domain_scores_codex":[0.9966472,0.002496426,0.0001312957,0.0003035681,0.0003052079,0.0001163023],"domain_scores_gemma":[0.9835975,0.01363131,0.0007610308,0.0006702988,0.001022203,0.0003176778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002555608,0.0007063323,0.1882117,0.0002322082,0.001235925,0.00007702617,0.0001029594,0.6196575,0.0006235968,0.002718977,0.003198968,0.1806792],"study_design_scores_gemma":[0.00004233028,0.0003063759,0.01148286,0.00003227685,0.00005888467,0.00002062932,0.00002488578,0.9862552,0.0002998261,0.001118627,0.0003438352,0.00001430101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8132613,0.006148271,0.1732304,0.002472165,0.0004463972,0.0001891278,0.001191463,0.0006555944,0.0024053],"genre_scores_gemma":[0.9640212,0.0006450696,0.03349375,0.0001800683,0.0001177698,0.00007680123,0.0008229663,0.00003315213,0.0006092083],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01521334,"threshold_uncertainty_score":0.08045679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2133557829917201,"score_gpt":0.5354164724147623,"score_spread":0.3220606894230422,"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."}}