{"id":"W4415128312","doi":"10.1093/tse/tdaf037","title":"A driving risk prediction method for elderly drivers considering data imbalance and feature extraction","year":2025,"lang":"en","type":"article","venue":"Transportation Safety and Environment","topic":"Innovation in Digital Healthcare Systems","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Education and Child Care","funders":"National Natural Science Foundation of China","keywords":"Categorical variable; Reliability (semiconductor); Artificial neural network; Feature (linguistics); Feature extraction; Hazard; Residual; Poison control","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":[0.0008732671,0.0001216002,0.000187045,0.00007296567,0.0007302099,0.00000981239,0.00005849045,0.0001800812,0.00002207025],"category_scores_gemma":[0.00004430692,0.0001244801,0.00001800926,0.00008707227,0.00004141957,0.000348119,0.0000131534,0.0003018266,0.000002793887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001081767,"about_ca_system_score_gemma":0.00005367508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001346648,"about_ca_topic_score_gemma":0.00025537,"domain_scores_codex":[0.9986255,0.0001358018,0.0005219702,0.0003886105,0.0001285028,0.0001996045],"domain_scores_gemma":[0.9989231,0.0004723315,0.0002566183,0.0002597397,0.00003275812,0.00005545433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005160118,0.00005176556,0.827573,0.001809131,0.0001465922,0.000002059987,0.005728704,0.001019337,0.0008480151,0.01071494,0.002887974,0.1487025],"study_design_scores_gemma":[0.001165647,0.00005202909,0.8174471,0.0002685435,0.00006328637,0.000001026884,0.002893819,0.005278759,0.00002249688,0.0008729889,0.1718255,0.0001089106],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08075637,0.0002856221,0.9112682,0.003342177,0.0006247567,0.001723004,0.001216663,0.00009172827,0.0006914931],"genre_scores_gemma":[0.9591902,0.00202781,0.03502947,0.0003635242,0.0001100531,0.0001997858,0.001320748,0.00002100324,0.001737407],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8784338,"threshold_uncertainty_score":0.5616258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04077481255200655,"score_gpt":0.3913958139965679,"score_spread":0.3506210014445613,"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."}}