{"id":"W4408919541","doi":"10.1016/j.aej.2025.03.089","title":"XGBoost-based model for predicting PICC occlusion risk in cancer patients: Insights from SHAP analysis","year":2025,"lang":"en","type":"article","venue":"Alexandria Engineering Journal","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"Natural Science Foundation for Young Scientists of Shanxi Province; National Natural Science Foundation of China","keywords":"Medicine; Occlusion; Environmental science; Environmental health; Statistics; Mathematics; Internal medicine","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":[0.0001640302,0.0001279588,0.000279363,0.0006091002,0.0001456246,0.00003342559,0.00007870085,0.0001137037,0.00005249597],"category_scores_gemma":[0.0004974992,0.0001152362,0.0001430954,0.0005674261,0.000009818323,0.0001067111,0.0000143446,0.0003681155,0.000001862978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003335901,"about_ca_system_score_gemma":0.0002903831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009257678,"about_ca_topic_score_gemma":0.0008129404,"domain_scores_codex":[0.9988567,0.00002147077,0.0005318963,0.0001949003,0.0001688815,0.0002261784],"domain_scores_gemma":[0.9990815,0.000271932,0.0001304234,0.000138532,0.0002576414,0.0001199743],"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":[0.0001286024,0.0001017941,0.4192063,0.0000431361,0.0001571954,0.00000200675,0.0008796859,0.5753983,0.0003010754,0.00001428397,0.0002390338,0.003528547],"study_design_scores_gemma":[0.0003273709,0.00006897224,0.06576322,0.0003778021,0.0004832414,3.89617e-7,0.00009639648,0.9312618,0.001155849,0.00022536,0.0001501916,0.000089431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7475516,0.000493621,0.250729,0.0003216031,0.0006195697,0.0002193743,0.00002229631,0.00002459917,0.00001837244],"genre_scores_gemma":[0.9945862,0.00019907,0.004503539,0.0002186665,0.0002988452,0.00003734749,0.00007026978,0.0000145169,0.00007155517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3558634,"threshold_uncertainty_score":0.4699194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04229824701511224,"score_gpt":0.354481926946614,"score_spread":0.3121836799315017,"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."}}