{"id":"W4366989955","doi":"10.1002/cjce.24922","title":"Haemoglobin response modelling under erythropoietin treatment: Physiological model‐informed machine learning method","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Erythropoietin; Artificial neural network; Computer science; Machine learning; Artificial intelligence; Medicine; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0003058051,0.0001520859,0.0002173196,0.0001046714,0.0001313532,0.00004527186,0.0001670294,0.0000561275,0.00009431499],"category_scores_gemma":[0.00002541432,0.0001024874,0.0001730612,0.0002289778,0.00003725552,0.00007390246,0.00001464248,0.0004633607,0.000009503667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001499818,"about_ca_system_score_gemma":0.0002397983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005598415,"about_ca_topic_score_gemma":0.000008980271,"domain_scores_codex":[0.9991384,0.00004764186,0.0002570089,0.00009981583,0.0001142042,0.0003429632],"domain_scores_gemma":[0.9992646,0.000180915,0.00008659258,0.0001017365,0.0000438227,0.000322337],"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":[0.00004469358,0.000004118415,0.000008144935,0.000002067137,0.00004508059,0.000004719306,0.0001943896,0.9817179,0.01613451,0.0009251832,0.0001885586,0.0007305971],"study_design_scores_gemma":[0.0002849503,0.00003366073,0.000005186335,0.00002348869,0.00002127399,0.0000174806,0.00003790725,0.9878624,0.009640763,0.001043952,0.0009184465,0.0001105058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8730178,0.00008051259,0.1251255,0.001384322,0.0001421914,0.00007329603,0.000009592484,0.00003620399,0.0001305904],"genre_scores_gemma":[0.9972578,0.000005690172,0.002087002,0.0000333648,0.0002767745,0.000003757767,0.00001109359,0.00002143964,0.0003030655],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.12424,"threshold_uncertainty_score":0.4179315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04126560349640085,"score_gpt":0.2673935642281404,"score_spread":0.2261279607317395,"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."}}