{"id":"W4378714206","doi":"10.1080/17477778.2023.2217334","title":"Machine learning integrated patient flow simulation: why and how?","year":2023,"lang":"en","type":"article","venue":"Journal of Simulation","topic":"Healthcare Operations and Scheduling Optimization","field":"Health Professions","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Inflow; Computer science; Machine learning; Flow (mathematics); Artificial intelligence; Construct (python library); Industrial engineering; Simulation; Operations research","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":[0.0009986578,0.00009600218,0.0001943002,0.0002878548,0.000652778,0.00003552627,0.00003994399,0.00014135,0.000123791],"category_scores_gemma":[0.00127933,0.00007693996,0.00003957657,0.0004915874,0.00001417741,0.0003639197,0.00002455651,0.0005678333,0.00002090437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037653,"about_ca_system_score_gemma":0.0001465464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001829937,"about_ca_topic_score_gemma":0.00001817923,"domain_scores_codex":[0.9983917,0.0005180899,0.0005358696,0.0001073601,0.0002653715,0.0001815752],"domain_scores_gemma":[0.9977197,0.0006941706,0.000452932,0.00007773437,0.0009441412,0.0001112967],"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":[0.00003786711,0.00001038573,0.01054808,0.00002804956,0.0000112234,0.000004193858,0.002542553,0.9683047,0.00007153171,0.00003188345,0.0003254389,0.01808413],"study_design_scores_gemma":[0.000534654,0.0001722323,0.00261418,0.0001196081,0.00001312751,0.000001559157,0.0009937632,0.9638944,0.000003579934,0.00004960161,0.03153371,0.0000695298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.764816,0.0002240399,0.2263812,0.00688716,0.0009504223,0.000456945,0.00001143837,0.0000990343,0.0001736774],"genre_scores_gemma":[0.9949241,0.0001294536,0.003793713,0.000334358,0.0003358923,0.000003610821,0.0000811487,0.00001891701,0.000378755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2301081,"threshold_uncertainty_score":0.5020707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08317975876338429,"score_gpt":0.4159317185976195,"score_spread":0.3327519598342352,"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."}}