{"id":"W4396526950","doi":"10.1093/ckj/sfae136","title":"Optimizing home visits through machine learning for preventing peritoneal dialysis-associated peritonitis: a proof of concept study and results from PDOPPS","year":2024,"lang":"en","type":"article","venue":"Clinical Kidney Journal","topic":"Dialysis and Renal Disease Management","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"St. Michael's Hospital","funders":"Kidney Foundation of Thailand; Royal College of Physicians of Thailand; Thailand Science Research and Innovation; Chulalongkorn University; National Science and Technology Development Agency; Faculty of Medicine, Chulalongkorn University","keywords":"Peritoneal dialysis; Peritonitis; Proof of concept; Medicine; Dialysis; Intensive care medicine; Internal medicine; Computer science; Operating system","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":[0.002621613,0.0002248465,0.0009497136,0.0001202799,0.0002532743,0.0002335216,0.0001367103,0.0001245446,0.00007917969],"category_scores_gemma":[0.005191794,0.0001676783,0.0006418556,0.0002546286,0.0001181054,0.0001758375,0.0001630533,0.0007965732,0.000001778626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005436674,"about_ca_system_score_gemma":0.0002349881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000459073,"about_ca_topic_score_gemma":0.000006951321,"domain_scores_codex":[0.9963911,0.0004976065,0.00181138,0.0005082125,0.0004747732,0.0003169487],"domain_scores_gemma":[0.9976438,0.0009035661,0.0005355556,0.0001880599,0.0002223562,0.0005067122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01573237,0.0265012,0.1887579,0.002492715,0.05256928,0.004426146,0.08269418,0.002268786,0.002563706,0.0001739648,0.02944032,0.5923794],"study_design_scores_gemma":[0.1375018,0.03497932,0.2297346,0.0308155,0.05620926,0.0002838458,0.03318356,0.3930245,0.001892047,0.003699144,0.07528976,0.003386637],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866539,0.005237349,0.0024997,0.002668904,0.0009590928,0.001113392,0.0003153476,0.00007710075,0.0004751814],"genre_scores_gemma":[0.9947399,0.0003011906,0.002648931,0.0002424951,0.001042552,0.00002028286,0.0002194131,0.00004187301,0.0007433558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5889928,"threshold_uncertainty_score":0.6837722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04727756501308536,"score_gpt":0.362847385174861,"score_spread":0.3155698201617756,"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."}}