{"id":"W4324018008","doi":"10.1289/ehp11305","title":"HExpPredict: <i>In Vivo</i> Exposure Prediction of Human Blood Exposome Using a Random Forest Model and Its Application in Chemical Risk Prioritization","year":2023,"lang":"en","type":"article","venue":"Environmental Health Perspectives","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Fudan University","keywords":"Exposome; Prioritization; Random forest; Risk assessment; Environmental health; Environmental science; Computational biology; Environmental chemistry; Medicine; Biology; Computer science; Chemistry; Machine learning; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009601656,0.0002469843,0.0003548644,0.0001964444,0.0002183678,0.000008942001,0.000130419,0.0001449671,0.00006162356],"category_scores_gemma":[0.00004604083,0.0002891673,0.00004865544,0.0003958534,0.0002760646,0.0004171049,0.0001944186,0.000348524,0.0000166668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038606,"about_ca_system_score_gemma":0.00002450897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000603742,"about_ca_topic_score_gemma":0.0002382267,"domain_scores_codex":[0.9972023,0.0002610653,0.0006663668,0.0008762679,0.0004665632,0.000527483],"domain_scores_gemma":[0.9991671,0.00008878591,0.0002967959,0.0002557307,0.000002358208,0.0001891922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006583933,0.0004536062,0.6896281,0.00007350522,0.000008881011,0.000004263226,0.01270621,0.02817036,0.267882,0.0000497713,0.000006404393,0.0009510271],"study_design_scores_gemma":[0.004361781,0.0002908717,0.7198567,0.0001191071,0.00002326313,0.000009755936,0.006511678,0.2620349,0.005690513,0.0008149515,0.00001051061,0.0002759589],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965783,0.0004926142,0.0007938463,0.0001217703,0.00001998051,0.001588102,0.0002003007,0.0000546271,0.0001504891],"genre_scores_gemma":[0.9970898,0.002139717,0.000384814,0.00005401621,0.00003897307,0.0001742127,0.00005110458,0.00004287161,0.00002447912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2621915,"threshold_uncertainty_score":0.9999561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0146778915628007,"score_gpt":0.2671195492152401,"score_spread":0.2524416576524394,"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."}}