{"id":"W4229001541","doi":"10.1061/ajrua6.0001239","title":"Machine Learning–Based Decision Support Framework for Construction Injury Severity Prediction and Risk Mitigation","year":2022,"lang":"en","type":"article","venue":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part A Civil Engineering","topic":"Occupational Health and Safety Research","field":"Health Professions","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Interdependence; Risk analysis (engineering); Set (abstract data type); Risk assessment; Construction site safety; Key (lock); Computer science; Engineering; Business; Computer security","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":[0.004050787,0.0002189978,0.0004830541,0.0005702944,0.0006653334,0.00002508697,0.0001105421,0.0001965534,0.00003634396],"category_scores_gemma":[0.002478316,0.0002183308,0.00007859302,0.000389975,0.00002396969,0.0001913715,0.00006350745,0.002163872,8.479413e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004550237,"about_ca_system_score_gemma":0.0002589728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002917798,"about_ca_topic_score_gemma":0.00004598918,"domain_scores_codex":[0.9972807,0.0003665085,0.001111251,0.000242944,0.00052313,0.0004754365],"domain_scores_gemma":[0.9956337,0.003165298,0.0005550029,0.0001403337,0.0002438541,0.0002617968],"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":[0.0004640123,0.00002522098,0.2068836,0.0006452966,0.00003538682,0.000004153065,0.000438083,0.7852603,0.00003061254,0.0005892431,0.0000733929,0.005550692],"study_design_scores_gemma":[0.001747804,0.000551776,0.08730593,0.0007868051,0.00005106024,0.00005344527,0.0004567893,0.8895214,0.000005343035,0.0002336024,0.01908448,0.0002015742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6646612,0.001487891,0.3291828,0.00007595396,0.002996776,0.0009707581,0.0005338395,0.00007718903,0.00001358654],"genre_scores_gemma":[0.9922767,0.001555411,0.005329121,0.00001036308,0.0004826793,0.0002386507,0.00005583937,0.0000405165,0.0000107341],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3276155,"threshold_uncertainty_score":0.9401067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01431623687441175,"score_gpt":0.3226300763175513,"score_spread":0.3083138394431396,"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."}}