{"id":"W4297817394","doi":"10.17615/hc27-f622","title":"Machine Learning Can Unlock Insights Into Mortality","year":2022,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; Cecil G. Sheps Center for Health Services Research, University of North Carolina, Chapel Hill; Agency for Healthcare Research and Quality; University of North Carolina at Chapel Hill; National Institutes of Health; Hamilton Health Sciences Foundation","keywords":"Computer science; Data science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002774978,0.0001874974,0.0002167749,0.0001714719,0.001335579,0.0002949066,0.001338554,0.00004401738,0.0002770193],"category_scores_gemma":[0.0001727012,0.0001828112,0.00006482723,0.0007700197,0.00007632932,0.0006456613,0.001945691,0.0009492096,0.0000208887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009233235,"about_ca_system_score_gemma":0.00032315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003088625,"about_ca_topic_score_gemma":0.0002355274,"domain_scores_codex":[0.9976432,0.0006394436,0.0002892473,0.0005188403,0.0005684212,0.0003408733],"domain_scores_gemma":[0.9987627,0.0002023599,0.0001460176,0.0006987958,0.00003706176,0.0001530985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006317461,0.00003297428,0.1316031,0.00004677017,0.00002023113,0.00006118602,0.01393021,0.007176159,0.00002307104,0.8412924,0.0005929036,0.005214709],"study_design_scores_gemma":[0.0004018118,0.0004123507,0.0263691,0.00001416929,0.000009405066,0.00002971786,0.0005387212,0.2660278,0.0003595097,0.4228191,0.2824342,0.0005840299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7001451,0.01661709,0.156857,0.05909541,0.006879658,0.001621595,0.00003649167,0.00848907,0.0502586],"genre_scores_gemma":[0.9733049,0.000005000664,0.02296437,0.001691069,0.0001075596,0.00005009649,0.00005136257,0.00002440639,0.001801289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4184732,"threshold_uncertainty_score":0.9999645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02192247443258044,"score_gpt":0.2543086995440863,"score_spread":0.2323862251115059,"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."}}