{"id":"W3173809984","doi":"10.1371/journal.pone.0252384","title":"A machine learning based exploration of COVID-19 mortality risk","year":2021,"lang":"en","type":"article","venue":"PLoS ONE","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Children's Hospital of Western Ontario; Children’s Health Research Institute; Western University","funders":"","keywords":"Machine learning; Triage; Support vector machine; Computer science; Artificial intelligence; Predictive modelling; Feature (linguistics); Wearable computer; Coronavirus disease 2019 (COVID-19); Intensive care medicine; Medicine; Medical emergency; Internal medicine; Disease","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005005774,0.0001141722,0.0003691701,0.00010366,0.00008456071,0.00001331627,0.00005195979,0.00007194497,0.0006733346],"category_scores_gemma":[0.008650531,0.0001192856,0.00008808701,0.0003743102,0.00004976116,0.0001007068,0.00004152264,0.0002795608,0.00003125125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001711574,"about_ca_system_score_gemma":0.0006399936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007794959,"about_ca_topic_score_gemma":0.000209203,"domain_scores_codex":[0.9984711,0.000265711,0.0002973468,0.0002924533,0.0005203555,0.0001530428],"domain_scores_gemma":[0.9984228,0.0005456005,0.0001824166,0.0004135109,0.0002395,0.0001961822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002863672,0.008529315,0.8742521,0.003181697,0.000805179,0.0002550349,0.001582496,0.005215787,0.1040519,0.0001124647,0.000967606,0.0007600126],"study_design_scores_gemma":[0.01008233,0.00114279,0.08329175,0.001830706,0.004509274,0.000007792462,0.0004735211,0.1825166,0.6963837,0.001059044,0.01804684,0.0006555775],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9557625,0.0006111023,0.008138086,0.0346285,0.00003679246,0.0003844089,0.00005614876,0.0002169868,0.0001654662],"genre_scores_gemma":[0.9859289,0.0002791018,0.003940537,0.009205569,0.00008968876,0.00004218396,0.000226861,0.00002798537,0.0002591962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7909604,"threshold_uncertainty_score":0.9997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1637942786846126,"score_gpt":0.3482279431018888,"score_spread":0.1844336644172762,"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."}}