{"id":"W2948165300","doi":"10.22215/etd/2018-13263","title":"Applying Data Preparation Methods to Optimize Preterm Birth Prediction","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Preterm Birth and Chorioamnionitis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Machine learning; Artificial neural network; Preprocessor; Data pre-processing; Artificial intelligence; Missing data; Decision tree; Random forest; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009092204,0.001301233,0.001030329,0.001692183,0.0005578596,0.001764297,0.001323668,0.0007973709,0.002401437],"category_scores_gemma":[0.03714186,0.0006702895,0.001018943,0.002021659,0.0003793589,0.001500705,0.001252136,0.001776665,0.001867497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006084217,"about_ca_system_score_gemma":0.002113846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003182016,"about_ca_topic_score_gemma":0.003248879,"domain_scores_codex":[0.997373,0.001236618,0.0002771016,0.000492685,0.0005119565,0.0001085709],"domain_scores_gemma":[0.9876543,0.007157153,0.0007597161,0.001464029,0.002795318,0.0001694868],"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":[0.0008495893,0.0004138739,0.01963218,0.0004477642,0.0002838016,0.0001829405,0.0003146936,0.1096657,0.01751628,0.004386337,0.0105298,0.835777],"study_design_scores_gemma":[0.0001342894,0.0005064211,0.01258056,0.0001705788,0.0001822974,0.0001603892,0.0002833373,0.9132816,0.04264274,0.01247407,0.01749774,0.00008597438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0323566,0.0007310215,0.9598798,0.0006446281,0.0002039448,0.0004597309,0.001252107,0.003371835,0.001100399],"genre_scores_gemma":[0.1225731,0.0005378909,0.8705039,0.0001724701,0.0001096991,0.000686516,0.00339882,0.0006165086,0.00140107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009092204,"threshold_uncertainty_score":0.04808474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05054640446387623,"score_gpt":0.4051229426020586,"score_spread":0.3545765381381824,"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."}}