{"id":"W3107734136","doi":"10.1109/tcbb.2020.3041527","title":"An Enhanced Random Forests Approach to Predict Heart Failure From Small Imbalanced Gene Expression Data","year":2020,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Krembil Foundation","funders":"","keywords":"Random forest; Heart failure; Receiver operating characteristic; Matthews correlation coefficient; Machine learning; Classifier (UML); Artificial intelligence; Rank correlation; Medicine; Internal medicine; Computer science; Support vector machine","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":[0.003176026,0.0007254802,0.0009139529,0.002468216,0.000331411,0.0005234947,0.0006665002,0.0005472273,0.0005915922],"category_scores_gemma":[0.003917755,0.0001992228,0.001182028,0.001431199,0.0001905828,0.0004413099,0.0002823946,0.0005431406,0.0004493454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002779093,"about_ca_system_score_gemma":0.00072699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004639731,"about_ca_topic_score_gemma":0.00807148,"domain_scores_codex":[0.9991763,0.0003481804,0.00006849891,0.0001541192,0.000172255,0.00008060167],"domain_scores_gemma":[0.9983468,0.001156268,0.0001009658,0.00006814043,0.0002881825,0.00003969755],"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":[0.0009933549,0.0005394646,0.03655389,0.0005861798,0.000913518,0.0009993926,0.0001877626,0.2856174,0.02285433,0.002430283,0.009061553,0.6392629],"study_design_scores_gemma":[0.00007226333,0.0001814293,0.007354878,0.00003836969,0.0001866119,0.0002524587,0.00004663331,0.9805785,0.003482349,0.005102267,0.002672756,0.0000314753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1010118,0.003244215,0.8880513,0.0005646107,0.0001464323,0.0002626448,0.003062295,0.002501163,0.001155535],"genre_scores_gemma":[0.6157557,0.001163793,0.3728099,0.0003652706,0.0003587923,0.0004334598,0.007592994,0.0001262832,0.001393974],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004639731,"threshold_uncertainty_score":0.01679665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02880486137066785,"score_gpt":0.2775559790024433,"score_spread":0.2487511176317755,"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."}}