{"id":"W2184549704","doi":"10.1136/amiajnl-2012-000929","title":"Discretization of continuous features in clinical datasets","year":2012,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Discretization; Computer science; Artificial intelligence; Unsupervised learning; Machine learning; Consistency (knowledge bases); Pattern recognition (psychology); Naive Bayes classifier; Decision tree; Class (philosophy); Data mining; Mathematics; Support vector machine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00638237,0.00006372917,0.0003325361,0.00009436832,0.00003448375,0.00002590515,0.0008292309,0.00007331881,0.000004008477],"category_scores_gemma":[0.009721448,0.00004015761,0.0001025255,0.0004770533,0.00006812468,0.0005349806,0.0001770217,0.0007105466,0.000002501179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611985,"about_ca_system_score_gemma":0.0001953178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006770131,"about_ca_topic_score_gemma":0.00001215587,"domain_scores_codex":[0.9966873,0.0005601874,0.001327279,0.00003258821,0.001195465,0.0001971582],"domain_scores_gemma":[0.9943627,0.0008196122,0.004271003,0.0002294391,0.0001658504,0.000151396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009624823,0.00008798124,0.9351355,0.00002345,0.0000261997,6.482175e-7,0.001930516,0.0001096427,0.000002093884,0.002202868,0.006460701,0.05401078],"study_design_scores_gemma":[0.0003714097,0.0001399607,0.9775916,0.0001181969,0.00001264937,0.00002758711,0.0002920874,0.01872027,0.00001963823,0.0001937903,0.002449829,0.00006296392],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9256294,0.0001157405,0.05939389,0.01254406,0.001663269,0.000151857,0.00001186356,0.00001418734,0.0004757488],"genre_scores_gemma":[0.9874731,0.00009144154,0.01053913,0.001668275,0.0002063836,5.835876e-7,0.000004418695,0.000003332312,0.00001331257],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06184374,"threshold_uncertainty_score":0.9986201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01072032458380675,"score_gpt":0.3505241223265846,"score_spread":0.3398037977427779,"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."}}