{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008268117,0.0004426447,0.0006022856,0.00209813,0.0003905221,0.001753527,0.0008773195,0.0006680587,0.0008067813],"category_scores_gemma":[0.03651823,0.0002478515,0.0008876311,0.002381885,0.000996105,0.001016745,0.001068666,0.001260757,0.0002767689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009306032,"about_ca_system_score_gemma":0.001058945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001614947,"about_ca_topic_score_gemma":0.001587876,"domain_scores_codex":[0.9940036,0.003053701,0.0008944427,0.0009000397,0.0009822781,0.0001660083],"domain_scores_gemma":[0.9592677,0.03251792,0.002913474,0.003450917,0.001613122,0.0002368764],"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":[0.001174237,0.000430708,0.1489884,0.001103257,0.0005641008,0.0005555478,0.001233889,0.3484147,0.007341281,0.01102373,0.006724905,0.4724452],"study_design_scores_gemma":[0.000230565,0.0005925148,0.0536829,0.0004756177,0.0001623314,0.001164766,0.0007931931,0.851458,0.01098767,0.0695067,0.01082663,0.0001192146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3733594,0.002090816,0.6125432,0.001859685,0.0001859146,0.0005577566,0.00564579,0.001338392,0.002419],"genre_scores_gemma":[0.6595393,0.0004080473,0.3337531,0.0002666564,0.0001064432,0.0004566023,0.00514686,0.00006829262,0.0002545971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008268117,"threshold_uncertainty_score":0.0437265,"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."}}