{"id":"W4416544127","doi":"10.48550/arxiv.2504.12270","title":"Comparative analysis of unsupervised clustering techniques using validation metrics: Study on cognitive features from the Canadian Longitudinal Study on Aging (CLSA)","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rand index; Cluster analysis; Hierarchical clustering; Medoid; Cognition; Entropy (arrow of time); Silhouette; Consensus clustering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02780281,0.001307171,0.001054966,0.006351091,0.002235877,0.002280657,0.002087043,0.001158949,0.0005057993],"category_scores_gemma":[0.07549215,0.0002112302,0.001723109,0.004736796,0.0009228469,0.00109761,0.001424971,0.0009286609,0.0002142419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004979094,"about_ca_system_score_gemma":0.005978018,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1742067,"about_ca_topic_score_gemma":0.2238282,"domain_scores_codex":[0.9876432,0.004522874,0.001003927,0.001790847,0.004621397,0.0004177121],"domain_scores_gemma":[0.9251388,0.02866171,0.006597423,0.004485238,0.03368197,0.001434821],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002429171,0.0005752525,0.7838442,0.001674557,0.003933717,0.0002480005,0.005741566,0.02561868,0.002956139,0.002392982,0.01198323,0.1586025],"study_design_scores_gemma":[0.000163051,0.00091024,0.8655148,0.0005527072,0.0007265903,0.0004628506,0.004970405,0.1117403,0.005101798,0.002429303,0.007188515,0.0002395917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578033,0.002796814,0.03042244,0.0003418117,0.0001436125,0.0005509492,0.005116404,0.0003855756,0.002439083],"genre_scores_gemma":[0.9521676,0.0004694729,0.03349683,0.0001024408,0.00004760966,0.0004224575,0.01267554,0.0001213033,0.0004968266],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9721972,"threshold_uncertainty_score":0.3463854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.237956483094046,"score_gpt":0.4546531086857713,"score_spread":0.2166966255917253,"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."}}