{"id":"W6981713620","doi":"","title":"Exploration of Dimensionality Reduction Techniques for Improving Cancer Classification Accuracy: A Machine Learning Approach to Analyzing Single Extracellular Vesicles via Surface-Enhanced Raman Spectroscopy","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Cancer Society Research Institute; McGill University Health Centre; Canadian Institutes of Health Research; Fonds de recherche du Québec – Nature et technologies; Fondation Charles-Bruneau; Canada Research Chairs; McGill University","keywords":"Dimensionality reduction; Curse of dimensionality; Raman spectroscopy; Extracellular vesicles; Reduction (mathematics); Cancer; Pattern recognition (psychology)","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":[0.002418253,0.0007216185,0.0009061603,0.0008613733,0.0004304844,0.001501162,0.0006120743,0.0006334595,0.0007703769],"category_scores_gemma":[0.003719975,0.0002826279,0.00119884,0.0008400957,0.0005397013,0.001180179,0.0008388742,0.001263223,0.0003589244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000638956,"about_ca_system_score_gemma":0.000801679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001154823,"about_ca_topic_score_gemma":0.001395158,"domain_scores_codex":[0.9989823,0.0003015563,0.00007149704,0.0001823246,0.000394844,0.00006746892],"domain_scores_gemma":[0.9979752,0.0009335467,0.0002030252,0.0002489365,0.0005958689,0.00004330863],"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":[0.0002792995,0.0003642967,0.003914005,0.0004005339,0.000313028,0.0001162506,0.000424652,0.1289964,0.2176018,0.01311785,0.003469486,0.6310024],"study_design_scores_gemma":[0.0000209604,0.0002027631,0.00340335,0.00003761645,0.000106678,0.0001549519,0.0001000306,0.8781809,0.1065635,0.008604555,0.002562075,0.00006255698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1087803,0.002135196,0.8848507,0.001344641,0.0000836113,0.00009687285,0.0001654281,0.0006969825,0.001846222],"genre_scores_gemma":[0.328022,0.001947973,0.6666729,0.0001925637,0.00008004148,0.0001147721,0.0002540863,0.0001478893,0.002567839],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002418253,"threshold_uncertainty_score":0.01278907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03163160112760252,"score_gpt":0.3225906411487492,"score_spread":0.2909590400211467,"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."}}