{"id":"W4399679571","doi":"10.1038/s41591-024-03040-4","title":"Ultrasensitive plasma-based monitoring of tumor burden using machine-learning-guided signal enrichment","year":2024,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"Daiichi Sankyo Europe; National Cancer Institute; Medical Research Council; Chugai Pharmaceutical; Genentech; Bispebjerg Hospital; Novo Nordisk Fonden; Dansk Kræftforsknings Fond; Novo Nordisk; Wellcome Trust; Cancer Research UK; Vissing Fonden; BeiGene; Tizona Therapeutics; Ascentage Pharma; Ipsen; Jazz Pharmaceuticals; Moderna; Pfizer; Incyte; New York Genome Center; Burroughs Wellcome Fund; Francis Crick Institute; Dagmar Marshalls Fond; National Institutes of Health; Rosetrees Trust; Dr. Miriam and Sheldon G. Adelson Medical Research Foundation; Natera; National Institute for Health and Care Research; Melanoma Research Alliance; Bristol-Myers Squibb; Gangstedfonden; Eli Lilly and Company; AstraZeneca; Augustinus Fonden; U.S. Department of Health and Human Services; Hvidovre Hospital; Conquer Cancer Foundation; Memorial Sloan-Kettering Cancer Center","keywords":"SIGNAL (programming language); Computer science; Medicine; Computational biology; Biology","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":[0.0003949194,0.0005772972,0.000431242,0.0004771083,0.0001662641,0.0006148565,0.0004592444,0.000706545,0.00124608],"category_scores_gemma":[0.001334435,0.0002732669,0.0002768428,0.0003542121,0.0003721763,0.000584336,0.000617248,0.0007607112,0.0006200847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003720297,"about_ca_system_score_gemma":0.0002804031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006035667,"about_ca_topic_score_gemma":0.001185684,"domain_scores_codex":[0.9995971,0.00007971078,0.00001495506,0.0001588083,0.0001161744,0.00003313062],"domain_scores_gemma":[0.9996686,0.0001625461,0.00006351425,0.0000330866,0.00005207006,0.00002020086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006030556,0.0001505066,0.01120817,0.0004057157,0.0001146467,0.0003343682,0.0001487878,0.02223219,0.8077796,0.003010376,0.004310105,0.1497025],"study_design_scores_gemma":[0.00005932845,0.0003206113,0.006764249,0.00005214485,0.00006613204,0.0006048017,0.00005850169,0.3011159,0.6719828,0.006121303,0.01276904,0.00008530123],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3436541,0.005978988,0.6332578,0.001400436,0.0002277803,0.000125246,0.002357185,0.005510926,0.007487514],"genre_scores_gemma":[0.7991903,0.001635193,0.1912877,0.001176766,0.0001046768,0.0001871854,0.001688716,0.0004105896,0.0043189],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00124608,"threshold_uncertainty_score":0.00416863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01027011795806428,"score_gpt":0.2851586058600222,"score_spread":0.274888487901958,"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."}}