{"id":"W2953216366","doi":"10.1007/s00259-019-04382-9","title":"Why imaging data alone is not enough: AI-based integration of imaging, omics, and clinical data","year":2019,"lang":"en","type":"review","venue":"European Journal of Nuclear Medicine and Molecular Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":140,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; Krembil Foundation; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Radiomics; Artificial intelligence; Data science; Domain (mathematical analysis); Machine learning; Quality (philosophy); Data quality; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006439801,0.0005995697,0.002825089,0.0006899511,0.00009829582,0.0001172946,0.001365417,0.00006514726,0.0000575467],"category_scores_gemma":[0.002973213,0.0004417147,0.0003178039,0.0002530183,0.0008725364,0.0004354736,0.001123487,0.002435468,0.000009290543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004649645,"about_ca_system_score_gemma":0.0003480093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004997371,"about_ca_topic_score_gemma":2.655974e-7,"domain_scores_codex":[0.9942898,0.001056139,0.002494894,0.000968977,0.000788325,0.0004018601],"domain_scores_gemma":[0.9946436,0.0003800762,0.002055104,0.00204671,0.0003542383,0.0005202813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007243745,0.00008553773,0.0002419028,0.003162403,0.0003390541,0.00205604,0.0001697782,2.918945e-7,0.0003088609,0.0000150174,0.1150884,0.8784603],"study_design_scores_gemma":[0.003121566,0.0002168203,0.00007014015,0.02624933,0.005091082,0.003193237,0.0001946359,0.02263911,0.00000369795,0.000005037898,0.9388787,0.0003366428],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00005883264,0.9410837,0.01307862,0.04379088,0.0007579742,0.0004131203,0.0000816754,0.00003058911,0.0007045506],"genre_scores_gemma":[0.001251609,0.9359344,0.01010521,0.05076473,0.001075684,2.508291e-7,0.0005700783,0.0002827924,0.0000152274],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8781236,"threshold_uncertainty_score":0.9998659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1016817237997227,"score_gpt":0.4105108725437765,"score_spread":0.3088291487440538,"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."}}