{"id":"W4387117455","doi":"10.1016/j.isci.2023.108006","title":"Targeted deep learning classification and feature extraction for clinical diagnosis","year":2023,"lang":"en","type":"article","venue":"iScience","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of British Columbia","funders":"Scleroderma Society of Ontario","keywords":"Artificial intelligence; Computer science; Machine learning; Class (philosophy); Feature (linguistics); Extractor; Complement (music); Deep learning; Pattern recognition (psychology); Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003610033,0.00005424804,0.00005076392,0.00003811353,0.0001631985,0.00003096704,0.00008445593,0.00009984813,0.000004370875],"category_scores_gemma":[0.0003498902,0.0000490573,0.00003399058,0.0001834595,0.00006915424,0.000007055801,0.00003084605,0.00006524439,0.000008377869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005647133,"about_ca_system_score_gemma":0.0000247597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.527083e-7,"about_ca_topic_score_gemma":0.000003206469,"domain_scores_codex":[0.9993355,0.00004266157,0.000102806,0.0003185063,0.00008150958,0.0001189785],"domain_scores_gemma":[0.9996548,0.00003556693,0.00007053726,0.0001282035,0.00005728509,0.00005359282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002556849,0.00001763574,0.04056443,0.000007212545,0.000003432054,1.595352e-7,0.00004167768,0.00003916807,0.7984009,0.00008140552,0.01622949,0.1445889],"study_design_scores_gemma":[0.0002297991,0.0001309022,0.5332307,0.000006483128,0.000005991931,0.00000183182,0.0002982991,0.005641124,0.04121593,0.0000717572,0.4190678,0.0000993655],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819781,0.001283634,0.01374271,0.001982532,0.0004416401,0.0002255775,0.000003857122,0.00004839612,0.000293546],"genre_scores_gemma":[0.994581,0.002540263,0.0007630933,0.0001166282,0.0001609251,0.0001376674,0.00006860353,0.000006791412,0.001625002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.757185,"threshold_uncertainty_score":0.2000499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05894117063016358,"score_gpt":0.3846485753075375,"score_spread":0.3257074046773739,"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."}}