{"id":"W3001400349","doi":"10.1016/j.clnu.2020.01.008","title":"Automated body composition analysis of clinically acquired computed tomography scans using neural networks","year":2020,"lang":"en","type":"article","venue":"Clinical Nutrition","topic":"Nutrition and Health in Aging","field":"Medicine","cited_by":118,"is_retracted":false,"has_abstract":false,"ca_institutions":"Clinical Evaluation Research Unit; Queen's University; Kingston General Hospital; University of Alberta; University of Waterloo","funders":"National Cancer Institute","keywords":"Medicine; Adipose tissue; Skeletal muscle; Sarcopenia; Radiology; Computed tomography; Nuclear medicine; Internal medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0006501522,0.0001852646,0.001171477,0.0003614524,0.0001189597,0.00002400783,0.0001200956,0.0003269968,0.0001058866],"category_scores_gemma":[0.0001560854,0.0001906293,0.0008404583,0.002429582,0.0002532155,0.0001001605,0.00004768217,0.0003670582,0.000005459917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000384745,"about_ca_system_score_gemma":0.00004431013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000118579,"about_ca_topic_score_gemma":0.000001160143,"domain_scores_codex":[0.9962336,0.0003864894,0.002275786,0.0004789517,0.0003207877,0.0003043547],"domain_scores_gemma":[0.9976662,0.0005207615,0.0005833487,0.0002699972,0.0004150706,0.0005446122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01363916,0.012422,0.906177,0.002733224,0.004745468,0.0002181078,0.0002438947,0.0193947,0.01713508,0.0003211713,0.01688978,0.006080357],"study_design_scores_gemma":[0.004776854,0.000973616,0.1195962,0.0003313361,0.001853334,0.000009561168,0.00003220408,0.872048,0.00006006885,0.00003077834,0.0001453621,0.0001426959],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9584563,0.0003448401,0.03113232,0.007918964,0.0004203982,0.0008646743,0.00006612443,0.0007237301,0.00007261949],"genre_scores_gemma":[0.974607,0.0001783987,0.01517573,0.008366388,0.0006995079,0.00001001464,0.000939013,0.00002296264,0.000001005487],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8526533,"threshold_uncertainty_score":0.7773636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1056277538508154,"score_gpt":0.4296706755749973,"score_spread":0.3240429217241819,"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."}}