{"id":"W4381987696","doi":"10.21037/jmai-23-10","title":"Approximating femoral neck bone mineral density from hand, knee, and pelvis X-rays using deep learning","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Artificial Intelligence","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Activation Laboratories; University of Toronto; AUG Signals (Canada); Sunnybrook Health Science Centre; Health Sciences Centre","funders":"","keywords":"Pelvis; Bone mineral; Femoral neck; Medicine; Orthodontics; Geology; Radiology; Anatomy; Computer science; Osteoporosis; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004902511,0.0006515938,0.0003425072,0.0006120918,0.0001404836,0.0004909653,0.0006855208,0.0005607182,0.001087547],"category_scores_gemma":[0.001867398,0.0002374267,0.0004328107,0.000394428,0.0002327707,0.0003145216,0.0005761115,0.0005771561,0.0003489644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007368055,"about_ca_system_score_gemma":0.0007502214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01738109,"about_ca_topic_score_gemma":0.0162424,"domain_scores_codex":[0.9998289,0.00003318625,0.00001005435,0.00005625281,0.00003809586,0.00003348853],"domain_scores_gemma":[0.9996102,0.0001856159,0.00006621047,0.00002960347,0.00008448234,0.00002386259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006053242,0.0004393885,0.07121564,0.0001890196,0.0002264834,0.0002558984,0.0001286691,0.6354562,0.0113002,0.001024929,0.003447579,0.2757106],"study_design_scores_gemma":[0.00001420375,0.00004849186,0.007225984,0.00001790886,0.00001731258,0.00007969121,0.00001787503,0.9887683,0.002555462,0.0008810899,0.0003649558,0.000008766563],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5467932,0.0009128448,0.4461002,0.0003724275,0.00005949471,0.00009935023,0.001348992,0.0017914,0.002522023],"genre_scores_gemma":[0.9407169,0.0002163092,0.0561985,0.0001097492,0.00002113312,0.00007720081,0.001153619,0.00003149858,0.001475065],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01738109,"threshold_uncertainty_score":0.03455979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0887147532116295,"score_gpt":0.3455559096741161,"score_spread":0.2568411564624866,"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."}}