{"id":"W4414983661","doi":"10.1038/s41514-025-00271-8","title":"Spine age estimation using deep learning in lateral spine radiographs and DXA VFA to predict incident fracture and mortality","year":2025,"lang":"en","type":"article","venue":"npj Aging","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"National Research Foundation of Korea; Ministry of Science and ICT, South Korea; Korea Health Industry Development Institute; National Research Foundation; Korea Disease Control and Prevention Agency","keywords":"Radiography; Femoral neck; Osteoporosis; Cohort; Hip fracture; Fracture (geology); Cohort study","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":[0.0002534621,0.0001221438,0.0002056895,0.0003182335,0.00006558,0.00007944604,0.00004653578,0.00004772258,0.000008523839],"category_scores_gemma":[0.00008083431,0.0001203714,0.00002767401,0.0004107533,0.00002611098,0.0001209194,0.00003910375,0.0002604383,4.428076e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004157325,"about_ca_system_score_gemma":0.000005704495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000316501,"about_ca_topic_score_gemma":0.00005160107,"domain_scores_codex":[0.9992688,0.00002807006,0.0002079361,0.0001853815,0.0001209243,0.0001888474],"domain_scores_gemma":[0.9997677,0.00001616731,0.00002165103,0.00009409278,0.00001173936,0.00008861889],"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":[8.307818e-7,0.000008799482,0.5997909,0.000215559,0.00007030731,0.00005202555,0.0009457004,0.3572002,0.004303114,0.0000160601,0.0000280053,0.03736855],"study_design_scores_gemma":[0.0001671073,0.000003334599,0.3823561,0.0002330595,0.00004142013,0.000002067442,0.00003455535,0.6166784,0.0001778496,0.0001250277,0.0001012466,0.0000798679],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8545245,0.0008115256,0.1441171,0.0001918358,0.00005400427,0.00006469542,3.321256e-7,0.0001095903,0.0001264414],"genre_scores_gemma":[0.9944634,0.00005752219,0.005171968,0.0002178089,0.00003371024,0.000003961371,0.00001113771,0.00001089235,0.00002963118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2594782,"threshold_uncertainty_score":0.4908602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006625199806437918,"score_gpt":0.265774045226449,"score_spread":0.259148845420011,"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."}}