{"id":"W4408945665","doi":"10.1101/2025.03.25.25324645","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":"preprint","venue":"medRxiv","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":0,"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":"SPINE (molecular biology); Radiography; Fracture (geology); Estimation; Orthodontics; Medicine; Geology; Radiology; Biology; Engineering; Paleontology; Bioinformatics","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"],"consensus_categories":[],"category_scores_codex":[0.0004508794,0.0002683956,0.0004798044,0.0004652509,0.00004999799,0.0001010963,0.0001176008,0.0001903266,0.00001626925],"category_scores_gemma":[0.0001883339,0.0002608688,0.00007032308,0.0003265465,0.00004517562,0.00006683334,0.0001962397,0.0008257988,6.30891e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005776275,"about_ca_system_score_gemma":0.00001549939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004963186,"about_ca_topic_score_gemma":0.00009343379,"domain_scores_codex":[0.9986877,0.00007049696,0.0003884373,0.0003882775,0.0002275213,0.0002375695],"domain_scores_gemma":[0.9994912,0.00002254622,0.00006055651,0.0002325774,0.00002342298,0.0001697305],"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":[9.383144e-7,0.000009577681,0.4990883,0.0005483232,0.0001035857,0.00006213548,0.0005060793,0.4927436,0.0004961285,0.000002893589,0.00001253624,0.0064259],"study_design_scores_gemma":[0.0001263287,0.000004810468,0.4474444,0.0004726554,0.00009632252,0.000002020316,0.00000922909,0.5513731,0.00007107355,0.000166757,0.00008571619,0.0001475912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8982252,0.001344424,0.09973162,0.0001426057,0.0001574464,0.0001661661,0.000003768037,0.0001589205,0.00006985199],"genre_scores_gemma":[0.992898,0.0003029172,0.006466325,0.0001103855,0.00007524325,0.00001656867,0.00006607812,0.00001998857,0.00004442997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09467287,"threshold_uncertainty_score":0.9999843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01156681405721474,"score_gpt":0.2746833055226162,"score_spread":0.2631164914654014,"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."}}