{"id":"W4408672006","doi":"10.1101/2025.03.16.25323714","title":"Deep learning predicts onset acceleration of 38 age-associated diseases from blood and body composition biomarkers in the UK Biobank","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Biobank; Composition (language); Medicine; Acceleration; Physiology; Internal medicine; Bioinformatics; Biology; Physics","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":[0.0007759269,0.0002514444,0.0003786506,0.0002813962,0.0001780207,0.0002248672,0.001017425,0.0002501984,0.00001080606],"category_scores_gemma":[0.0006085538,0.0002182552,0.00008377428,0.0004548792,0.00008071624,0.0001038863,0.0008079167,0.0008919368,0.000001191809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006272971,"about_ca_system_score_gemma":0.000141596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002092199,"about_ca_topic_score_gemma":0.0003776943,"domain_scores_codex":[0.9964651,0.001664948,0.0005091334,0.0006553346,0.000455791,0.0002496841],"domain_scores_gemma":[0.9978534,0.0008765333,0.0004480554,0.0006403436,0.0001108051,0.00007083641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002093385,0.0001332168,0.9919355,0.0002152852,0.0001305217,0.00004795305,0.002492043,0.002163165,0.0002317845,0.0001593876,0.00004194854,0.002428258],"study_design_scores_gemma":[0.0003667497,0.00006987729,0.8597502,0.0005228082,0.00006643093,0.000001852328,0.00004331692,0.1379797,0.00008781927,0.0009406056,0.00001516218,0.000155482],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909316,0.00114845,0.005417574,0.001182668,0.0003940673,0.0005529355,0.00009005366,0.0001422933,0.0001403225],"genre_scores_gemma":[0.9975265,0.0001750962,0.001528875,0.0001352478,0.00004250816,0.00006153548,0.0005092547,0.000009611688,0.00001140009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1358166,"threshold_uncertainty_score":0.8900189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01738355118521172,"score_gpt":0.2814554728018129,"score_spread":0.2640719216166011,"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."}}