{"id":"W4416832596","doi":"10.1016/j.tjpad.2025.100398","title":"Towards an AI biomedical scientist: Accelerating discoveries in neurodegenerative disease","year":2025,"lang":"en","type":"article","venue":"The Journal of Prevention of Alzheimer s Disease","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Future Earth; Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; National Institute on Aging","keywords":"Workflow; Neuroinformatics; Disease; Scientific discovery; Function (biology); Data sharing; Translational research; Human disease","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":[0.001665707,0.000148163,0.0002116441,0.0001449307,0.0001837102,0.00004139955,0.0003975196,0.00002776384,0.0008054995],"category_scores_gemma":[0.0002812551,0.0001089661,0.0001244141,0.0004203708,0.0005605528,0.0008988296,0.0002396091,0.0002627283,0.00001124167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009280255,"about_ca_system_score_gemma":0.0002675752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005555458,"about_ca_topic_score_gemma":0.0000322257,"domain_scores_codex":[0.9974317,0.0007840045,0.0006654582,0.0002420328,0.0006349804,0.0002418516],"domain_scores_gemma":[0.9988482,0.00006376041,0.0003836081,0.0003057132,0.00002756605,0.0003711731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005385157,0.01215381,0.4367406,0.0003634199,0.0009192019,0.0005278155,0.009460184,0.04211013,0.05497148,0.005416086,0.006049093,0.425903],"study_design_scores_gemma":[0.0008831822,0.0001771117,0.9853209,0.0002294773,0.0004676174,0.000003100228,0.0003483136,0.00319939,0.002401479,0.006313435,0.0005054948,0.0001504973],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877581,0.0008304984,0.007088032,0.003219596,0.0002482355,0.0003684101,0.00003118587,0.000006454847,0.0004494886],"genre_scores_gemma":[0.9985651,0.00009894446,0.0004499744,0.000718184,0.00004871255,0.000007685117,0.000006697112,0.00001037255,0.00009429343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5485803,"threshold_uncertainty_score":0.8819655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02850317457622134,"score_gpt":0.3320927127659601,"score_spread":0.3035895381897387,"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."}}