{"id":"W4414494084","doi":"10.1007/s00371-025-04153-8","title":"Visual-action AI agents for medical diagnosis and treatment: advances and future outlook","year":2025,"lang":"en","type":"article","venue":"The Visual Computer","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China","keywords":"Transformative learning; Medical diagnosis; Personalized medicine; Precision medicine; Clinical diagnosis; 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":[0.0001393659,0.00009222969,0.0001473968,0.00005514987,0.0001857097,0.00002787349,0.00003025513,0.00008241167,0.00004132564],"category_scores_gemma":[0.00002757727,0.00005707879,0.00003237261,0.00008640248,0.00007004454,0.00006969312,0.00002259423,0.00008000284,0.000005321797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004265816,"about_ca_system_score_gemma":0.00007517034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009848062,"about_ca_topic_score_gemma":0.00006602662,"domain_scores_codex":[0.9993785,0.00003882522,0.000173716,0.0001738472,0.0001026578,0.000132464],"domain_scores_gemma":[0.9994742,0.0002706347,0.00003111381,0.00007660971,0.00006144385,0.00008600458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001234549,0.0001457598,0.01784223,0.0001081717,0.00003604471,0.000001236631,0.0008062959,7.498211e-7,0.000005752164,0.0003119691,0.00260878,0.9780096],"study_design_scores_gemma":[0.0005892228,0.003233599,0.04695195,0.000356831,0.0002495802,0.00003145779,0.001805911,0.03880722,0.004447018,0.002555646,0.9007635,0.0002080874],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9472956,0.003184287,0.006325642,0.04089916,0.001459817,0.0007193507,0.000002277195,0.00004225302,0.00007161969],"genre_scores_gemma":[0.9786815,0.009398187,0.0003112417,0.007981663,0.002943339,0.0001925633,0.00002385772,0.00001085222,0.0004568169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9778015,"threshold_uncertainty_score":0.2327606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1134110139919133,"score_gpt":0.5032195380244272,"score_spread":0.3898085240325139,"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."}}