{"id":"W4399107553","doi":"10.1016/j.media.2024.103225","title":"MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Graph; Machine learning; Theoretical computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007941656,0.001409136,0.0008491174,0.001655657,0.0004513108,0.001209719,0.002145972,0.001590653,0.02665816],"category_scores_gemma":[0.00486136,0.0007490284,0.001180247,0.001178712,0.0004048833,0.001726268,0.002693836,0.001922433,0.007872608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006935548,"about_ca_system_score_gemma":0.0009895539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004642146,"about_ca_topic_score_gemma":0.007691097,"domain_scores_codex":[0.9996141,0.0000933541,0.00002277155,0.0001188251,0.0001178076,0.00003315837],"domain_scores_gemma":[0.9990425,0.000460968,0.00005413665,0.0002395762,0.0001315231,0.00007135803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006357927,0.0003015631,0.00154781,0.0006786845,0.0002055411,0.0004343245,0.0001308239,0.05943068,0.01066392,0.009650791,0.1557148,0.7606052],"study_design_scores_gemma":[0.0001137834,0.0001125625,0.0006348445,0.00004037542,0.00003344167,0.0001765624,0.00003724087,0.9358125,0.01002521,0.03121193,0.02176254,0.00003906336],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006468911,0.000286284,0.8276287,0.0005563493,0.0001782134,0.0003349702,0.008853707,0.1537921,0.001900769],"genre_scores_gemma":[0.09306851,0.0003270673,0.878721,0.0005423647,0.00009423757,0.000833235,0.01486091,0.006196587,0.005356085],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02665816,"threshold_uncertainty_score":0.08918041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01196817928201128,"score_gpt":0.3037900918022589,"score_spread":0.2918219125202476,"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."}}