{"id":"W4382239691","doi":"10.1609/aaai.v37i4.25643","title":"Heterogeneous Graph Learning for Multi-Modal Medical Data Analysis","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Modal; Modalities; Graph; Medical diagnosis; Fuse (electrical); Artificial intelligence; Data mining; Machine learning; Theoretical computer science; Medicine","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":[0.001395981,0.0002098034,0.0003222295,0.0004032827,0.0003361507,0.0002359137,0.004622058,0.0001403301,0.0000490556],"category_scores_gemma":[0.001392521,0.0001680793,0.0002143667,0.002967718,0.0002322564,0.0004266017,0.00126698,0.0003597969,0.00006959046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004566717,"about_ca_system_score_gemma":0.0001360656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006769528,"about_ca_topic_score_gemma":0.00009094752,"domain_scores_codex":[0.9972558,0.00002751752,0.0005585544,0.0008655706,0.0008580949,0.000434435],"domain_scores_gemma":[0.9981276,0.0002062276,0.0003663214,0.0006563339,0.0005117935,0.0001316803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002185339,0.0003468643,0.002491208,0.0001817456,0.0007271791,0.000004738678,0.002751542,0.01343651,0.01763821,0.3702981,0.0008626897,0.5910427],"study_design_scores_gemma":[0.00003239528,0.0001336053,0.0001926287,0.00005412369,0.00006438495,0.000003432812,0.0001608436,0.8962643,0.08044985,0.02228273,0.0001845672,0.0001771468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05631294,0.00002489777,0.937591,0.003779148,0.0008374447,0.0005640918,0.00001821292,0.0004495494,0.000422745],"genre_scores_gemma":[0.9923576,0.00007683429,0.007084885,0.0001199446,0.00009729825,0.00006063432,0.000006033784,0.00001592146,0.0001808927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9360446,"threshold_uncertainty_score":0.8589011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2120581995870117,"score_gpt":0.3760106845677527,"score_spread":0.1639524849807409,"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."}}