{"id":"W3160522549","doi":"10.2196/29433","title":"Foodborne Disease Risk Prediction Using Multigraph Structural Long Short-term Memory Networks: Algorithm Design and Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Food Safety and Hygiene","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China","keywords":"Computer science; Similarity (geometry); Multigraph; Data mining; Margin (machine learning); Beijing; Term (time); Disease; Artificial neural network; Artificial intelligence; Machine learning; Geography; Medicine; China; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005231455,0.0001641582,0.000195803,0.00001719786,0.0003646815,0.0001130728,0.0001444658,0.0001201691,0.0001508098],"category_scores_gemma":[0.00009376201,0.00007315134,0.00006439278,0.0003191613,0.00009918062,0.0004213543,0.0001284654,0.0002736615,0.000002097942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000232513,"about_ca_system_score_gemma":0.00003308713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002055943,"about_ca_topic_score_gemma":0.00004165429,"domain_scores_codex":[0.9982588,0.0002156457,0.0005183787,0.0001677363,0.0005755882,0.0002638696],"domain_scores_gemma":[0.9991205,0.0001762113,0.0001256963,0.00008647447,0.00009640116,0.0003947438],"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":[0.00009591803,0.0002916931,0.06277713,0.00004700993,0.0001010313,0.00007764031,0.001881568,0.002840666,0.0001334094,0.00000686285,0.000102396,0.9316447],"study_design_scores_gemma":[0.0003853597,0.0002923245,0.450558,0.00005563292,0.00007145948,0.00002437334,0.00228144,0.5460046,0.00009594537,0.00003968387,0.00002879315,0.0001623863],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9850934,0.0001772189,0.0137668,0.00008134856,0.0002157933,0.0005294117,0.00004444001,0.0000794552,0.00001209285],"genre_scores_gemma":[0.9963464,0.0001552531,0.00285273,0.0001043953,0.0003024093,0.00002524338,0.0002045109,0.000001447633,0.000007582636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9314823,"threshold_uncertainty_score":0.2983025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02821971403158088,"score_gpt":0.2683872972837118,"score_spread":0.2401675832521309,"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."}}