{"id":"W4213422477","doi":"10.1038/s41598-022-07034-5","title":"Cross-institutional outcome prediction for head and neck cancer patients using self-attention neural networks","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Outcome (game theory); Head and neck cancer; Head and neck; Head (geology); Computer science; Cancer; Artificial neural network; Medicine; Artificial intelligence; Internal medicine; Surgery; Biology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001287883,0.0008116168,0.0004759121,0.000781382,0.0001918823,0.0004315714,0.0006872379,0.0004683988,0.0007364625],"category_scores_gemma":[0.002106968,0.0001860533,0.0005560388,0.0003740601,0.0002221813,0.0004399513,0.0006510464,0.0005863221,0.0001961929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008582356,"about_ca_system_score_gemma":0.0005643398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01598183,"about_ca_topic_score_gemma":0.01672058,"domain_scores_codex":[0.9997169,0.00007595021,0.00001889656,0.0001001042,0.00003457216,0.0000535219],"domain_scores_gemma":[0.9993048,0.0003461703,0.0001025184,0.00005744218,0.0001283223,0.00006079579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008512088,0.0005607214,0.1493622,0.00007958308,0.0003484686,0.0003166745,0.00007157598,0.7063755,0.001639256,0.0002782452,0.002346459,0.1377701],"study_design_scores_gemma":[0.000006953594,0.00007791812,0.007498746,0.0000042745,0.00001968589,0.00002307718,0.00001418303,0.9913679,0.0006339225,0.0002626533,0.00008464314,0.000006147947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9593747,0.0006085621,0.0373276,0.0003412347,0.00006683629,0.00007364034,0.0006862316,0.0005461164,0.0009751722],"genre_scores_gemma":[0.9954627,0.00008327448,0.003046893,0.00003384275,0.00001707912,0.00002018045,0.000971328,0.000008219538,0.0003564392],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01598183,"threshold_uncertainty_score":0.03177762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05028375798059879,"score_gpt":0.3170297970918369,"score_spread":0.2667460391112381,"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."}}