{"id":"W3098301945","doi":"10.1101/396663","title":"Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Spinal Cord Injury BC","funders":"Chiba University; Weill Cornell Medical College; National Cancer Institute; National Institutes of Health; Pfizer; Amgen","keywords":"Social media; Classifier (UML); Artificial intelligence; Disease; Deep learning; Computer science; Machine learning; Digital pathology; Medicine; Pathology; World Wide Web","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":[0.0008933805,0.001200661,0.0006001705,0.001743025,0.0004129075,0.0007559342,0.001140925,0.001616489,0.006858491],"category_scores_gemma":[0.003385948,0.0003327378,0.0006266515,0.0007257364,0.0003182598,0.001196048,0.001465783,0.0008243918,0.002568872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008692663,"about_ca_system_score_gemma":0.0005231525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007872817,"about_ca_topic_score_gemma":0.01409698,"domain_scores_codex":[0.999526,0.0001043997,0.00002292615,0.0001378061,0.0001092838,0.00009964792],"domain_scores_gemma":[0.9990945,0.0004731941,0.00009218512,0.0001104309,0.0001637422,0.00006599039],"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":[0.001977398,0.00111616,0.02251009,0.0007257498,0.0003331882,0.001367931,0.0003608211,0.1311185,0.03232211,0.002333082,0.09401475,0.7118203],"study_design_scores_gemma":[0.00003695711,0.0001095436,0.002542075,0.00002755859,0.00002254162,0.0001158672,0.00008838568,0.9834968,0.007541155,0.002700372,0.003300702,0.00001806726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5617307,0.003613252,0.3086825,0.003569697,0.0006299929,0.000700716,0.02084305,0.08669056,0.01353943],"genre_scores_gemma":[0.8736705,0.0003045018,0.1072517,0.0009695998,0.0001266,0.0002473701,0.0103571,0.0005742615,0.006498383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007872817,"threshold_uncertainty_score":0.02294397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01953008543341095,"score_gpt":0.2628129422653458,"score_spread":0.2432828568319348,"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."}}