{"id":"W4365516058","doi":"10.1007/s10489-023-04577-6","title":"Reverse survival model (RSM): a pipeline for explaining predictions of deep survival models","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Ranking (information retrieval); Similarity (geometry); Survival analysis; Pipeline (software); Machine learning; Artificial neural network; Black box; Process (computing); Rank (graph theory); Event (particle physics); Data mining; Statistics; Mathematics","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":[0.001820697,0.001597581,0.0008164077,0.001493708,0.0004178874,0.001226416,0.002430252,0.00155858,0.01710621],"category_scores_gemma":[0.00774069,0.000859156,0.002032091,0.0009232004,0.0002626462,0.00143816,0.001347408,0.002826486,0.00828479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006953001,"about_ca_system_score_gemma":0.001699348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007787305,"about_ca_topic_score_gemma":0.01400544,"domain_scores_codex":[0.9997646,0.00007589641,0.00001730976,0.00006342223,0.00005364035,0.00002514562],"domain_scores_gemma":[0.9985006,0.0009771698,0.00008583462,0.0002024816,0.0001779273,0.00005599643],"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":[0.0004448866,0.0002331377,0.007873671,0.0005227756,0.0005109643,0.0004841381,0.0002103174,0.3625104,0.005594973,0.03693046,0.08942247,0.4952618],"study_design_scores_gemma":[0.00001653022,0.0000215965,0.0002528748,0.00002065833,0.00002279522,0.0000373039,0.000007962642,0.9769036,0.0009652897,0.01851858,0.00321962,0.00001306343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007777507,0.0004239022,0.9461057,0.0004440405,0.0001040989,0.0001016933,0.004072493,0.0395941,0.001376428],"genre_scores_gemma":[0.2178343,0.0009052894,0.7518987,0.0004857945,0.0001888194,0.0006247048,0.0151965,0.005103196,0.007762752],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01710621,"threshold_uncertainty_score":0.05722594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08343278273136005,"score_gpt":0.3304444716492289,"score_spread":0.2470116889178688,"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."}}