{"id":"W4224057374","doi":"10.1080/08839514.2022.2055393","title":"Explainable Analytics to Predict the Quality of Life in Patients with Prostate Cancer from Longitudinal Data","year":2022,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thompson Rivers University; University of Calgary","funders":"","keywords":"Interpretability; Computer science; Machine learning; Baseline (sea); Artificial intelligence; Prostate cancer; Bayesian network; Quality of life (healthcare); Set (abstract data type); Analytics; Data mining; Medicine; Cancer; Internal 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":[0.0003861354,0.0001427277,0.0003329872,0.00006441014,0.0001329556,0.00001852515,0.000332839,0.00001955056,0.0002966478],"category_scores_gemma":[0.00006034527,0.00009768188,0.00002543367,0.0005306316,0.00009198346,0.00005301337,0.0003592792,0.0001862642,0.000008819314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002005227,"about_ca_system_score_gemma":0.0002466298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004795069,"about_ca_topic_score_gemma":0.001624498,"domain_scores_codex":[0.9981799,0.00004420352,0.0005234772,0.0004656777,0.0005323206,0.0002543979],"domain_scores_gemma":[0.9987062,0.0001453948,0.00017484,0.0007713598,0.00009021688,0.000112002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004736324,0.001265117,0.9473166,0.00003935684,0.0001700702,0.000007215598,0.001706376,0.0127751,0.00007921347,0.001891374,0.0005603785,0.02945283],"study_design_scores_gemma":[0.0007785409,0.001084626,0.9803799,0.00009747044,0.0001996013,2.307758e-7,0.00430773,0.001701643,0.007424195,0.002149787,0.00156179,0.0003145184],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953463,0.0002101103,0.0005169226,0.001139765,0.00009187763,0.001424527,0.00109685,0.00001562176,0.0001580462],"genre_scores_gemma":[0.9982646,0.00005097675,0.0002360753,0.0004328287,0.00004869718,0.0006029709,0.0003302817,0.00001610352,0.00001753468],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03306322,"threshold_uncertainty_score":0.7248742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1098564976490424,"score_gpt":0.3437958969716771,"score_spread":0.2339393993226347,"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."}}