{"id":"W4387185802","doi":"10.24846/v32i3y202309","title":"Deep Learning Model for Early Subsequent COPD Exacerbation Prediction","year":2023,"lang":"en","type":"article","venue":"Studies in Informatics and Control","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Development Research Centre; University of Twente; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Exacerbation; Copd exacerbation; COPD; Artificial intelligence; Deep learning; Machine learning; Medicine; Internal medicine; Acute exacerbation of chronic obstructive pulmonary disease","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.00039379,0.0001122129,0.0002616111,0.0001735968,0.0001623807,0.0000208779,0.00003997499,0.00005143971,0.000004089848],"category_scores_gemma":[0.0002594396,0.00009781376,0.00005153292,0.0001726557,0.0001192069,0.0001765069,0.00005648594,0.0001643168,0.000009987724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002099906,"about_ca_system_score_gemma":0.00005678042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000667817,"about_ca_topic_score_gemma":0.000008721057,"domain_scores_codex":[0.9989663,0.00001884148,0.0003688873,0.0001018703,0.0002539564,0.0002900796],"domain_scores_gemma":[0.9993792,0.0001603516,0.00007996062,0.0001082584,0.0001974517,0.00007478981],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003362565,0.0002667569,0.373553,0.01157765,0.00193732,0.00005076548,0.08890987,0.2187307,0.0002978891,0.007476529,0.003073872,0.2907631],"study_design_scores_gemma":[0.003938296,0.0001418289,0.05626896,0.00009967703,0.00006324285,0.000003272518,0.007117268,0.9310466,0.000003863224,0.0008521765,0.000388608,0.00007621489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9516277,0.002695899,0.04072512,0.0005678159,0.0002369948,0.002336788,0.00006307498,0.0001562793,0.001590275],"genre_scores_gemma":[0.9971052,0.001263098,0.0004177516,0.00008425122,0.00007383135,0.0004061502,0.00004714926,0.00001282021,0.000589747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7123159,"threshold_uncertainty_score":0.3988729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03649568052189048,"score_gpt":0.3210129474417679,"score_spread":0.2845172669198774,"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."}}