{"id":"W3002855918","doi":"10.1109/access.2020.2968608","title":"Handling Irregularly Sampled Longitudinal Data and Prognostic Modeling of Diabetes Using Machine Learning Technique","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto; Toronto Metropolitan University","funders":"Prince Sultan University","keywords":"Computer science; Hidden Markov model; Machine learning; Artificial intelligence; Interval (graph theory); Polynomial; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009369151,0.0001868744,0.0004204635,0.000102404,0.0007267715,0.00004418536,0.0007339526,0.000188729,0.00006072438],"category_scores_gemma":[0.001925333,0.0001782595,0.00002976912,0.0003731053,0.0000834495,0.0006861099,0.0007573167,0.000915468,0.000007954648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004617446,"about_ca_system_score_gemma":0.0002381049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002756763,"about_ca_topic_score_gemma":0.000658911,"domain_scores_codex":[0.9974609,0.0004152669,0.0008194773,0.0005389786,0.0002600775,0.0005053009],"domain_scores_gemma":[0.9979012,0.0008212108,0.0003513473,0.0004210462,0.0003077544,0.000197432],"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":[0.00003229674,0.0000151291,0.9787424,0.00111352,0.00002144604,0.000003635477,0.001346436,0.008871961,0.008814722,0.0000316695,0.00001212494,0.000994698],"study_design_scores_gemma":[0.0000981,0.00006245788,0.001039599,0.0007569335,0.00004977349,7.925512e-7,0.0004861516,0.9935364,0.003195264,0.0005530574,0.00004967691,0.0001718512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.825865,0.0006780369,0.1714989,0.000512089,0.0002035597,0.001029119,0.00006674381,0.0001215348,0.00002510538],"genre_scores_gemma":[0.9940556,0.00004644112,0.005164841,0.0002295127,0.0003413408,0.00006161082,0.0000499933,0.0000462354,0.000004445587],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9846644,"threshold_uncertainty_score":0.7269213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4917977887778538,"score_gpt":0.5114198097816329,"score_spread":0.01962202100377913,"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."}}