{"id":"W2989324284","doi":"10.2196/15510","title":"Longitudinal Risk Prediction of Chronic Kidney Disease in Diabetic Patients using Temporal-Enhanced Gradient Boosting Machine: Retrospective Cohort Study","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of General Medical Sciences; Major Research Plan; National Natural Science Foundation of China","keywords":"Medicine; Gradient boosting; Boosting (machine learning); Kidney disease; Retrospective cohort study; Receiver operating characteristic; Timeline; Diabetes mellitus; Artificial intelligence; Cohort; Machine learning; Computer science; Internal medicine; Random forest; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.001242293,0.0002271383,0.0004574985,0.0002607978,0.0001130126,0.00004937841,0.000680651,0.0001109433,0.00005983858],"category_scores_gemma":[0.001222034,0.0002002746,0.00007158324,0.0007071571,0.00007488632,0.0006344636,0.0004598675,0.0008766427,0.00002052106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006848183,"about_ca_system_score_gemma":0.0005198563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005187902,"about_ca_topic_score_gemma":0.00003310433,"domain_scores_codex":[0.9960419,0.0002502186,0.001237859,0.0003050982,0.001720902,0.0004440458],"domain_scores_gemma":[0.9976479,0.0001308752,0.0007575175,0.0006983064,0.000212618,0.0005527167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001471987,0.0004024454,0.9927742,0.000387463,0.00002272452,0.000003868965,0.003129729,0.0008453108,7.433832e-7,0.00007990094,0.00002603989,0.002312796],"study_design_scores_gemma":[0.0008193278,0.000378464,0.5432491,0.0002706478,0.000009679086,5.982246e-7,0.00005259952,0.4550868,0.000002528164,0.00003319559,0.000008661345,0.00008838456],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819034,0.0000241825,0.01508124,0.00004683203,0.000636252,0.00194797,0.00004004439,0.0001065818,0.0002135097],"genre_scores_gemma":[0.9982359,0.00001009844,0.00148321,0.00007737066,0.00005554963,0.00006760527,0.00004828313,0.00001223637,0.000009685125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4542415,"threshold_uncertainty_score":0.8166963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01022035174913181,"score_gpt":0.2832313009389772,"score_spread":0.2730109491898454,"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."}}