{"id":"W4402406507","doi":"10.23889/ijpds.v9i5.2849","title":"Identifying patterns of co-occurring chronic conditions preceding dementia: An unsupervised machine learning approach using health administrative data ","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Health Services and Policy Research; Regional Municipality of Waterloo; Sunnybrook Health Science Centre; University of Manitoba; Trillium Health Centre","funders":"","keywords":"Dementia; Unsupervised learning; Computer science; Artificial intelligence; Psychology; Machine learning; Data science; Medicine; Disease","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00641337,0.0001646284,0.000238103,0.0005257967,0.003642363,0.0005447743,0.002737908,0.00007622412,0.0001885781],"category_scores_gemma":[0.001199005,0.000159201,0.00004494063,0.000415716,0.0001339214,0.005909426,0.0008082664,0.0008435356,0.000007439983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008955383,"about_ca_system_score_gemma":0.002262514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004745845,"about_ca_topic_score_gemma":0.002397341,"domain_scores_codex":[0.9958361,0.0004254355,0.001372143,0.0007466328,0.001098019,0.0005216072],"domain_scores_gemma":[0.9971359,0.000462636,0.0007798215,0.0006675675,0.0006929881,0.00026109],"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":[0.0001033024,0.0002114582,0.9133189,0.001459271,0.0003426359,0.0000171702,0.008244906,0.01760042,0.005977964,0.01800013,0.0005633875,0.03416043],"study_design_scores_gemma":[0.0001572051,0.00009303963,0.006613585,0.001263569,0.00003375087,0.00004504166,0.004107291,0.984998,0.0001079104,0.0007642901,0.001666553,0.0001497308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4568167,0.0008934272,0.5247043,0.0007160248,0.006863766,0.001206694,0.008584294,0.0001224783,0.00009226306],"genre_scores_gemma":[0.9788478,0.000138351,0.01226449,0.0001066829,0.00103059,0.00001686896,0.007543348,0.00002799584,0.00002388186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9673976,"threshold_uncertainty_score":0.9976547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6244747597443215,"score_gpt":0.6384524637883252,"score_spread":0.01397770404400367,"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."}}