{"id":"W4402764036","doi":"10.2196/preprints.57926","title":"Extracting Critical Information from Unstructured Clinicians’ Notes Data to Identify Dementia Severity Using a Rule-Based Approach: Feasibility Study (Preprint)","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Dementia; Data science; Computer science; Psychology; Medicine; Data mining; World Wide Web; Internal medicine; Disease","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004922902,0.0006359291,0.0007910081,0.0004038922,0.0003747036,0.00282057,0.005240013,0.000513734,0.0001230556],"category_scores_gemma":[0.006854442,0.0006390257,0.0001933409,0.0005913967,0.00007291036,0.001345607,0.02155156,0.003527549,0.0001363134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003988984,"about_ca_system_score_gemma":0.001138868,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01495447,"about_ca_topic_score_gemma":0.0005209694,"domain_scores_codex":[0.9919188,0.001391155,0.001933378,0.002763493,0.001337565,0.000655578],"domain_scores_gemma":[0.9903042,0.001633905,0.000501028,0.006688177,0.0004890708,0.0003835667],"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":[0.0002471188,0.001942045,0.6081382,0.006883228,0.0008966064,0.0001055301,0.0202997,0.1598054,0.0002223145,0.002218175,0.0003929978,0.1988487],"study_design_scores_gemma":[0.0002639351,0.00004615805,0.1561467,0.0002754036,0.0001520916,0.000005004521,0.0005140342,0.8338881,0.0000385169,0.008060362,0.00004998758,0.0005597722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3838109,0.00005399578,0.6093893,0.001351686,0.002257483,0.002063923,0.0002263798,0.0006822366,0.0001640622],"genre_scores_gemma":[0.5938335,4.200882e-7,0.4051493,0.0004668661,0.0001824288,0.00004277879,0.0003021422,0.00002150402,0.000001009171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6740827,"threshold_uncertainty_score":0.9996061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2281510146757457,"score_gpt":0.4661360618317131,"score_spread":0.2379850471559674,"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."}}