{"id":"W4410074846","doi":"10.1101/2025.05.02.25326887","title":"Evaluating the Potential of AI-Generated Synthetic Diaries in Parkinson’s Disease Research","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Parkinson's disease; Disease; Psychology; Data science; Medicine; Computer science; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01849574,0.0005756525,0.0003636031,0.001236805,0.0004746932,0.002779816,0.001488108,0.001079975,0.002718117],"category_scores_gemma":[0.105275,0.0002381595,0.0005958552,0.001045623,0.0009315858,0.001948525,0.002496393,0.0009709367,0.0008947414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001136509,"about_ca_system_score_gemma":0.001208193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001942355,"about_ca_topic_score_gemma":0.002398967,"domain_scores_codex":[0.9882983,0.009438607,0.0005759826,0.0007023104,0.0008491191,0.0001357095],"domain_scores_gemma":[0.8917788,0.09290657,0.002705995,0.007931395,0.003655033,0.001022295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005037981,0.002786748,0.1220773,0.005690845,0.0006665075,0.001796501,0.02412699,0.1918713,0.01367302,0.04381024,0.02424106,0.5642216],"study_design_scores_gemma":[0.001179776,0.003894564,0.03806834,0.001808549,0.0003568492,0.001325612,0.008845939,0.7737573,0.01744497,0.06507511,0.08783606,0.0004068546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7547957,0.00108029,0.2011605,0.004412178,0.0004979886,0.003456523,0.01117434,0.003758563,0.01966382],"genre_scores_gemma":[0.8389282,0.0003287058,0.1513135,0.0005174865,0.00005969703,0.001537758,0.006067906,0.0001415957,0.001105062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01849574,"threshold_uncertainty_score":0.09781599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0853112994754933,"score_gpt":0.4109059820351313,"score_spread":0.325594682559638,"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."}}