{"id":"W7164923981","doi":"10.2196/86145","title":"Large Language Models for Endodontic Symptom Assessment and Treatment Planning Using Image-Free Clinical Records: A Comparative Evaluation Study (Preprint)","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Radiation treatment planning; MEDLINE; Health care; Medical treatment; Clinical trial","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01341984,0.0008491716,0.0007915255,0.001546094,0.0006053163,0.002383649,0.001776753,0.001096259,0.00542735],"category_scores_gemma":[0.08408973,0.0006514883,0.001568279,0.001230225,0.0006738437,0.004257355,0.001828518,0.001182692,0.001493348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002122916,"about_ca_system_score_gemma":0.002161412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01373599,"about_ca_topic_score_gemma":0.008383584,"domain_scores_codex":[0.9915195,0.006480645,0.0005929388,0.0005807399,0.00068675,0.0001395031],"domain_scores_gemma":[0.8038487,0.1823967,0.003335085,0.004741237,0.00474346,0.0009348526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.05738749,0.02275923,0.1675167,0.003065402,0.002027445,0.001106221,0.01514399,0.05694955,0.007357631,0.003521902,0.009367959,0.6537966],"study_design_scores_gemma":[0.006178908,0.02527588,0.1762937,0.001172031,0.005110089,0.001681775,0.0150383,0.7357526,0.01407696,0.00642373,0.01226631,0.000729764],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770462,0.0005295084,0.0157473,0.0004015412,0.00005705182,0.0009843,0.002630583,0.001143153,0.001460363],"genre_scores_gemma":[0.9712956,0.0004759579,0.02143799,0.0001094323,0.00003416885,0.0008945318,0.004411463,0.000208622,0.001132302],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01373599,"threshold_uncertainty_score":0.07097173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08892127194876016,"score_gpt":0.4811391227386216,"score_spread":0.3922178507898615,"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."}}