{"id":"W4414561830","doi":"10.1093/dmfr/twaf069","title":"Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive learning and Bayesian auto-tuned deep learning model","year":2025,"lang":"en","type":"article","venue":"Dentomaxillofacial Radiology","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Deep learning; Bayesian probability; Focus (optics); Bayesian network; Chest radiograph; Convolutional neural network; Inferior alveolar nerve; Panoramic radiograph","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000764665,0.0008271249,0.0005227303,0.0009660135,0.0001561084,0.0005307098,0.0008085662,0.000722887,0.0009427651],"category_scores_gemma":[0.002197656,0.000312623,0.0007482094,0.0002823069,0.0002308274,0.000394262,0.0005291561,0.0007385802,0.000325627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008108462,"about_ca_system_score_gemma":0.001090536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01341355,"about_ca_topic_score_gemma":0.01850584,"domain_scores_codex":[0.9997743,0.00003116438,0.00001811948,0.00007562136,0.00006297672,0.00003791516],"domain_scores_gemma":[0.9995271,0.000204846,0.00007723406,0.00002338598,0.0001367004,0.00003084854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008800988,0.0005120633,0.1115967,0.0002230525,0.0002510342,0.0006395623,0.0000806934,0.5602405,0.0141945,0.0006743603,0.004584769,0.3061227],"study_design_scores_gemma":[0.000008848655,0.00006700296,0.005708979,0.0000193815,0.00002794202,0.00007831976,0.00001329088,0.991143,0.002359509,0.0003485371,0.0002157314,0.000009437292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8180764,0.002831243,0.1733973,0.0006475424,0.0001142205,0.0001442752,0.001461104,0.001246725,0.002081267],"genre_scores_gemma":[0.9781991,0.0003804677,0.01875425,0.0001130035,0.00003262425,0.00005482899,0.001143151,0.0000302082,0.00129236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01341355,"threshold_uncertainty_score":0.02667093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00883327976971053,"score_gpt":0.2716184993445473,"score_spread":0.2627852195748367,"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."}}