{"id":"W4410216476","doi":"10.1007/978-3-031-88220-3_16","title":"UlcerGPT: A Multimodal Approach Leveraging Large Language and Vision Models for Diabetic Foot Ulcer Image Transcription","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Diabetic Foot Ulcer Assessment and Management","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Computer science; Transcription (linguistics); Computer vision; Diabetic foot; Image (mathematics); Artificial intelligence; Diabetic foot ulcer; Foot (prosody); Natural language processing; Diabetes mellitus; Medicine; Linguistics","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":[0.001053098,0.002326847,0.001547618,0.002164918,0.0007305983,0.001778286,0.001968656,0.00220839,0.01937108],"category_scores_gemma":[0.002116141,0.0007026038,0.002224732,0.001938265,0.0003619282,0.00209766,0.002594275,0.001995084,0.01526883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006793501,"about_ca_system_score_gemma":0.0009899084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01187149,"about_ca_topic_score_gemma":0.01683524,"domain_scores_codex":[0.9992193,0.000144544,0.00004267936,0.0002876068,0.0001958316,0.0001100493],"domain_scores_gemma":[0.9993331,0.0002616531,0.00003135677,0.0001262921,0.000187467,0.00006009046],"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":[0.000707066,0.0003499156,0.0008809251,0.0002534639,0.0002452711,0.0004148882,0.00009078219,0.01526065,0.0459929,0.001122428,0.04682478,0.8878569],"study_design_scores_gemma":[0.0001203078,0.0003478536,0.002519456,0.00006080521,0.000227801,0.000569481,0.0002120433,0.9313322,0.03525332,0.005943164,0.02330795,0.0001056495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0230536,0.001701688,0.9020271,0.0005170883,0.0007629289,0.0006986952,0.008947163,0.05595781,0.006333984],"genre_scores_gemma":[0.1377648,0.001345525,0.8012185,0.0008833974,0.0005318597,0.0009537483,0.03144199,0.00363088,0.02222927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01937108,"threshold_uncertainty_score":0.06480277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01394616248159471,"score_gpt":0.2825586649222945,"score_spread":0.2686125024406998,"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."}}