{"id":"W4416904921","doi":"10.3390/make7040157","title":"SkinVisualNet: A Hybrid Deep Learning Approach Leveraging Explainable Models for Identifying Lyme Disease from Skin Rash Images","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Deep learning; Lyme disease; Preprocessor; Generalizability theory; Borrelia burgdorferi; Disease; Robustness (evolution)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004486962,0.0003391093,0.0003144921,0.0003950303,0.0009168137,0.001346617,0.0003886679,0.00005088839,0.000006301058],"category_scores_gemma":[0.0003845799,0.0003655218,0.0001734184,0.0003718765,0.00006321147,0.002335946,0.0003818801,0.0004617323,0.00001588756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009846116,"about_ca_system_score_gemma":0.00009439348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002299025,"about_ca_topic_score_gemma":0.000007336536,"domain_scores_codex":[0.9977907,0.0002218236,0.0003461684,0.0009337893,0.0002133023,0.0004942117],"domain_scores_gemma":[0.9987202,0.0004343958,0.0001818988,0.0003007822,0.0001403767,0.0002223631],"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":[0.0002076573,0.001320498,0.02590722,0.001003182,0.0003106593,0.00005623259,0.002946183,0.08266588,0.001441187,0.009491558,0.001138191,0.8735116],"study_design_scores_gemma":[0.0009528561,0.00003143415,0.004382727,0.0001665985,0.0000987895,0.000008832854,0.0002210411,0.9722605,0.0007662628,0.0130456,0.007673228,0.0003921828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03607897,0.01141568,0.9417024,0.0001452666,0.000390475,0.0003272734,0.000009390969,0.0006689652,0.009261574],"genre_scores_gemma":[0.976019,0.0001144853,0.01496217,0.00005247256,0.0001451484,0.0001294909,0.0001580771,0.00004241721,0.00837678],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.93994,"threshold_uncertainty_score":0.9998797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01908224841181635,"score_gpt":0.2965188878889322,"score_spread":0.2774366394771158,"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."}}