{"id":"W4401625984","doi":"10.20944/preprints202408.0966.v1","title":"Enhancing the Interpretability of Malaria and Typhoid Diagnosis with Explainable AI and Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Interpretability; Typhoid fever; Malaria; Computer science; Artificial intelligence; Plasmodium falciparum; Natural language processing; Medicine; Virology; Immunology","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":[],"consensus_categories":[],"category_scores_codex":[0.0007245057,0.0002224158,0.0002937132,0.00003581404,0.00005736335,0.0000220796,0.0002572243,0.0003317283,0.00004168695],"category_scores_gemma":[0.0002643437,0.0001471025,0.00006945762,0.00004925004,0.0003114962,0.000003072947,0.002887735,0.0005040148,0.000004796418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001285435,"about_ca_system_score_gemma":0.00009136445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002108554,"about_ca_topic_score_gemma":0.0001650333,"domain_scores_codex":[0.9985911,0.0001080347,0.0002598118,0.0006880389,0.0001259445,0.0002270655],"domain_scores_gemma":[0.9989959,0.00005879901,0.0001021204,0.0007134489,0.00006139607,0.00006834741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007585058,0.0004700089,0.6975063,0.005026709,0.001521614,0.00005982775,0.0189913,0.0001766588,0.2544822,0.001637846,0.0003759756,0.01899311],"study_design_scores_gemma":[0.0007620477,0.0002927909,0.05385076,0.001138479,0.0003569252,0.00005740701,0.003924374,0.001481338,0.9248722,0.007327084,0.005177542,0.0007590714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903206,0.00624924,0.001527533,0.0006861747,0.0001127098,0.0002877878,0.00006031995,0.00003132745,0.0007242979],"genre_scores_gemma":[0.9982557,0.0006900701,0.0003628685,0.0001325934,0.00006207661,0.0001599815,0.00002641242,0.00002222811,0.0002880761],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.67039,"threshold_uncertainty_score":0.5998667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03433271375113809,"score_gpt":0.3200210188595128,"score_spread":0.2856883051083747,"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."}}