{"id":"W4412932599","doi":"10.1371/journal.pntd.0012879","title":"Multi-contrast machine learning improves schistosomiasis diagnostic performance","year":2025,"lang":"en","type":"article","venue":"PLoS neglected tropical diseases","topic":"Parasites and Host Interactions","field":"Immunology and Microbiology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto General Hospital; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Bill and Melinda Gates Foundation","keywords":"Gold standard (test); Contrast (vision); Artificial intelligence; Schistosoma haematobium; Machine learning; Computer science; Medicine; Schistosomiasis; Pattern recognition (psychology); Medical physics; Radiology; Immunology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002794189,0.001265674,0.0008734202,0.001006968,0.0003420188,0.001083311,0.0008150284,0.00140319,0.001213743],"category_scores_gemma":[0.007126764,0.0003842397,0.001191024,0.0003235352,0.0003798811,0.001270617,0.001055878,0.00126343,0.0006991043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007913241,"about_ca_system_score_gemma":0.0007281008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005545534,"about_ca_topic_score_gemma":0.005216173,"domain_scores_codex":[0.9990145,0.0003977184,0.00007223311,0.0002868187,0.0001326271,0.00009596199],"domain_scores_gemma":[0.9970323,0.002004066,0.0001985939,0.0002432462,0.0003948228,0.0001269486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002194305,0.001011065,0.1314367,0.0002647559,0.0009783399,0.000403817,0.0002157593,0.4986903,0.02534742,0.0007240434,0.003846115,0.3348873],"study_design_scores_gemma":[0.00002580306,0.0002428048,0.007076874,0.00002040325,0.00007890096,0.00008901999,0.00002278463,0.9867807,0.004623445,0.0006315786,0.0003833832,0.00002425427],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8723255,0.002326963,0.1149848,0.00190792,0.0001736513,0.0001153965,0.0006468186,0.003382058,0.004136801],"genre_scores_gemma":[0.9736707,0.0001731931,0.02434738,0.0002925493,0.00004826099,0.00002037801,0.0005275853,0.00005027776,0.0008697614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005545534,"threshold_uncertainty_score":0.01477724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009098611289785934,"score_gpt":0.2447567380114211,"score_spread":0.2356581267216352,"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."}}