{"id":"W4403365555","doi":"10.1007/978-3-031-72083-3_54","title":"Can Crowdsourced Annotations Improve AI-Based Congestion Scoring for Bedside Lung Ultrasound?","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Ultrasound in Clinical Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Lung ultrasound; Artificial intelligence; Machine learning; Data science; Ultrasound; Radiology; Medicine","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":[0.002776731,0.001756693,0.001232076,0.002024028,0.0008570489,0.00252563,0.002216686,0.002503145,0.009390119],"category_scores_gemma":[0.02006012,0.0005704573,0.0007311347,0.001516728,0.0005143929,0.003044978,0.002529153,0.00184474,0.008969371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005678794,"about_ca_system_score_gemma":0.000953573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008840621,"about_ca_topic_score_gemma":0.01766667,"domain_scores_codex":[0.9978901,0.0007016471,0.000090287,0.0005424888,0.0005935904,0.0001819006],"domain_scores_gemma":[0.9933168,0.003784295,0.0002679513,0.0007348259,0.001612401,0.000283651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002087812,0.0005825146,0.01082654,0.001212988,0.0003199054,0.0003270087,0.0007439789,0.033687,0.0252201,0.002665066,0.09743511,0.824892],"study_design_scores_gemma":[0.0003342475,0.000593826,0.01526745,0.0005377584,0.0003409835,0.0004739404,0.001382404,0.8620654,0.0272274,0.03265804,0.058801,0.0003175274],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09728139,0.007609072,0.7962275,0.004067332,0.005152172,0.0008699616,0.009986276,0.03523881,0.04356751],"genre_scores_gemma":[0.6215416,0.002186874,0.3358877,0.001759521,0.0018103,0.0006334555,0.01153892,0.002925137,0.0217165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009390119,"threshold_uncertainty_score":0.03141308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02316816195192067,"score_gpt":0.3226865911463722,"score_spread":0.2995184291944515,"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."}}