{"id":"W6977553122","doi":"10.6084/m9.figshare.c.7248780","title":"Testing the generalizability and effectiveness of deep learning models among clinics: sperm detection as a pilot study","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"CReATe Fertility Centre; University of Toronto","funders":"","keywords":"Deep learning; Generalizability theory; Preprocessor; Sample (material); Intraclass correlation; Object detection; Pattern recognition (psychology)","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":[0.01370742,0.001156692,0.0009113338,0.0006292402,0.0005104457,0.0009781949,0.001386853,0.001629662,0.001205162],"category_scores_gemma":[0.05191294,0.0005352459,0.001591731,0.000390395,0.001415284,0.001030464,0.001729161,0.001990773,0.0006569327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006825748,"about_ca_system_score_gemma":0.0008598886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003740824,"about_ca_topic_score_gemma":0.002125503,"domain_scores_codex":[0.9939122,0.002443942,0.0004810952,0.002200944,0.0006975677,0.000264383],"domain_scores_gemma":[0.9560764,0.02847077,0.00216505,0.008577375,0.003931186,0.0007792123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01513923,0.006054565,0.3234458,0.001413201,0.003776105,0.0008568509,0.002604259,0.2414215,0.1129415,0.001806756,0.006838227,0.283702],"study_design_scores_gemma":[0.001113766,0.02198103,0.1836759,0.0001685662,0.001956827,0.001132273,0.0009015375,0.6745033,0.1049617,0.004877949,0.004427551,0.0002997047],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9568208,0.0003149318,0.04043806,0.0002253811,0.000101588,0.0004522857,0.0004721995,0.0005228242,0.0006518277],"genre_scores_gemma":[0.9778832,0.0000790628,0.01998554,0.0002024573,0.00004272225,0.0004393611,0.0008221689,0.0000851829,0.0004603167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01370742,"threshold_uncertainty_score":0.0724926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06236278408729332,"score_gpt":0.2965040417806014,"score_spread":0.2341412576933081,"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."}}