{"id":"W4392450861","doi":"10.21203/rs.3.rs-4008354/v1","title":"Testing the reproducibility and effectiveness of deep learning models among clinics: sperm detection as a pilot study","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"CReATe Fertility Centre; University of Toronto","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Chinese University of Hong Kong; National Natural Science Foundation of China","keywords":"Reproducibility; Sperm; Psychology; Artificial intelligence; Medical physics; Computer science; Medicine; Statistics; Mathematics; Andrology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01036433,0.0009720464,0.0008694072,0.0006064562,0.0004840934,0.0008800161,0.001308272,0.001562564,0.0008933069],"category_scores_gemma":[0.03443957,0.0004937704,0.001236973,0.0004226725,0.001129186,0.0007220715,0.001329273,0.001490292,0.0005997762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006176002,"about_ca_system_score_gemma":0.0007630025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002560359,"about_ca_topic_score_gemma":0.001861869,"domain_scores_codex":[0.9945039,0.001986174,0.0005089167,0.001944898,0.0008420349,0.0002140265],"domain_scores_gemma":[0.9684461,0.01777388,0.001880488,0.007330354,0.003909832,0.0006593727],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01192757,0.004551774,0.2553859,0.00143753,0.003564605,0.001055317,0.002149406,0.2001039,0.2253372,0.001605585,0.007258276,0.285623],"study_design_scores_gemma":[0.0006984822,0.01554903,0.1477879,0.0001489616,0.001406833,0.001516313,0.0006232448,0.6086751,0.2157579,0.002954756,0.004574662,0.0003069156],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9414827,0.0004376169,0.05545318,0.0002227818,0.0001364636,0.0003063859,0.000492809,0.0008274651,0.0006405537],"genre_scores_gemma":[0.9704627,0.00007902282,0.02747353,0.0001850371,0.00004137288,0.0003098688,0.0007990458,0.0001142629,0.0005350278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9896356,"threshold_uncertainty_score":0.05481243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4837401849432953,"score_gpt":0.5478760521794851,"score_spread":0.06413586723618975,"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."}}