{"id":"W4417117542","doi":"10.21203/rs.3.rs-8194963/v1","title":"Accelerating Machine Learning in Healthcare: Addressing the Labelling Bottleneck","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Bottleneck; Scalability; Annotation; Transfer of learning; Modalities; Deep learning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01768154,0.0008011321,0.001638626,0.002064164,0.002820518,0.0009049933,0.001340796,0.0009788305,0.0002455152],"category_scores_gemma":[0.007229287,0.0006324366,0.000599764,0.004379531,0.0004339568,0.0001562468,0.002761309,0.02098893,0.0001096095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001682569,"about_ca_system_score_gemma":0.003055597,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02668763,"about_ca_topic_score_gemma":0.00153536,"domain_scores_codex":[0.9838349,0.006385507,0.001817645,0.001954339,0.003303435,0.002704205],"domain_scores_gemma":[0.9904518,0.00493334,0.0004576051,0.001856884,0.001729948,0.0005704938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003866884,0.000535099,0.669984,0.01648029,0.0006379262,0.0005034703,0.006086456,0.0336077,0.0009963388,0.0004406011,0.0002725094,0.2700689],"study_design_scores_gemma":[0.003333974,0.0009006445,0.0280604,0.1136112,0.0004402235,0.00002327457,0.01401015,0.8190586,0.002815282,0.001113348,0.01522513,0.001407817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5221325,0.2998187,0.001480002,0.1476531,0.003684711,0.008017275,0.0002561836,0.0007005542,0.01625699],"genre_scores_gemma":[0.9529325,0.02794219,0.0009409096,0.0001720776,0.002550481,0.000338677,0.0002224939,0.0001042626,0.01479637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7854509,"threshold_uncertainty_score":0.9996127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2645008355560837,"score_gpt":0.4908586045679754,"score_spread":0.2263577690118918,"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."}}