{"id":"W4237111741","doi":"10.2196/preprints.10281","title":"A Deep Learning Method to Automatically Identify Reports of Scientifically Rigorous Clinical Research from the Biomedical Literature: Comparative Analytic Study (Preprint)","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Deep learning; Artificial intelligence; Filter (signal processing); Computer science; Convolutional neural network; Clinical Practice; Information retrieval; Recall; Machine learning; Medicine; Psychology; Family 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.06297765,0.0006457207,0.001886454,0.0009072352,0.0008460226,0.002170786,0.007042441,0.0007890041,0.0002979152],"category_scores_gemma":[0.01753805,0.0004398385,0.0005541765,0.003787489,0.001078704,0.0002238637,0.01787434,0.008378355,0.0002943763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002610386,"about_ca_system_score_gemma":0.001274768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002706265,"about_ca_topic_score_gemma":0.0005086911,"domain_scores_codex":[0.9621313,0.02263078,0.004356811,0.004506513,0.005178653,0.001195943],"domain_scores_gemma":[0.9735134,0.01356398,0.001432253,0.006559343,0.003969247,0.0009617317],"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":[0.0004916947,0.00938129,0.4617077,0.001280204,0.003517319,0.003740363,0.2915632,0.02298043,0.0002927562,0.010148,0.02865694,0.1662401],"study_design_scores_gemma":[0.0003530864,0.001431649,0.3434811,0.0009193614,0.00007915199,0.00006199474,0.001231924,0.6352707,0.00003318444,0.01492457,0.001684464,0.0005288473],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2441474,0.0001709967,0.7448469,0.003784276,0.002279943,0.00347965,0.00001038525,0.0004728486,0.0008075933],"genre_scores_gemma":[0.6338043,0.000004008628,0.3649134,0.0002114758,0.0004620558,0.0001734652,0.00006030261,0.0000311948,0.0003398336],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6122903,"threshold_uncertainty_score":0.9998053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1746760251906887,"score_gpt":0.5416441971488496,"score_spread":0.3669681719581609,"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."}}