{"id":"W3027335960","doi":"10.1101/2020.05.15.20103044","title":"Trialstreamer: a living, automatically updated database of clinical trial reports","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; Medical Research Council; National Institutes of Health; McMaster University","keywords":"Computer science; Randomized controlled trial; Information retrieval; Sample size determination; Categorization; Clinical trial; Database; Artificial intelligence; Data mining; Medicine; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008816058,0.0004663374,0.001902352,0.0002009205,0.00007591602,0.0001623122,0.002654003,0.0006006038,0.0002481949],"category_scores_gemma":[0.02982036,0.0004251136,0.0006294546,0.0004747101,0.0001511266,0.0001535204,0.005534148,0.002467662,0.00005851611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003901618,"about_ca_system_score_gemma":0.001944179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000361358,"about_ca_topic_score_gemma":0.00001988711,"domain_scores_codex":[0.9889726,0.003101502,0.004384759,0.001897062,0.001175279,0.0004688073],"domain_scores_gemma":[0.9892903,0.002286363,0.003364982,0.004176412,0.0003315124,0.0005504498],"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":[0.01535632,0.006271557,0.6085905,0.01197493,0.002458386,0.01210763,0.006915717,0.001383732,0.0005186027,0.02986314,0.06932202,0.2352374],"study_design_scores_gemma":[0.0273339,0.004098239,0.1114024,0.004622741,0.0005180181,0.000245449,0.00003187052,0.8052793,0.0003094673,0.01606572,0.02725741,0.002835543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8292966,0.0002640806,0.1334626,0.01257114,0.01694533,0.003416716,0.00008485511,0.001873265,0.002085439],"genre_scores_gemma":[0.8580634,0.00008593806,0.139082,0.0005721223,0.001715351,0.000119048,0.0001516466,0.00006375542,0.0001467376],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8038955,"threshold_uncertainty_score":0.9998337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1267574432258337,"score_gpt":0.4269701377054367,"score_spread":0.3002126944796031,"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."}}