{"id":"W7162014667","doi":"10.82308/34697","title":"Detecting venous thromboembolism using radiologic examination text data from electronic health records: comparing the predictive accuracy of random forest and logistic regression modeling","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bigram; Random forest; Logistic regression; Deep vein; Health care; Health records; Regression; Deep learning; Clinical decision support system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02911194,0.001424372,0.00105434,0.005323871,0.0003806338,0.001389425,0.001157617,0.001100808,0.0007674437],"category_scores_gemma":[0.08772738,0.0004129746,0.002088311,0.001968518,0.0004817429,0.002130436,0.0008658788,0.001524541,0.0006645458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000777323,"about_ca_system_score_gemma":0.00103738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00733823,"about_ca_topic_score_gemma":0.004744826,"domain_scores_codex":[0.9903261,0.007014367,0.0005797097,0.0009941611,0.0007718321,0.0003138632],"domain_scores_gemma":[0.8116964,0.1742482,0.006663066,0.002248765,0.004447584,0.0006960984],"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":[0.006136721,0.0009350982,0.7197747,0.0007996121,0.001647848,0.0002754696,0.0007588347,0.08590016,0.001155694,0.0006407659,0.002171947,0.1798032],"study_design_scores_gemma":[0.0001972667,0.001889607,0.08913132,0.000385388,0.0006976,0.0004434697,0.0005470598,0.9018138,0.001844059,0.002247624,0.0007024903,0.0001002917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388092,0.002234918,0.05328728,0.001017435,0.0001404189,0.0003341521,0.001972856,0.0007839185,0.001419883],"genre_scores_gemma":[0.9730029,0.0006487913,0.02376389,0.0001260351,0.0001139076,0.0001432795,0.001950594,0.00004658867,0.0002040175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02911194,"threshold_uncertainty_score":0.1539605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.103993520611854,"score_gpt":0.3615935353786245,"score_spread":0.2576000147667705,"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."}}