{"id":"W2992918713","doi":"10.1007/s10278-019-00290-4","title":"A Comparison of the Efficiency of Using a Deep CNN Approach with Other Common Regression Methods for the Prediction of EGFR Expression in Glioblastoma Patients","year":2019,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Winnipeg; University of Manitoba; CancerCare Manitoba","funders":"","keywords":"Elastic net regularization; Lasso (programming language); Convolutional neural network; Artificial intelligence; Overfitting; Regression; Feature selection; Linear regression; Deep learning; Regression analysis; Computer science; Regularization (linguistics); Pattern recognition (psychology); Artificial neural network; Machine learning; Statistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0006199211,0.0001056193,0.0004607697,0.0001579123,0.00003699862,0.00001714681,0.0001869611,0.00003141183,0.000002389524],"category_scores_gemma":[0.0003468153,0.00004853737,0.0001443491,0.0002464183,0.0001471185,0.0002205956,0.0000597603,0.0003294314,3.694239e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004789931,"about_ca_system_score_gemma":0.00005797896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008612393,"about_ca_topic_score_gemma":2.019506e-7,"domain_scores_codex":[0.9985851,0.00008849115,0.0006870801,0.0001006908,0.0004065003,0.0001321073],"domain_scores_gemma":[0.9980857,0.0003170908,0.001139045,0.000191961,0.0002241586,0.00004200031],"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":[0.0007183074,0.0005538032,0.9068664,0.0002470202,0.00003750611,4.204999e-7,0.001626611,0.004473525,0.05374386,0.000006152949,0.00001938797,0.03170698],"study_design_scores_gemma":[0.005500345,0.0008972611,0.06021914,0.004731042,0.0001968373,0.0000873895,0.00216832,0.8693168,0.05650612,0.00008761577,0.0001935548,0.00009561741],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8633046,0.0003522193,0.1355505,0.00009763232,0.0001296284,0.0003262307,0.00000306212,0.000002550451,0.0002336225],"genre_scores_gemma":[0.9802806,0.000002772978,0.01963363,0.00002322454,0.00003119159,0.000001322466,8.570494e-7,0.00001792099,0.000008455952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8648432,"threshold_uncertainty_score":0.1979297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02017689411226259,"score_gpt":0.3580639777643544,"score_spread":0.3378870836520919,"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."}}