{"id":"W4313318640","doi":"10.1371/journal.pone.0279739","title":"Raman microspectroscopy and machine learning for use in identifying radiation-induced lung toxicity","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Effects of Radiation Exposure","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Hypersensitivity pneumonitis; Artificial intelligence; Computer science; Test set; Pattern recognition (psychology); Raman spectroscopy; Metric (unit); Support vector machine; Fibrosis; Grading (engineering); Machine learning; Lung; Pathology; Medicine; Physics; Biology; Internal medicine; Optics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004115156,0.0001062973,0.0002673329,0.000197246,0.0002242404,0.00004511933,0.00005458567,0.00004207854,0.00008301037],"category_scores_gemma":[0.0005814833,0.0001235861,0.00003814244,0.0001998216,0.00001234192,0.00016202,0.0000546743,0.0003901905,0.000002271101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002294313,"about_ca_system_score_gemma":0.00003832984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001085251,"about_ca_topic_score_gemma":0.00006048691,"domain_scores_codex":[0.9989614,0.00009587919,0.0002088048,0.0002556298,0.0002666196,0.0002116953],"domain_scores_gemma":[0.9993604,0.0002790111,0.0001005111,0.0001457047,0.00003742875,0.00007692909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001467884,0.0003900749,0.4700375,0.0001816762,0.00008051579,0.000008811643,0.0004129481,0.00004863435,0.5283273,0.00004824478,0.00006767905,0.0002497755],"study_design_scores_gemma":[0.009318629,0.001518357,0.4680274,0.000199593,0.0003742735,0.00002268309,0.0001931737,0.1017836,0.4177927,0.0001190056,0.000255848,0.0003947915],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972228,0.000651993,0.0001973933,0.0007786231,0.00004472205,0.0009843882,0.00001546031,0.00007300332,0.00003157983],"genre_scores_gemma":[0.9951363,0.00004691353,0.00365563,0.0003569048,0.00008439501,0.0001679837,0.000112028,0.00003291395,0.0004069755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1105346,"threshold_uncertainty_score":0.5039696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04762571602462543,"score_gpt":0.2832258673362539,"score_spread":0.2356001513116285,"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."}}