{"id":"W4295430429","doi":"10.11817/j.issn.1672-7347.2022.220353","title":"Construction of a predictive model for radiation proctitis after radiotherapy for female pelvic tumors based on machine learning.","year":2022,"lang":"en","type":"article","venue":"PubMed","topic":"Effects of Radiation Exposure","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Proctitis; Radiation therapy; Medicine; Logistic regression; Radiation proctitis; Random forest; Machine learning; Gradient boosting; Support vector machine; Pelvis; Artificial intelligence; Radiology; Computer science; Internal medicine; Disease","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":[0.0004486431,0.0001234942,0.0002563102,0.0002337179,0.0001142237,0.000007537326,0.00005122842,0.00004837557,0.00003754565],"category_scores_gemma":[0.0003644197,0.0001258128,0.0001396189,0.000157951,0.00004098087,0.00007173503,0.000007308694,0.000157537,2.103811e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003095964,"about_ca_system_score_gemma":0.0001103353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006621238,"about_ca_topic_score_gemma":0.000002072228,"domain_scores_codex":[0.9989339,0.00007347587,0.0002334438,0.0002558198,0.0002814718,0.0002218619],"domain_scores_gemma":[0.9992095,0.0002379116,0.000210421,0.0001496264,0.0001092572,0.00008328073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02552662,0.0007893234,0.1883365,0.0008638579,0.0003366849,0.000005669572,0.002016045,0.4712105,0.0003716534,0.0003654379,0.001401808,0.3087759],"study_design_scores_gemma":[0.006284948,0.001450012,0.1049565,0.00001115651,0.00008694898,0.000009341083,0.00004602161,0.8841286,0.0008023477,0.00006896528,0.002047839,0.0001072666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8155176,0.0009950569,0.1603879,0.003174246,0.0005246343,0.01773418,0.00108802,0.0002410294,0.0003373769],"genre_scores_gemma":[0.9679343,0.000008435374,0.004695296,0.0004497133,0.0001321787,0.02590334,0.0002453657,0.00004336448,0.0005880463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4129181,"threshold_uncertainty_score":0.5130495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00977585154907207,"score_gpt":0.2293305646585903,"score_spread":0.2195547131095182,"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."}}