{"id":"W2802494476","doi":"10.7717/peerj-cs.154","title":"Supervised deep learning embeddings for the prediction of cervical cancer diagnosis","year":2018,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"European Regional Development Fund","keywords":"Machine learning; Artificial intelligence; Computer science; Deep learning; Dimensionality reduction; Cervical cancer; Supervised learning; Embedding; Population; Cancer; Medicine; Artificial neural network","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":[0.0009734308,0.0001399278,0.000158841,0.0001588623,0.0008118585,0.0002664924,0.002087623,0.00005048409,0.00003105256],"category_scores_gemma":[0.00009998571,0.0001055875,0.00008467063,0.001413703,0.0006983176,0.0009566864,0.0006076006,0.0001528283,0.000009367564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001547573,"about_ca_system_score_gemma":0.0001667671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001590543,"about_ca_topic_score_gemma":0.00004257217,"domain_scores_codex":[0.9979133,0.00004256903,0.0002771619,0.0006401314,0.0007056095,0.0004211983],"domain_scores_gemma":[0.998015,0.0003966088,0.0001531524,0.0005783819,0.0007568931,0.00009999522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002474748,0.00005523857,0.01489723,0.00004033297,0.00002539504,5.27213e-7,0.004847244,0.006996901,0.002557742,0.003300216,0.001736653,0.9655178],"study_design_scores_gemma":[0.0002425048,0.000369776,0.03118159,0.00002967859,0.00001077661,0.000006303905,0.0000178943,0.9422522,0.0195298,0.0004511095,0.005800092,0.0001083271],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03297585,0.0001347865,0.9617395,0.001601731,0.002987118,0.0003108485,0.000004581168,0.0001811512,0.00006445648],"genre_scores_gemma":[0.9115713,0.00004654744,0.0868746,0.0003518465,0.0008253533,0.0002889478,4.714581e-7,0.000009572605,0.00003134308],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9654095,"threshold_uncertainty_score":0.6244242,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02399263484056004,"score_gpt":0.2799082927756323,"score_spread":0.2559156579350723,"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."}}