{"id":"W4210594218","doi":"10.2196/preprints.9960","title":"Predicting the Reasons of Customer Complaints: A First Step Toward Anticipating Quality Issues of In Vitro Diagnostics Assays with Machine Learning (Preprint)","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Quality and Safety in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Vendor; Boosting (machine learning); Computer science; Training set; Artificial intelligence; Preprint; Machine learning; Quality (philosophy); Data mining; Business; Marketing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002548636,0.001254786,0.001016342,0.001399663,0.0003595907,0.002130006,0.0009346001,0.001549757,0.002045159],"category_scores_gemma":[0.007490887,0.000314233,0.0008959028,0.0008682304,0.0002624454,0.0009971681,0.0004837056,0.001300596,0.001365257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000732203,"about_ca_system_score_gemma":0.0009728331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002492028,"about_ca_topic_score_gemma":0.002540371,"domain_scores_codex":[0.998782,0.000521653,0.0001181897,0.0001901897,0.0002444246,0.0001434914],"domain_scores_gemma":[0.9940241,0.00369882,0.0008677231,0.0003313113,0.000895441,0.0001825487],"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":[0.002056756,0.003135837,0.2075291,0.0008504241,0.000411071,0.0008841252,0.0003997395,0.1684593,0.07444976,0.001194727,0.02042402,0.5202053],"study_design_scores_gemma":[0.00002516499,0.0005866622,0.04429204,0.00007250915,0.00009261688,0.0002451466,0.0002300987,0.9176461,0.03243133,0.001215938,0.00310452,0.00005790689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5180385,0.003751604,0.455707,0.004856404,0.0005321525,0.0006488441,0.002846255,0.008174884,0.005444351],"genre_scores_gemma":[0.8523892,0.0006486897,0.1415533,0.0006609408,0.0002538759,0.0001743876,0.002188883,0.00009972045,0.002030995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002548636,"threshold_uncertainty_score":0.01347864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1548285037617101,"score_gpt":0.461962306695009,"score_spread":0.3071338029332989,"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."}}