{"id":"W3035389563","doi":"10.2196/17619","title":"Using Machine Learning to Optimize the Quality of Survey Data: Protocol for a Use Case in India","year":2020,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Strong; Bill and Melinda Gates Foundation","keywords":"Quality assurance; Computer science; Analytics; Data quality; Data collection; Reliability (semiconductor); Data science; Quality (philosophy); Quality management; Machine learning; Data mining; Engineering; Statistics; Operations management; Management system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07243701,0.001289761,0.001266759,0.002615175,0.002566624,0.002025159,0.002256104,0.002406568,0.04438795],"category_scores_gemma":[0.08207754,0.001516736,0.002122913,0.002862188,0.002508854,0.00159965,0.002753014,0.00362324,0.008377407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005308734,"about_ca_system_score_gemma":0.01458441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003208774,"about_ca_topic_score_gemma":0.004931647,"domain_scores_codex":[0.958727,0.03060849,0.004885661,0.001340721,0.002880729,0.001557441],"domain_scores_gemma":[0.9520379,0.02104586,0.004802465,0.00846675,0.0120641,0.001582845],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.03500891,0.02222856,0.01463942,0.03176932,0.0005901645,0.005099596,0.02502059,0.01321888,0.0102086,0.04360619,0.1826797,0.61593],"study_design_scores_gemma":[0.05554377,0.05046233,0.05564951,0.03715628,0.0008217963,0.002145055,0.0198819,0.01640956,0.01664443,0.03411874,0.7102495,0.0009170179],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.004940778,0.0001192154,0.01130665,0.0005070867,0.0001390357,0.979062,0.001381901,0.0001179757,0.002425325],"genre_scores_gemma":[0.002405853,0.0001023327,0.01117481,0.0001694379,0.00001481009,0.9855481,0.0001643552,0.00001105362,0.0004092951],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.927563,"threshold_uncertainty_score":0.3830881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8155315001526711,"score_gpt":0.6775852804360526,"score_spread":0.1379462197166185,"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."}}