{"id":"W1993627307","doi":"10.2196/jmir.3062","title":"Evaluation of the Accuracy of Smartphone Medical Calculation Apps","year":2014,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network","funders":"","keywords":"mHealth; Smartphone application; Computer science; Smartphone app; Mobile apps; Machine learning; Medicine; World Wide Web; Multimedia; Psychological intervention","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":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09723613,0.00008398983,0.00039236,0.0002633577,0.0001865229,0.000003954779,0.001088384,0.0004767913,0.005489563],"category_scores_gemma":[0.07874914,0.00004945571,0.0001265869,0.0005442356,0.0004032545,0.0000723027,0.0003016365,0.00285806,0.00004962581],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002923328,"about_ca_system_score_gemma":0.007891988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008564537,"about_ca_topic_score_gemma":0.0004364994,"domain_scores_codex":[0.9777477,0.007446013,0.002115545,0.0001540634,0.01205597,0.0004806466],"domain_scores_gemma":[0.9847007,0.007416528,0.001373544,0.0005057294,0.00504528,0.0009582632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003216716,0.0006288638,0.02679416,0.00128334,0.00008824754,0.000002336508,0.001970751,0.00002350273,0.000353483,0.0200912,0.2025589,0.7458835],"study_design_scores_gemma":[0.01270953,0.001384604,0.2147234,0.01108546,0.0002198051,0.00009486014,0.002001997,0.1775549,0.001742705,0.01739315,0.560864,0.0002256207],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9321209,0.001031149,0.006162262,0.04987295,0.001495726,0.00205555,0.00000496357,0.00000835489,0.007248177],"genre_scores_gemma":[0.9972557,0.0005932922,0.00008789018,0.000640406,0.0009096165,0.0002178181,0.000003167476,0.00001193388,0.0002801084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7456579,"threshold_uncertainty_score":0.9994424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.239186366664667,"score_gpt":0.6043300449433879,"score_spread":0.365143678278721,"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."}}