{"id":"W3192313172","doi":"10.2196/23938","title":"Comparison of the Validity and Generalizability of Machine Learning Algorithms for the Prediction of Energy Expenditure: Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Physical Activity and Health","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council","keywords":"Generalizability theory; Machine learning; Computer science; Energy expenditure; Algorithm; Artificial intelligence; Predictive validity; Psychology; Statistics; Mathematics; Clinical psychology; Medicine","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":[0.08798075,0.001810012,0.00103203,0.001394738,0.0007560354,0.001620416,0.002112742,0.002141696,0.001229977],"category_scores_gemma":[0.1979607,0.0006095486,0.003008937,0.0008385881,0.002223796,0.001890276,0.002427409,0.001877887,0.0007665831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008944568,"about_ca_system_score_gemma":0.001301396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003083381,"about_ca_topic_score_gemma":0.001817038,"domain_scores_codex":[0.9631963,0.02509263,0.003108586,0.004152873,0.003899992,0.0005495063],"domain_scores_gemma":[0.7434446,0.2002842,0.009634099,0.02486936,0.02059832,0.001169415],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02473705,0.006411779,0.7174754,0.001020345,0.008279902,0.0002331436,0.002263194,0.08348347,0.006580684,0.00131233,0.003141525,0.1450611],"study_design_scores_gemma":[0.004070347,0.03029818,0.5327339,0.0006856793,0.003185741,0.0007091032,0.001371196,0.4064005,0.01158301,0.003774053,0.004922933,0.0002653376],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9529141,0.001276404,0.04121168,0.0002013674,0.0002288648,0.001509278,0.0006859783,0.0003085175,0.001663871],"genre_scores_gemma":[0.9833192,0.000318817,0.01272901,0.0001758357,0.00007038759,0.0007972416,0.001992278,0.0001247024,0.0004724881],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9120193,"threshold_uncertainty_score":0.4652923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.170527898966134,"score_gpt":0.4348356812391856,"score_spread":0.2643077822730516,"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."}}