{"id":"W3178339185","doi":"10.5093/pi2021a4","title":"A Systematic Review of Machine Learning for Assessment and Feedback of Treatment Fidelity","year":2021,"lang":"en","type":"review","venue":"Psychosocial Intervention","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fidelity; Computer science; Coding (social sciences); Machine learning; Implementation; Scalability; Artificial intelligence; Session (web analytics); Utterance; Software engineering; Database","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05362033,0.002005054,0.00923536,0.01778248,0.001198587,0.00428308,0.00346979,0.00245878,0.006142646],"category_scores_gemma":[0.2276953,0.001597772,0.007658939,0.01318267,0.001768543,0.004129981,0.002866994,0.002367399,0.0007442467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008455884,"about_ca_system_score_gemma":0.02484472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009440855,"about_ca_topic_score_gemma":0.02707083,"domain_scores_codex":[0.9479378,0.02378985,0.01733398,0.001747422,0.008791673,0.0003993371],"domain_scores_gemma":[0.7965292,0.1642149,0.01882294,0.004106704,0.01556933,0.0007568963],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001524947,0.00002125121,0.0003543243,0.8034109,0.004997612,0.00005409954,0.0003054032,0.0002177302,0.0001081739,0.0008911666,0.004686571,0.1848003],"study_design_scores_gemma":[0.0001214267,0.00009120488,0.0009769298,0.9608357,0.01103683,0.0001192163,0.0001158192,0.0001547323,0.0001333819,0.00083066,0.025549,0.00003506202],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003233524,0.9954027,0.001346566,0.0008501638,0.0002463736,0.0009210653,0.0004049734,0.00002880253,0.0004760004],"genre_scores_gemma":[0.006984639,0.9827234,0.006303488,0.000846534,0.0001252277,0.002392516,0.0004089743,0.00002523883,0.0001899025],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9463797,"threshold_uncertainty_score":0.2835748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1299597314221525,"score_gpt":0.5242350526048934,"score_spread":0.3942753211827409,"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."}}