{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00119692,0.0003859645,0.003576911,0.0001671665,0.00006062027,0.00002448166,0.0001955362,0.0002295341,0.0004327747],"category_scores_gemma":[0.0002083752,0.0003304745,0.00279657,0.0002679847,0.00007201403,0.000068398,0.00006423291,0.0002118715,0.00001534667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005364344,"about_ca_system_score_gemma":0.00009660929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002107387,"about_ca_topic_score_gemma":0.00004595671,"domain_scores_codex":[0.99473,0.001183605,0.003162723,0.0004826854,0.0001939747,0.0002470381],"domain_scores_gemma":[0.9957637,0.0004135975,0.003085849,0.0004090427,0.000243209,0.000084609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000007963502,0.0008087391,0.000002785561,0.6986756,0.00106842,7.296597e-7,0.00004752534,7.982164e-9,3.420137e-8,0.001966546,0.0002635513,0.2971581],"study_design_scores_gemma":[0.0005730879,0.001710252,0.00001005441,0.9278873,0.003877593,0.00001826612,0.0000901993,0.000002980131,4.288714e-7,0.0002040791,0.06543456,0.0001911877],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006087229,0.9912211,0.0006361414,0.00005409148,0.00122691,0.004883755,0.0006266225,0.00002458827,0.001320704],"genre_scores_gemma":[0.0002238535,0.9931355,0.0002207635,0.00001911749,0.00006437684,0.002748498,0.0009408519,0.00005633388,0.002590732],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2969669,"threshold_uncertainty_score":0.9999147,"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."}}