{"id":"W3135757929","doi":"10.1016/j.genhosppsych.2021.02.010","title":"Considerations for evaluating digital mental health tools remotely- reflections after a randomized trial of Thought Spot","year":2021,"lang":"en","type":"article","venue":"General Hospital Psychiatry","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; Centre for Addiction and Mental Health; University of Toronto","funders":"Institute of Health Services and Policy Research; Canadian Institutes of Health Research; Ministry of Training, Colleges and Universities","keywords":"Randomized controlled trial; Mental health; Blind spot; Psychology; Applied psychology; Medicine; Psychiatry; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000672926,0.0003080743,0.000816073,0.0001465179,0.0003400751,0.0002050843,0.0001337751,0.0001511056,0.0006490453],"category_scores_gemma":[0.0005493114,0.0003102295,0.0009650863,0.0003225402,0.0001883116,0.0004472453,0.00008628461,0.0002245389,0.00008414493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001544113,"about_ca_system_score_gemma":0.0006306744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005087186,"about_ca_topic_score_gemma":0.0001537605,"domain_scores_codex":[0.996334,0.0003801915,0.001662542,0.0006631856,0.0003609049,0.0005992122],"domain_scores_gemma":[0.997966,0.0004113862,0.0005670327,0.0005643687,0.0002573436,0.0002338737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.5434328,0.01247496,0.0002915679,0.0004995743,0.001564576,0.00001625255,0.00364917,0.00002614891,0.0001369449,0.2877041,0.1008913,0.04931257],"study_design_scores_gemma":[0.8582336,0.008026355,0.0007426194,0.0004415378,0.0001768317,0.0001454633,0.001569063,0.0001424361,0.0002896157,0.1246057,0.004879076,0.0007477569],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.891311,0.003318634,0.002864766,0.03447928,0.03539126,0.007239941,0.003500883,0.0001890117,0.0217052],"genre_scores_gemma":[0.9282896,0.00001357264,0.05598423,0.001663582,0.0011912,0.001469932,0.0005929408,0.00007952462,0.01071542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3148007,"threshold_uncertainty_score":0.999935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06826704267554354,"score_gpt":0.4340870289429833,"score_spread":0.3658199862674398,"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."}}