{"id":"W4416379937","doi":"10.2196/85329","title":"Methodological Considerations in Evaluating Mental Health Apps: Ensuring Reliability and Patient Safety","year":2025,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Patient safety; Mental health; mHealth; MEDLINE; Health care","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":["metaresearch"],"category_scores_codex":[0.6832619,0.002705267,0.005545931,0.007630228,0.006846822,0.01178291,0.007244476,0.007360253,0.004331358],"category_scores_gemma":[0.8590968,0.003297154,0.006293873,0.007027058,0.01480696,0.007974901,0.006430192,0.009135067,0.001453135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008810285,"about_ca_system_score_gemma":0.02925423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009955182,"about_ca_topic_score_gemma":0.02341723,"domain_scores_codex":[0.1829251,0.6007203,0.1132768,0.0125109,0.0878152,0.002751725],"domain_scores_gemma":[0.1103837,0.7139369,0.0407027,0.06459706,0.0678229,0.002556751],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01562002,0.007620173,0.2010063,0.05829854,0.02249409,0.003159521,0.09229273,0.01501368,0.009121253,0.1727992,0.04525452,0.35732],"study_design_scores_gemma":[0.01279268,0.01943108,0.2185813,0.07027249,0.01799665,0.004980163,0.02799524,0.05042591,0.01691972,0.301758,0.256686,0.002160871],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1107627,0.02673035,0.6230441,0.04321468,0.01673477,0.1423933,0.002116044,0.0007468019,0.03425724],"genre_scores_gemma":[0.3683107,0.002490277,0.4180165,0.0106447,0.002072014,0.194968,0.0005949656,0.0003762596,0.002526549],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3167381,"threshold_uncertainty_score":0.3905945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2794140933994985,"score_gpt":0.550959408493924,"score_spread":0.2715453150944255,"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."}}