[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127349-en":3,"doc-seo-127349-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127349,962085564381,"Clementine","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms - Supplementary information","Supplementary material details missing-data handling and the resulting participant counts across passive controls and training conditions for a meta-analytic machine learning study targeting anxiety and depression symptoms. The document reports missing-data analyses for complete and clinical datasets and provides LME model evaluation via training/validation MSE. It also lists selected individual- and study-level moderators with estimated Beta coefficients and interaction terms (AIC backward-stepwise regression), including main and secondary outcomes for Aim 1 and Aim 2, supported by supplementary figures and tables.","Supplementary material  \nMachine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms  \nSupplementary Information 1: Missing data  \nParticipants assigned to a passive control condition (e.g., waiting list) were excluded from the full data set analysis to allow for the investigation of study-level moderators. This led to the removal of 78 participants. Additionally, 125 participants were missing a posttraining main score, and 8 lacked demographic information, leaving a total of 1,333 participants for the analysis of Aim 1 main outcome and 1,116 participants for the secondary outcome analysis.  \nFor Aim 2, the analysis focused on participants assigned to one of the training conditions, totaling 771 individuals. After excluding those with missing data, 694 participants remained for the main outcome analysis and 588 for the secondary outcome.  \nThe clinical data set analysis included 190 participants across three studies. After accounting for missing data, 171 participants were included in the analysis of Aim 1 main outcome, 144 in the secondary outcome analysis, and 86 in the Aim 2 main and secondary outcome analyses.  \nSupplementary Figure 1: Missing data analysis of the complete data set  \nSupplementary Figure 1. Missing data analysis of the complete data set. The figure shows the proportion of missing data for each predictor variable across the included studies. The color intensity indicates the proportion of missing values, with darker shades representing a higher proportion of missing data.  \nSupplementary Figure 2: Missing data analysis of the clinical data set  \nSupplementary Figure 2 . Missing data analysis of the clinical data set. The figure shows the proportion of missing data for each predictor variable across the included studies. The color intensity indicates the proportion of missing values, with darker shades representing a higher proportion of missing data  \nSupplementary Table 1, 2, & 3: Results ofthe LME analysis of the complete data set  \nTable 1 presents MSE values of the training and validation sets for the main and secondary outcomes.  \nSupplementary Table 1. MSE values for the main and secondary outcomes prediction of Aim 1.  \n\n|  | Training MSE | Validation MSE |\n| --- | --- | --- |\n| Main outcome | 1.23 | 0.99 |\n| Secondary outcome | 0.46 | 0.44 |\n\nSimilarly to the MSE values ofthe RF model, the MSE values for the LME model demonstrate relatively high accuracy, with values falling within less than one standard deviation of the standardized outcome scale.  \nTables 2 and 3 present the individual and study-level moderators selected for the model through backward-stepwise regression based on AIC, along with their Beta coefficients and the Beta coefficients ofthe interactions between the moderators.  \nSupplementary Table 2 . Beta coefficients of Aim 1: Main outcome  \nGain main  \n\n| Predictors | Estimates | CI | p |\n| --- | --- | --- | --- |\n| (Intercept) | -0.25 | -0.88– 0.38 | 0.438 |\n| is training [2] | -0.15 | -0.66 – 0.35 | 0.552 |\n| nsessions | 0.01 | 0.01 – 0.02 | 0.001 |\n| days between sessions | 0.11 | -0.03 – 0.25 | 0.115 |\n| session duration | -0.02 | -0.03 – -0.00 | 0.030 |\n| at home [2] | 0.42 | 0.03 – 0.81 | 0.033 |\n| has emotional stimuli [2] | 0.52 | 0.20 – 0.83 | 0.001 |\n| country [2] | -0.11 | -0.50 – 0.28 | 0.587 |\n| diagnosis [2] | -0.02 | -0.48 – 0.44 | 0.942 |\n| pre main | 0.35 | 0.20 – 0.49 | \u003C0.001 |\n| is training [2] X days between sessions | -0.18 | -0.35 – -0.01 | 0.042 |\n| is training [2] X at home [2] | -0.41 | -0.77 – -0.05 | 0.024 |\n| is training [2] X diagnosis [2] | 0.45 | 0.03 – 0.87 | 0.035 |\n| is training [2] X pre main | -0.12 | -0.21 – -0.03 | 0.008 |\n| days between sessions X pre main | -0.10 | -0.14 – -0.07 | \u003C0.001 |\n| at home [2] X pre main | 0.27 | 0.18 – 0.37 | \u003C0.001 |\n| has emotional stimuli [2] X pre main | 0.18 | 0.06 – 0.29 | 0.002 |\n| country [2] X pre main | 0.14 | 0.03 – 0.","cbCailgTDDNaoBf4","https://ap.wps.com/l/cbCailgTDDNaoBf4","pdf",605773,1,9,"English","en",105,"# Missing data\n## Participant exclusions and final sample sizes\n## Supplementary Figure 1-2: Missing data analysis\n# LME modeling results\n## Supplementary Table 1: Training/validation MSE\n## Supplementary Tables 2-3: Moderator Beta coefficients and interactions","[{\"question\":\"How were missing-data cases handled and what impact did it have on sample sizes?\",\"answer\":\"Participants in passive control conditions were excluded from the full-data analysis to support study-level moderator investigation. Additional exclusions occurred for missing posttraining main scores and missing demographics, yielding different final sample sizes across Aim 1, Aim 2, and the clinical dataset.\"},{\"question\":\"What do the supplementary figures show about missing data?\",\"answer\":\"Supplementary Figure 1 and Figure 2 present the proportion of missing data for each predictor variable across included studies. Color intensity indicates the relative proportion of missing values, with darker shades representing more missingness.\"},{\"question\":\"Which model performance metric is reported for training and validation sets?\",\"answer\":\"Supplementary Table 1 reports MSE values for both training and validation sets for the main and secondary outcomes, demonstrating relatively high predictive accuracy for the LME approach.\"}]","Machine learning meta-analysis identifies individual characteristics moderating cognitive intervention efficacy for anxiety and depression symptoms - Supplementary information | PDF",1785938426,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-meta-analysis-identifies-individual-characteristics-moderating-cognitive-intervention-efficacy-for-anxiety-and-depression-symptoms-supplementary-information","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-meta-analysis-identifies-individual-characteristics-moderating-cognitive-intervention-efficacy-for-anxiety-and-depression-symptoms-supplementary-information/127349/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How were missing-data cases handled and what impact did it have on sample sizes?","Question",{"text":75,"@type":76},"Participants in passive control conditions were excluded from the full-data analysis to support study-level moderator investigation. Additional exclusions occurred for missing posttraining main scores and missing demographics, yielding different final sample sizes across Aim 1, Aim 2, and the clinical dataset.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What do the supplementary figures show about missing data?",{"text":80,"@type":76},"Supplementary Figure 1 and Figure 2 present the proportion of missing data for each predictor variable across included studies. Color intensity indicates the relative proportion of missing values, with darker shades representing more missingness.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performance metric is reported for training and validation sets?",{"text":84,"@type":76},"Supplementary Table 1 reports MSE values for both training and validation sets for the main and secondary outcomes, demonstrating relatively high predictive accuracy for the LME approach.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]