[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125790-en":3,"doc-seo-125790-105":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},125790,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Validation of a Machine Learning Model to Predict Childhood Lead Poisoning - Supplementary Online Content","Supplementary online material for a study validating a machine learning model designed to predict childhood lead poisoning. The content details spatiotemporal, spatial, and sociodemographic predictors used in a random forest framework, alongside logistic regression fitted coefficients. Validation performance is assessed through confusion-matrix metrics, receiver operating characteristic curves, and comparisons between original and updated models. Risk estimation covers elevated blood lead outcomes across validation cohorts and includes sensitivity analyses and subgroup stratifications.","Supplementary Online Content  \nPotash E, Ghani R, Walsh J, et al. Validation of a machine learning model to predict childhood lead poisoning. JAMA Netw Open. 2020;3(9):e2012734 .  \ndoi:10.1001/jamanetworkopen.2020.12734  \neTable 1. Spatiotemporal Predictors in the Random Forest Model eTable 2. Spatial Predictors in the Random Forest Model  \neTable 3. Sociodemographic Predictors in the Random Forest Model eTable 4. Fitted Coefficients for the Logistic Regression Model  \neTable 5. Comparison Between Original and Updated Random Forest Models of Confusion Matrix Metrics on 2013 Cohort  \neTable 6. Elevated Blood Lead Level Outcomes by Validation Cohort  \neTable 7. Confusion Matrix Metrics for the Random Forest Model by Validation Cohort eTable 8. Inspection Cohort Lead Hazard Rate Estimate  \neTable 9. Comparison of Most Important Random Forest Predictor Values in Training and Test Sets  \neTable 10. Baseline Characteristics of 2013 Cohort, With and Without Measured Outcome eTable 11. Baseline Characteristics of Inspection Cohort, Inspected and Uninspected eTable 12. Sensitivity Analysis of Area Under Receiver Operating Characteristic Curve  \neTable 13. Sensitivity Analysis of Confusion Matrix Metrics  \neTable 14. Elevated Blood Lead Level Risk in 2013 Cohort by Enrollment in Women, Infants, and Children (WIC) Program  \neTable 15. Elevated Blood Lead Level Risk in 2013 Cohort by Race/Ethnicity eTable 16. Race/Ethnicity by Risk Group for the Random Forest Model  \neTable 17. Confusion Matrix Metrics for the Random Forest Model by Race/Ethnicity eMethods. Sensitivity Analysis  \neFigure. Receiver Operating Characteristic Curves by Validation Cohort  \nThis supplementary material has been provided by the authors to give readers additional information about their work.  \neTable 1. Spatiotemporal Predictors in the Random Forest Model  \n\n| Data Source | Variable | Aggregation Functions |\n| --- | --- | --- |\n| Blood Lead Levels | Address days between first and last sample | mean |\n|  | Address days since BLL sample | max, min |\n|  | Address days since EBLL ≥ 10 μg/dL | max, min |\n|  | Address days since EBLL ≥ 6 μg/dL | max, min |\n|  | Child age | max, mean, min |\n|  | Child average BLL | max, mean, median, min |\n|  | Child maximum BLL | max, mean, median, min |\n|  | Child EBLL ≥ 10 μg/dL | count, rate |\n|  | Child EBLL ≥ 10 μg/dL at present address | count, rate |\n|  | Child EBLL ≥ 10 μg/dL at previous address | count, rate |\n|  | Child EBLL ≥ 10 μg/dL at subsequent address | count, rate |\n|  | Child EBLL ≥ 6 μg/dL | count, rate |\n|  | Child EBLL ≥ 6 μg/dL at present address | count, rate |\n|  | Child EBLL ≥ 6 μg/dL at previous address | count, rate |\n|  | Child EBLL ≥ 6 μg/dL at subsequent address | count, rate |\n|  | Child number of BLL samples | max, mean |\n|  | Child number of addresses | max, mean |\n|  | Child screened | %, count |\n| Building Permits and Violations | Complied | %, count |\n|  | Easy permits | %, count |\n|  | Electric wiring permits | %, count |\n|  | Elevator permits | %, count |\n|  | Extension permits | %, count |\n|  | New construction permits | %, count |\n|  | No entry | %, count |\n|  | Open violation | %, count |\n|  | Paint violations | %, count |\n|  | Permits | count |\n|  | Porch permits | %, count |\n|  | Porch violations | %, count |\n|  | Reinstate permits | %, count |\n|  | Renovation/alteration permits | %, count |\n|  | Scaffolding permits | %, count |\n|  | Signs permits | %, count |\n|  | Violations | count |\n|  | Wall violations | %, count |\n|  | Water violations | %, count |\n|  | Window violations | %, count |\n|  | Wrecking/demolition permits | %, count |\n| Investigations | Compliance | %, count |\n|  | Days since case closure | max, mean, min |\n|  | Days since compliance | max, mean, min |\n|  | Days since inspection | max, mean, min |\n\n\n| Data Source | Variable | Aggregation Functions |\n| --- | --- | --- |\n|  | Days since referral | max, mean, min |\n|  | Inspection | %, count |\n|  | Inspection Interior or exterior ","cbCaifk2H8dK2p3w","https://ap.wps.com/l/cbCaifk2H8dK2p3w","pdf",529700,1,22,"English","en",105,"# eTable 1. Spatiotemporal Predictors in the Random Forest Model\n## Data sources and aggregated functions\n# eTable 2. Spatial Predictors in the Random Forest Model\n## Spatial scales and variable definitions\n# eTable 3. Sociodemographic Predictors in the Random Forest Model\n## Predictors by category","[{\"question\":\"What kinds of predictors are used in the random forest model validation?\",\"answer\":\"The supplementary material organizes predictors into spatiotemporal, spatial, and sociodemographic groups, each mapped to specific variables and aggregation functions.\"},{\"question\":\"How is model performance evaluated across validation cohorts?\",\"answer\":\"Performance uses confusion-matrix metrics and receiver operating characteristic analysis, including comparisons between original and updated random forest models.\"},{\"question\":\"What analyses support robustness of the predictive model?\",\"answer\":\"Sensitivity analyses are provided, including area under the receiver operating characteristic curve and additional confusion-matrix metric sensitivity results across cohorts.\"}]","Validation of a Machine Learning Model to Predict Childhood Lead Poisoning - Supplementary Online Content | PDF",1785901219,55,{"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},"validation-of-a-machine-learning-model-to-predict-childhood-lead-poisoning-supplementary-online-content","",{"@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/validation-of-a-machine-learning-model-to-predict-childhood-lead-poisoning-supplementary-online-content/125790/",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},"What kinds of predictors are used in the random forest model validation?","Question",{"text":75,"@type":76},"The supplementary material organizes predictors into spatiotemporal, spatial, and sociodemographic groups, each mapped to specific variables and aggregation functions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is model performance evaluated across validation cohorts?",{"text":80,"@type":76},"Performance uses confusion-matrix metrics and receiver operating characteristic analysis, including comparisons between original and updated random forest models.",{"name":82,"@type":73,"acceptedAnswer":83},"What analyses support robustness of the predictive model?",{"text":84,"@type":76},"Sensitivity analyses are provided, including area under the receiver operating characteristic curve and additional confusion-matrix metric sensitivity results across cohorts.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]