[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125338-en":3,"doc-seo-125338-105":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},125338,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","A Machine Learning Approach to Improve Prediction in Chemical Exposure Risk Assessment","Exposure models underpin chemical exposure prediction in workplaces, providing an essential alternative when measurements are costly, time-consuming, or infeasible. Despite extensive use, prediction variability, limited model updating, and restricted access to required inputs hinder performance. The study evaluates modern machine learning techniques to strengthen exposure modeling by generating synthetic datasets when data are scarce and applying supervised methods when measurements exist. Deep neural networks show strong gains over Advanced Reach Tool predictions, and a multi-source pipeline improves general robustness via unified shared representations.","Technological University Dublin  \nARROW@TU Dublin  \n\n| SAML-25 Workshop on Statistical and Machine Learning | Research Institutes/Centres/Groups |\n| --- | --- |\n| 2025-06-05\u003Cbr>A Machine Learning Approach to Improve Prediction in Chemical Exposure Risk Assessment\u003Cbr>Michele Marro\u003Cbr>Department of Occupational and Environmental Health, University of Lausanne, michele. marr[o@unisante.ch](o@unisante.ch)\u003Cbr>Cédric Koller\u003Cbr>Department of Occupational and Environmental Health, University of Lausanne, [cedric.koller@unisante.ch](cedric.koller@unisante.ch)\u003Cbr>Hasnaa Chettou\u003Cbr>Department of Occupational and Environmental Health, University of Lausanne, hasnaa.chettou@inisante.ch\u003Cbr>See next page for additional authors\u003Cbr>Follow this and additional works at: [https://arrow.tudublin.ie/saml](https://arrow.tudublin.ie/saml)\u003Cbr> Part of the Physical Sciences and Mathematics Commons |  |\n\nRecommended Citation  \nMarro, Michele; Koller, Cédric; Chettou, Hasnaa; and Vernez, David, \"A Machine Learning Approach to Improve Prediction in Chemical Exposure Risk Assessment\" (2025) . SAML-25 Workshop on Statistical and Machine Learning. 12.  \n[https://arrow.tudublin.ie/saml/12](https://arrow.tudublin.ie/saml/12)  \nThis Conference Paper is brought to you by the EUt+ Academic Press a free to read and publish press of the European University of Technology.  \nThis work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.  \nAuthors  \nMichele Marro, Cédric Koller, Hasnaa Chettou, and David Vernez  \nThis conference paper is available at ARROW@TU Dublin: [https://arrow.tudublin.ie/saml/12](https://arrow.tudublin.ie/saml/12)  \nA machine learning approach to improve prediction in chemical  \nexposure risk assessment  \nMichele Marro∗  \nmichele.marro@unisante.ch Center for Primary Care and Public Health (Unisanté), University of Lausanne, Department of Occupational and Environmental Health  \nLausanne, Switzerland  \nHasnaa Chettou  \nhasnaa.chettou@unisante.ch Center for Primary Care and Public Health (Unisanté), University of Lausanne, Department of Occupational and Environmental Health  \nLausanne, Switzerland  \nCédric Koller  \n[cedric.koller@unisante.ch](cedric.koller@unisante.ch)[ ](cedric.koller@unisante.ch)Center for Primary Care and Public Health (Unisanté), University of Lausanne, Department of Occupational and Environmental Health  \nLausanne, Switzerland  \nDavid Vernez  \n[david.vernez@unisante.ch](david.vernez@unisante.ch)[ ](david.vernez@unisante.ch)Center for Primary Care and Public Health (Unisanté), University of Lausanne, Department of Occupational and Environmental Health  \nLausanne, Switzerland  \nAbstract  \nExposure models play a crucial role in predicting chemical exposure in workplaces, offering an essential alternative to measurements, which are resource-intensive and time-consuming and sometimes not possible. Despite their widespread use and continuous development, significant challenges persist, including variability in predictions, limited model updates, and difficulties in accessing the required input data. In this study, we investigate how modern machine learning techniques can contribute to the improvement of exposure models by addressing these limitations.  \nTo overcome the frequent lack of data, we explore the use of synthetic datasets generated through existing exposure models. This approach allows for the study of relationships among variables, pattern extraction, and dimensionality reduction, facilitating model refinement without the need for complex model integration. When measurement data are available, supervised machine learning methods can be directly applied. As an example, deep neural networks trained on exposure data from a reference measurement dataset demonstrate substantial improvements compared to the Advanced Reach Tool (ART) predictions. However, this approach restricts the model to the determinants and exposure scenarios present ina single database, limiting its generali","cbCaioJWFiifnHh3","https://ap.wps.com/l/cbCaioJWFiifnHh3","pdf",418280,1,5,"English","en",105,"# Abstract\n# Context and problem\n# Exposure modeling and REACH framework\n# Machine learning strategy and synthetic data\n# Supervised learning and neural network results\n# Multi-source unified predictive pipeline\n# Preliminary evaluation and outlook","[{\"question\":\"Why are exposure models important in chemical exposure risk assessment?\",\"answer\":\"Exposure models support predicting chemical exposure scenarios in workplaces without relying on direct experiments, which can be resource-intensive or impractical.\"},{\"question\":\"What challenges limit current exposure modeling approaches?\",\"answer\":\"Key issues include variability in predictions, limited updates to models over time, and difficulty obtaining the input data required for modeling.\"},{\"question\":\"How does the proposed machine learning approach improve prediction accuracy?\",\"answer\":\"It uses synthetic datasets when measurements are unavailable and supervised machine learning when measurement data exist; deep neural networks can outperform Advanced Reach Tool predictions, and a unified multi-source pipeline improves robustness.\"}]","A Machine Learning Approach to Improve Prediction in Chemical Exposure Risk Assessment | PDF",1785898275,13,{"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},"a-machine-learning-approach-to-improve-prediction-in-chemical-exposure-risk-assessment","",{"@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/a-machine-learning-approach-to-improve-prediction-in-chemical-exposure-risk-assessment/125338/",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},"Why are exposure models important in chemical exposure risk assessment?","Question",{"text":75,"@type":76},"Exposure models support predicting chemical exposure scenarios in workplaces without relying on direct experiments, which can be resource-intensive or impractical.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What challenges limit current exposure modeling approaches?",{"text":80,"@type":76},"Key issues include variability in predictions, limited updates to models over time, and difficulty obtaining the input data required for modeling.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed machine learning approach improve prediction accuracy?",{"text":84,"@type":76},"It uses synthetic datasets when measurements are unavailable and supervised machine learning when measurement data exist; deep neural networks can outperform Advanced Reach Tool predictions, and a unified multi-source pipeline improves robustness.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"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":21,"slug":137},19,"General","general"]