[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117448-en":3,"doc-seo-117448-105":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},117448,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",7,"Healthcare","Orthodontic Predictions with Machine Learning - Research-in-Progress Paper","The study addresses how machine learning models can be optimized to improve both the accuracy and transparency of Invisalign treatment outcome predictions. A Design Science Research approach combined with CRISP-DM is used to build a predictive model based on 657 de-identified orthodontic records from five private clinics in Thailand. Decision tree, random forest, neural network, and XGBoost are trained to support interpretability, and SHAP-based analysis of ANN and XGBoost is applied to reveal feature importance for clinical decision interpretability.","Association for Information Systems  \nAIS Electronic Library (AISeL)  \n\n| Digit 2024 Proceedings | Diffusion Interest Group In Information Technology |\n| --- | --- |\n| 12-15-2024\u003Cbr>Orthodontic Predictions with Machine Learning Khin Than Win\u003Cbr>Sanisa Trakulmututa\u003Cbr>Mahdi Fahmideh\u003Cbr>Follow this and additional works at: [https://aisel.aisnet.org/digit2024](https://aisel.aisnet.org/digit2024) |  |\n\nThis material is brought to you by the Diffusion Interest Group In Information Technology at AIS Electronic Library (AISeL) . It has been accepted for inclusion in Digit 2024 Proceedings by an authorized administrator of AIS Electronic Library (AISeL) . For more information, please contact [elibrary@aisnet.org](elibrary@aisnet.org).  \nOrthodontic Predictions with Machine  \nLearning  \nResearch-in-Progress Paper  \nKhin Than Win  \nUniversity of Wollongong Wollongong, Australia [win@uow.edu.au](win@uow.edu.au)  \nSanisa Trakulmututa  \nOrthodontist,DDS,RACDs,CHIA,MHI Private Practice, Bangkok, Thailand  \nUniversity of Wollongong, Australia [sanisaTK@outlook.com](sanisaTK@outlook.com)  \nMahdi Fahmideh  \nUniversity of Southern Queensland  \nQueensland, Australia  \n[Mahdi.Fahmideh@unisq.edu.au](Mahdi.Fahmideh@unisq.edu.au)  \nAbstract  \nThe study aims to answer the research question: how can machine learning models be optimized to enhance the accuracy and transparency of Invisalign treatment outcome predictions? The research methodology deployed in this study focuses on applying the Design Science Research and Cross Industry Standard Process for Data Mining (CRISP-DM) to construct a predictive model for Invisalign treatment outcomes. The data set is from five distinct private dental clinics across Thailand, consisting of 657 deidentified orthodontic treatment records. Machine learning models, Decision tree, random forest, Neural Net and XGBoost were selected for the model development to ensure transparency and interpretability. SHapley Additive exPlanations (SHAP) analysis of ANN and XG Boost demonstrated the feature importance in Invisalign treatment decision interpretability.  \n.  \nKeywords: Orthodontic, machine learning, transparency, explainability, SHapley Additive exPlanations  \nOrthodontic Predictions with Machine  \nLearning  \nResearch-in-Progress Paper  \nIntroduction  \nAdvances in artificial intelligence (AI) have led to the adoption and integration of AI in different industries. While the applicability of AI and its benefits have been identified, there are concerns regarding ethical perspectives and the explainability of AI for its use and decision-making. Healthcare is not an exception. Various AI models have been applied in healthcare decision-making, such as the prediction of lung cancer (Altuhaifa et al. 2023), breast cancer (Shukla et al. 2018), personalized dietary advice (Guan et al. 2023) . Similarly, artificial intelligence (AI) has been increasingly employed, as well as the Invisalign, clear aligner treatment (CAT) in dentistry (Thurzo et al. 2021) . Invisalign treatment is a prime example that reflects patient-centred care, highlighting the critical role of machine learning (ML) in enhancing treatment predictability and personalisation (Malaga 2023) . The synergy between predictive analytics and practical application in orthodontics exemplifies how data-driven decision-making can significantly augment clinical practice and patient satisfaction (Sycińska-Dziarnowska et al. 2022) . In a study by Younis et al. (2024) Integrating AI in Orthodontics faces challenges including the practical application of theoretical models, data diversity, and ethical concerns. Interpretability and explainability of the models have been of great concern in the implementation and adoption of these models in healthcare. Thus, the World Health Organisation’s ethical principles for using AI in health (WHO 2024) recommended ensuring the explainability, transparency and intelligibility of the AI models.  \nDeveloping robust, interpretable AI models and","cbCaiedPtjpUjmNz","https://ap.wps.com/l/cbCaiedPtjpUjmNz","pdf",640137,1,10,"English","en",105,"# Introduction\n## AI in healthcare and explainability\n## Research question and study focus\n# Materials and Methods\n## Methodology (DSR and CRISP-DM)\n## Dataset and ethics\n# Model Development and Interpretability\n## Selected ML models\n## SHAP-based feature importance","[{\"question\":\"What research question does this paper focus on?\",\"answer\":\"How can machine learning models be optimized to enhance the accuracy and transparency of Invisalign treatment outcome predictions?\"},{\"question\":\"What dataset and data sources were used?\",\"answer\":\"The model is built using 657 de-identified orthodontic treatment records from five distinct private dental clinics across Thailand.\"},{\"question\":\"Which machine learning models and interpretability method are used?\",\"answer\":\"Decision tree, random forest, neural net, and XGBoost are selected, and SHAP analysis is used on ANN and XGBoost to identify feature importance for interpretability.\"}]","Orthodontic Predictions with Machine Learning - Research-in-Progress Paper | PDF",1785675914,25,{"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},"orthodontic-predictions-with-machine-learning-research-in-progress-paper","",{"@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/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/orthodontic-predictions-with-machine-learning-research-in-progress-paper/117448/",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","2026-08-02",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 research question does this paper focus on?","Question",{"text":75,"@type":76},"How can machine learning models be optimized to enhance the accuracy and transparency of Invisalign treatment outcome predictions?","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What dataset and data sources were used?",{"text":80,"@type":76},"The model is built using 657 de-identified orthodontic treatment records from five distinct private dental clinics across Thailand.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning models and interpretability method are used?",{"text":84,"@type":76},"Decision tree, random forest, neural net, and XGBoost are selected, and SHAP analysis is used on ANN and XGBoost to identify feature importance for interpretability.","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},[93,97,101,105,110,115,118,123,128,131,134],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]