[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118541-en":3,"doc-seo-118541-105":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},118541,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Streamlining Healthcare Operations using Causal Inference and Machine Learning","Healthcare operations involve complex interactions among physician decision-making, system design, and technology tools. Although Electronic Health Records and predictive analytics can improve efficiency, their effects on workload distribution, appointment delays, and patient outcomes require rigorous evaluation. This dissertation applies operations management principles, machine learning, and causal inference to restructure healthcare workflows. Results show scheduling documentation shifts, standardized documentation effects, and prediction-informed opioid relapse care can reduce EHR burden, improve timeliness, and lower relapse rates.","STREAMLINING HEALTHCARE OPERATIONS USING CAUSAL INFERENCE AND  \nMACHINE LEARNING  \nUmit Celik  \nA dissertation submitted to the faculty at the University of North Carolina at Chapel Hill in partial fulfillment of the requirements for the degree of Doctor of Philosophy in the Kenan-Flagler  \nBusiness School (Operations) .  \nChapel Hill  \n2025  \nApproved by:  \nBradley Staats Vinayak Deshpande Chloe Glaeser Saravanan Kesavan  \nSandeep Rath  \n©2025 Umit Celik  \nALL RIGHTS RESERVED  \nABSTRACT  \nUmit Celik: Streamlining Healthcare Operations using Causal Inference and Machine Learning  \n(Under the direction of Bradley Staats)  \nAim: Healthcare operations involve complex interactions between physician decision-making, system design, and technological tools. While Electronic Health Records (EHR) and predictive analytics influence efficiency, their effects on workload distribution, appointment delays, and patient outcomes require further examination.  \nBackground: The increasing use of digital systems in healthcare has reshaped provider workflows, yet challenges remain in balancing efficiency, standardization, and clinical decision-making.  \nMethodology and Results: This dissertation applies operations management principles, machine learning, and causal inference methods to improve healthcare workflows. The first study (Chapter 1) finds that shifting documentation to before appointments decreases total EHR time by 15.5% and reduces after-hours EHR work by 12%. Alternatively, completing tasks after appointments lowers after-hours work by 22% but increases overall workload. The second study (Chapter 2) shows that increased use of standardized documentation reduces appointment delays by 0.4% and in-room time by 6.8% but also leads to 78 more words per note and longer follow-up visits. The third study (Chapter 3) uses machine learning to identify patients at risk of opioid relapse with 0.97 accuracy and 0.99 recall, and shows that prediction-informed care reduces relapse rates by 2.6%.  \nConclusion: This dissertation provides empirical evidence on how healthcare workflows can be structured to reduce workload strains, improve timeliness, and enhance patient care. By integrating causal inference with operations management and machine learning, these findings contribute to the development of data-driven strategies for streamlining healthcare operations while addressing the challenges faced by providers and patients.  \nACKNOWLEDGEMENTS  \nThe completion of this dissertation marks the culmination of years of learning, research, and perseverance, but it is far from an individual achievement. This work has been shaped, refined, and strengthened by the support, guidance, and encouragement of many incredible people along the way. I am deeply grateful to everyone who has contributed to this journey, both academically and personally.  \nFirst and foremost, I extend my sincerest gratitude to my advisor, Brad Staats. From the very beginning of my doctoral journey, Brad has been a constant source of mentorship, encouragement, and intellectual challenge. Through every discussion, draft revision, and important decision, he has taught me not only how to conduct rigorous research but also how to communicate effectively. I have learned more from him than I can put into words, and I will always carry the lessons he has imparted. Thank you, Brad, for your patience, your belief in my work, and for setting an example of what it means to be an exceptional leader. Noted, I will never stop learning.  \nI am also deeply thankful to Sandeep Rath, whose keen understanding of both analytical and empirical research in operations management has been instrumental in shaping my work. His diverse expertise in healthcare operations provided critical insights that helped refine this dissertation. Working with him on the first two chapters was not only intellectually enriching but also genuinely fun. His wisdom and perspective always helped bring clarity to the most complex probl","cbCaitwQ6mcIEstA","https://ap.wps.com/l/cbCaitwQ6mcIEstA","pdf",1631948,1,162,"English","en",105,"# Abstract\n# Acknowledgements","[{\"question\":\"What is the main aim of the dissertation?\",\"answer\":\"To improve healthcare workflows by examining how EHR and predictive analytics affect workload distribution, appointment delays, and patient outcomes, using causal inference and machine learning approaches.\"},{\"question\":\"What does the first study on documentation timing show?\",\"answer\":\"Moving documentation to before appointments decreases total EHR time by 15.5% and reduces after-hours EHR work by 12%, while completing tasks after appointments lowers after-hours work by 22% but increases overall workload.\"},{\"question\":\"How does machine learning support patient care in the dissertation?\",\"answer\":\"It identifies patients at risk of opioid relapse with high accuracy and recall, and prediction-informed care reduces relapse rates by 2.6%.\"}]","Streamlining Healthcare Operations using Causal Inference and Machine Learning | PDF",1785684065,408,{"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},"streamlining-healthcare-operations-using-causal-inference-and-machine-learning","",{"@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/streamlining-healthcare-operations-using-causal-inference-and-machine-learning/118541/",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 is the main aim of the dissertation?","Question",{"text":75,"@type":76},"To improve healthcare workflows by examining how EHR and predictive analytics affect workload distribution, appointment delays, and patient outcomes, using causal inference and machine learning approaches.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the first study on documentation timing show?",{"text":80,"@type":76},"Moving documentation to before appointments decreases total EHR time by 15.5% and reduces after-hours EHR work by 12%, while completing tasks after appointments lowers after-hours work by 22% but increases overall workload.",{"name":82,"@type":73,"acceptedAnswer":83},"How does machine learning support patient care in the dissertation?",{"text":84,"@type":76},"It identifies patients at risk of opioid relapse with high accuracy and recall, and prediction-informed care reduces relapse rates by 2.6%.","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"]