[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124013-en":3,"doc-seo-124013-105":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},124013,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",7,"Healthcare","Privacy-Preserving Machine Learning for Electronic Health Records using Federated Learning and Differential Privacy - Slides","Electronic Health Record (EHR) systems store highly sensitive patient information including diagnoses, treatments, costs, and other personal identifiers. When machine learning is applied to analyze EHR data to improve care, privacy risks arise from potential data breaches, insecure communication, and weak access controls, alongside regulatory pressure from HIPAA and GDPR. This work presents privacy-preserving machine learning (PPML) approaches that enable collaborative model training and evaluation while limiting disclosure through federated learning and differential privacy.","Privacy-Preserving Machine Learning for Electronic Health Records using Federated Learning and Differential Privacy  \nNaif Ganadily & Han J. Xia  \nUniversity of Washington, Department of Electrical and Computer Engineering  \nAbstract — An Electronic Health Record (EHR) is an electronic database used by healthcare providers to store patients’ medical records which may include diagnoses, treatments, costs, and other personal information. Machine learning (ML) algorithms can be used to extract and analyze patient data to improve patient care. Patient records contain highly sensitive information, such as social security numbers (SSNs) and residential addresses, which introduces a need to apply privacy-preserving techniques for these ML models using federated learning and differential privacy.  \nI. INTRODUCTION  \nWith the increased application of machine learning (ML) in the healthcare industry to diagnose patients or to prescribe medication, applying a privacy-preserving machine learning (PPML) framework for Electronic Health Record (EHR) systems allows healthcare providers to collaboratively train and evaluate ML models without exposing sensitive patient records. EHRs are prone to attacks by cybercriminals, hackers, unauthorized third parties, and even administrators operating within the healthcare system. Attacks may occur in the form of data breaches, insecure communication channels, or insufficient access controls. Given the sensitive nature of patient records, these risks must be mitigated to protect the trust between patients and those working in the healthcare industry, and to protect healthcare providers against potential legal repercussions in the event of an unauthorized access.  \nPPML algorithms are also needed to comply with federal regulations, such as the Health Insurance Portability and Accountability Act (HIPAA) in the United States or the General Data Protection Regulation (GDPR) in the European Union. These privacy laws were created to protect personally identifiable information from being disclosed without their knowledge or consent.  \nII. ARCHITECTURE  \nThe EHR architecture described in this section is based on the literature, Aspects of privacy for electronic health records (Haas, et al.) . As shown in Fig. 1, the architecture consists of two subsystems – the patient services scheme and the data services scheme. The patient services subsystem focuses on administrative communication and provides an interface for patients to express their consent and agreement for privacy policies regarding the usage of their data. The data service controls the flow and storage of medical records and providesan interface for different medical providers to access its data in a secure manner.  \nFig. 1 EHR architecture overview [1] .  \nThe patient service scheme shown in Fig. 2 has three primary functions: (1) to provide a means of communication with patients,(2) to control the flow of information, and (3) to allow verifiers to ensure that all agreed-upon policies have been enforced. The policy management allows patients to view, express their consent, and to modify privacy policies that describe their access rights. The logging service uses hash chains to store authentic log files for every access request generated from the policy service. When the verification service obtains log files from the logging service, it uses this information to prove to the verifier that the system has enforced the agreed-upon policy.  \nFig. 2 Scheme of the patient service [1] .  \nThe purpose of the policy service within the data service subsystem, as shown in Fig. 3, is to inform the policy enforcement point (PEP) the validity of an access request based on the previously agreed-upon privacy policy. The policy service also sends the resulting decision to the patient service for logging. The watermarking scheme (WMS) applies an asymmetrical digital watermarking (or fingerprinting) scheme, wherein the provider and the consumer receive different watermark","cbCair8JzoEyxQbX","https://ap.wps.com/l/cbCair8JzoEyxQbX","pdf",2189892,1,5,"English","en",105,"# I. Introduction\n# II. Architecture\n## Patient services scheme\n## Data services scheme\n# III. Data Extraction and Modelling","[{\"question\":\"Why is privacy-preserving machine learning needed for EHR systems?\",\"answer\":\"EHRs contain highly sensitive patient information, so machine learning workflows must reduce risks from attacks such as data breaches and unauthorized access. Privacy-preserving methods also support compliance with HIPAA and GDPR.\"},{\"question\":\"How does the proposed architecture handle patient consent and policy enforcement?\",\"answer\":\"The patient services subsystem lets patients express consent for privacy policies and manage access rights. It uses logging with hash chains and a verification service to demonstrate that agreed-upon policies were enforced.\"},{\"question\":\"What roles do federated learning and differential privacy play in protecting patient data?\",\"answer\":\"Federated learning enables collaborative training and evaluation without exposing raw patient records across providers. Differential privacy further limits information leakage from model training outcomes.\"}]","Privacy-Preserving Machine Learning for Electronic Health Records using Federated Learning and Differential Privacy - Slides | PDF",1785819825,13,{"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},"privacy-preserving-machine-learning-for-electronic-health-records-using-federated-learning-and-differential-privacy-slides","",{"@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/privacy-preserving-machine-learning-for-electronic-health-records-using-federated-learning-and-differential-privacy-slides/124013/",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","2026-08-04",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 is privacy-preserving machine learning needed for EHR systems?","Question",{"text":75,"@type":76},"EHRs contain highly sensitive patient information, so machine learning workflows must reduce risks from attacks such as data breaches and unauthorized access. Privacy-preserving methods also support compliance with HIPAA and GDPR.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed architecture handle patient consent and policy enforcement?",{"text":80,"@type":76},"The patient services subsystem lets patients express consent for privacy policies and manage access rights. It uses logging with hash chains and a verification service to demonstrate that agreed-upon policies were enforced.",{"name":82,"@type":73,"acceptedAnswer":83},"What roles do federated learning and differential privacy play in protecting patient data?",{"text":84,"@type":76},"Federated learning enables collaborative training and evaluation without exposing raw patient records across providers. Differential privacy further limits information leakage from model training outcomes.","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},[93,97,101,105,109,114,117,122,127,130,134],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":115,"slug":116},40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",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"]