[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123113-en":3,"doc-seo-123113-105":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},123113,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores","Polygenic risk scores (PRS) use genetic markers weighted by effect size, yet they under-capture heritability and show limited generalizability for late-onset Alzheimer’s disease (LOAD). This study develops a paragenic risk score that augments single-marker PRS with epistatic interaction features and machine learning to improve LOAD risk prediction. Using an evolutionary-algorithm strategy informed by shared pathway information, the work evaluates an ensemble of non-linear models against multiple PRS baselines on matched datasets.","UC Davis  \nUC Davis Previously Published Works  \nTitle  \nEpistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores  \nPermalink  \n[https://escholarship.org/uc/item/0z65p1vw](https://escholarship.org/uc/item/0z65p1vw)  \nJournal  \nJournal of Alzheimer's Disease, 99(4)  \nISSN  \n1387-2877  \nAuthors  \nHermes, Stephen  \nCady, Janet Armentrout, Stevenet al.  \nPublication Date  \n2024-06-11  \nDOI  \n10.3233/jad-230236  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nAuthor Manuscr ipt Author Manuscr ipt Author Manuscr ipt Author Manuscript  \n\n|  | HHS Public Access\u003Cbr>Author manuscript\u003Cbr>J Alzheimers Dis. Author manuscript; available in PMC 2024 July 29. |\n| --- | --- |\n\nPublished in final edited form as:  \nJ Alzheimers Dis. 2024 ; 99(4): 1425–1440. doi:10.3233/JAD-230236 .  \nEpistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores  \nStephen Hermesa, Janet Cadya, Steven Armentrouta, James O’Connora, Sarah Carlson Holdawaya, Carlos Cruchagab,c, Thomas Wingod,e,f, Ellen McRae Greytaka,* , Alzheimer’s Disease Neuroimaging Initiative1  \naParabon NanoLabs, Inc. , Reston, VA, USA  \nb Department of Psychiatry, Washington University, St. Louis, MO, USA  \nc Hope Center Program on Protein Aggregation and Neurodegeneration, Washington University, St. Louis, MO, USA  \ndGoizueta Alzheimer’s Disease Center, Emory University School of Medicine, Atlanta, GA, USA e Department of Neurology, Emory University School of Medicine, Atlanta, GA, USAfDepartment of Human Genetics, Emory University School of Medicine, Atlanta, GA, USA  \nAbstract  \nBackground: Polygenic risk scores (PRS) are linear combinations of genetic markers weighted by effect size that are commonly used to predict disease risk. For complex heritable diseases such as late-onset Alzheimer’s disease (LOAD), PRS models fail to capture much of the heritability.  \nAdditionally, PRS models are highly dependent on the population structure of the data on which effect sizes are assessed and have poor generalizability to new data.  \nObjective: The goal of this study is to construct a paragenic risk score that, in addition to single genetic marker data used in PRS, incorporates epistatic interaction features and machine learning methods to predict risk for LOAD.  \nCDresponta useddience ton prepa:rEatlinnMcRaof thiseaGrrticyetakwe,rPeabonbtaineNdnoLromabs, Inthe Al.h, Reseimorn’s, VADise, USAase N.eellen@uroimaparagingbonInit.comiative. (ADNI) database ([http://adni.loni.usc.edu](http://adni.loni.usc.edu)). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing ofADNI investigators can be found at: [http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf](http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf).  \nAUTHOR CONTRIBUTIONS  \nStephen Hermes (Formal analysis; Investigation; Methodology; Validation; Visualization; Writing – original draft; Writing – review & editing); Janet Cady (Conceptualization; Formal analysis; Investigation; Writing – review & editing); Steven Armentrout (Funding acquisition; Methodology; Project administration; Resources; Supervision; Writing – review & editing); James O’Connor  \n(Methodology; Project administration; Resources; Software); Sarah Holdaway (Resources; Software); Carlos Cruchaga (Data curation; Methodology; Writing – review & editing); Thomas Wingo (Data curation; Methodology; Writing – review & editing); Ellen Greytak (Conceptualization; Data curation; Formal analysis; Funding acquisition; Investigation; Methodology; Project administration; Supervision; Visualization; Writing – original draft; Writing – review & editing) .  \nCONFLICT OF INTEREST  \nSH, JC, SA, JO, SCH, and EG a","cbCaiixzWbnv6kFf","https://ap.wps.com/l/cbCaiixzWbnv6kFf","pdf",1646527,1,28,"English","en",105,"## Abstract\n## Methods\n## Results\n## Conclusions\n## Keywords\n## Introduction","[{\"question\":\"Why do conventional polygenic risk scores (PRS) perform poorly for late-onset Alzheimer’s disease?\",\"answer\":\"They fail to capture much of the heritability and depend strongly on population structure, limiting generalizability to new data.\"},{\"question\":\"What does the study’s paragenic risk score add compared with PRS?\",\"answer\":\"It incorporates epistatic interaction features between SNP loci and uses an ensemble of non-linear machine learning models rather than a single linear model.\"},{\"question\":\"How does the paragenic model perform relative to PRS models?\",\"answer\":\"It is significantly more accurate under 10-fold cross-validation (reported AUC 83%) and remains more accurate on an independent holdout dataset, including within APOE genotype strata.\"}]","Epistatic Features and Machine Learning Improve Alzheimer’s Disease Risk Prediction Over Polygenic Risk Scores | PDF",1785814704,71,{"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},"epistatic-features-and-machine-learning-improve-alzheimers-disease-risk-prediction-over-polygenic-risk-scores","",{"@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/epistatic-features-and-machine-learning-improve-alzheimers-disease-risk-prediction-over-polygenic-risk-scores/123113/",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 do conventional polygenic risk scores (PRS) perform poorly for late-onset Alzheimer’s disease?","Question",{"text":75,"@type":76},"They fail to capture much of the heritability and depend strongly on population structure, limiting generalizability to new data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the study’s paragenic risk score add compared with PRS?",{"text":80,"@type":76},"It incorporates epistatic interaction features between SNP loci and uses an ensemble of non-linear machine learning models rather than a single linear model.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the paragenic model perform relative to PRS models?",{"text":84,"@type":76},"It is significantly more accurate under 10-fold cross-validation (reported AUC 83%) and remains more accurate on an independent holdout dataset, including within APOE genotype strata.","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"]