MSGene: Derivation and validation of a multistate model for lifetime risk of coronary artery disease using genetic risk and the electronic health record

Current coronary artery disease (CAD) is the leading cause of death among adults worldwide. However, current lifetime risk scores perform poorly with limited generalizability precluding optimal prevention. We designed a novel multistate model (MSGene) that employs generalized linear models to estimate age-specific transitions across cardiometabolic states with a CAD polygenic risk score to compute lifetime risk. We analyzed 480,638 UK Biobank (UKB) participants from 1940 to 2021 and compared with the existing 30-year Framingham risk score (FRS30RC). MSGene versus FRS30RC improved discrimination (C-index 0.71 vs 0.66), age of high-risk detection (C-index 0.73 vs 0.52), and calibration (RMSE 1.1% vs 10.9%), with external validation. We refine estimates of lifetime absolute risk reduction for CAD from earlier statin initiation based on MSGene. Our findings underscore the potential public health value of a novel multistate model for accurate lifetime estimation of CAD risk using widely available clinical risk factors and increasingly available genetics. ### Competing Interest Statement During the course of the project, M.W.Y. became a full-time employee of GSK. A.C.F. is co-founder of Goodpath. PTE reports personal fees from Bayer AG, Novartis, and MyoKardia. GP holds equity in Phaeno Biotechnologies, is on the SAB of RealmIDX and currently consults for Delphi Diagnostics. P.N. reports research grants from Allelica, Apple, Amgen,Boston Scientific, Genentech / Roche, and Novartis, personal fees from Allelica, Apple, AstraZeneca, Blackstone Life Sciences, Foresite Labs, Genentech / Roche, GV, HeartFlow, Magnet Biomedicine, and Novartis, scientific advisory board membership of Esperion Therapeutics, Preciseli, and TenSixteen Bio, scientific co-founder of TenSixteen Bio, equity in MyOme, Preciseli, and TenSixteen Bio, and spousal employment at Vertex Pharmaceuticals, all unrelated to the present work. The remaining authors have nothing to disclose.   ### Funding Statement SOURCES OF FUNDING S.M.U. is supported by T32HG010464 from the National Human Genome Research Institute. S.K is supported by the NIH (K23HL169839) and the American Heart Association (23CDA1050571). S.J.C. is supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health and Welfare, Republic of Korea (grant no.: HI19C1330). A.C.F is supported by grants 1K08HL161448 and R01HL164629 from the National Heart, Lung, and Blood Institute. P.T.E reported receiving grants from the NIH (1RO1HL092577, 1R01HL157635, and 5R01HL139731), the American Heart Association Strategically Focused Research Networks (18SFRN34110082), the European Union (MAESTRIA 965286), Bayer AG (to the Broad Institute), IBM Health (to the Broad Institute), Bristol Myers Squibb (to Massachusetts General Hospital), and Pfizer (to Massachusetts General Hospital). A.G. is supported by National Institutes of Health (NIH) grant nos R01CA227237, R01CA244569 and R21HG010748, and awards from the Claudia Adams Barr Foundation, Louis B. Mayer Foundation, Doris Duke Charitable Foundation, Emerson Collective and Phi Beta Psi Sorority. P.N. is supported by grants R01HL1427, R01HL148565, and R01HL148050 from the National Heart, Lung, and Blood Institute, and grant 1U01HG011719 from the National Human Genome Research Institute. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Informed consent was obtained from all participants, and secondary data analyses of dbGAP based FOS and UKB were approved by the Mass General Brigham Institutional Review Board applications 2016P002395 and 2021P002228. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All code for running the MSGene model is available at https://github.com/surbut/MSGene. Vignettes for running the analyses are available at https://surbut.github.io/MSGene/vignette.html and https://surbut.github.io/MSGene/usingMarginal.html. Shiny app for calculating interval risk is available at https://surbut.shinyapps.io/risk/. UK Biobank data is available upon application through the UKB Showcase https://www.ukbiobank.ac.uk. Framingham Offspring Data is available through dbGap access by investigator application.