--- title: "ASVD risk prediction in multi-ethnic population. | Sutter Health" description: "Machine learning models achieved comparable/improved performance compared to the pooled cohort equations & allowed risk discrimination in a larger group of pts." url: "https://www.sutterhealth.org/research/publications/asvd-risk-prediction-in-multi-ethnic-population-1055312841" --- 1. [Home](https://www.sutterhealth.org/) / 2. [Research](https://www.sutterhealth.org/research) / 3. [Research publications](https://www.sutterhealth.org/research/publications) / 4. ASVD risk prediction in multi-ethnic population. # Machine learning and atherosclerotic cardiovascular disease risk prediction in a multi-ethnic population. Ward A, Sarraju A, Chung S, Li J, Harrington R, Heidenreich P, Palaniappan L, Scheinker D, & Rodriguez F. _NPJ Digit Med. 3:125. doi: 10.1038/s41746-020-00331-1. eCollection 2020._ 2020-09-23 ## Abstract The pooled cohort equations (PCE) predict atherosclerotic cardiovascular disease (ASCVD) risk in patients with characteristics within prespecified ranges and has uncertain performance among Asians or Hispanics. It is unknown if machine learning (ML) models can improve ASCVD risk prediction across broader diverse, real-world populations. We developed ML models for ASCVD risk prediction for multi-ethnic patients using an electronic health record (EHR) database from Northern California. Our cohort included patients aged 18 years or older with no prior CVD and not on statins at baseline (n = 262,923), stratified by PCE-eligible (n = 131,721) or PCE-ineligible patients based on missing or out-of-range variables. We trained ML models \[logistic regression with L2 penalty and L1 lasso penalty, random forest, gradient boosting machine (GBM), extreme gradient boosting\] and determined 5-year ASCVD risk prediction, including with and without incorporation of additional EHR variables, and in Asian and Hispanic subgroups. A total of 4309 patients had ASCVD events, with 2077 in PCE-ineligible patients. GBM performance in the full cohort, including PCE-ineligible patients (area under receiver-operating characteristic curve (AUC) 0.835, 95% confidence interval (CI): 0.825-0.846), was significantly better than that of the PCE in the PCE-eligible cohort (AUC 0.775, 95% CI: 0.755-0.794). Among patients aged 40-79, GBM performed similarly before (AUC 0.784, 95% CI: 0.759-0.808) and after (AUC 0.790, 95% CI: 0.765-0.814) incorporating additional EHR data. Overall, ML models achieved comparable or improved performance compared to the PCE while allowing risk discrimination in a larger group of patients including PCE-ineligible patients. EHR-trained ML models may help bridge important gaps in ASCVD risk prediction. [PubMed abstract](https://pubmed.ncbi.nlm.nih.gov/33043149/) ![Jiang Li, Ph.D., MPH](https://dyn.mktgcdn.com/p/H4OFJqNxBzDqkSWaIqDBiZgqIsHNsHLWdLuMd9IlNx0/fit=crop,gravity=auto,dpr=2,width=188,height=250,quality=100) Jiang Li, Ph.D., MPH Principal investigator [View profile](https://www.sutterhealth.org/research/investigators/jiang-li-phd-mph-1049681008) ## Research topics - [Cardiovascular Diseases](https://www.sutterhealth.org/research-search-results?query=%22%5C%22Cardiovascular+Diseases%5C%22%22) - [Medical Informatics](https://www.sutterhealth.org/research-search-results?query=%22%5C%22Medical+Informatics%5C%22%22) ## Related publications [View all publications](https://www.sutterhealth.org/research-search-results?verticalKey=research_publication) - Publication ### [Under diagnosis of hypertension using electronic health records.](https://www.sutterhealth.org/research/publications/under-diagnosis-of-hypertension-using-ehr-1055312667) Banerjee D, Chung S, Wong EC, Wang EJ, Stafford RS, Palaniappan LP. Am J Manag Care. 16(2):e35-42 2010 Feb 01 - Publication ### [Statin utilization and low-density lipoprotein cholesterol in statin-treated patients with atherosclerotic cardiovascular disease: trends from a community-based health care delivery system, 2002-2016.](https://www.sutterhealth.org/research/publications/statin-use-and-ldl-in-statin-treated-patients-with-ascvd-1055312752) Romanelli RJ, Ito MK, Karalis DG, Huang HC, Iorga SR, Kam IW, Thompson S, Azar KMJ. J Clin Lipidol. pii: S1933-2874(20)30068-4. doi: 10.1016/j.jacl.2020.03.006. \[Epub ahead of print\] 2020 Apr 10 - Publication ### [Heterogeneity of treatment and outcomes among Asians with coronary artery disease in the United States.](https://www.sutterhealth.org/research/publications/treatment-and-outcomes-among-asians-with-cad-in-us-1055312760) Manjunath L, Chung S, Li J, Shah H, Palaniappan L, Yong CM. J Am Heart Assoc. e014362. doi: 10.1161/JAHA.119.014362. \[Epub ahead of print\] 2020 May 11 - Publication ### [Shared decision making: using health information technology to integrate patient choice into primary care.](https://www.sutterhealth.org/research/publications/health-it-to-integrate-pt-choice-in-shared-decision-making-1055312702) Jones JB, Bruce CA, Shah NR, Taylor WF, Stewart WF. Transl Behav Med. 1(1):123-33. doi: 10.1007/s13142-011-0023-5. 2011 Mar 01 - Publication ### [The wired patient: patterns of electronic patient portal use among patients with cardiac disease or diabetes.](https://www.sutterhealth.org/research/publications/patterns-of-ehr-portal-use-in-pts-with-cvd-or-diabetes-1055312712) Jones JB, Weiner JP, Shah NR, Stewart WF. J Med Internet Res. 17(2):e42. doi: 10.2196/jmir.3157. 2015 Feb 20 [View all publications](https://www.sutterhealth.org/research-search-results?verticalKey=research_publication) ```json {"@context":"https://schema.org","@type":"MedicalOrganization","name":"Sutter Health","@id":"https://www.sutterhealth.org/#medicalorganization","url":"https://www.sutterhealth.org","logo":"https://www.sutterhealth.org/static/images/sutter-health-logo.svg","address":{"@type":"PostalAddress","streetAddress":"2200 River Plaza Drive","addressLocality":"Sacramento","addressRegion":"CA","postalCode":"95833","addressCountry":"US"},"areaServed":{"@type":"AdministrativeArea","name":"California"},"sameAs":["https://www.facebook.com/SutterHealth","https://www.instagram.com/sutterhealth/","https://x.com/SutterHealth","https://www.youtube.com/sutterhealth","https://www.linkedin.com/company/sutter-health","https://en.wikipedia.org/wiki/Sutter_Health"]} ``` ```json {"@context":"https://schema.org","@type":"BreadcrumbList","@id":"https://www.sutterhealth.org/research/publications/asvd-risk-prediction-in-multi-ethnic-population-1055312841#breadcrumblist","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://www.sutterhealth.org/"},{"@type":"ListItem","position":2,"name":"Research","item":"https://www.sutterhealth.org/research"},{"@type":"ListItem","position":3,"name":"Research publications","item":"https://www.sutterhealth.org/research/publications"},{"@type":"ListItem","position":4,"name":"ASVD risk prediction in multi-ethnic population."}]} ``` ```json {"@context":"https://schema.org","@type":"MedicalScholarlyArticle","@id":"https://www.sutterhealth.org/research/publications/asvd-risk-prediction-in-multi-ethnic-population-1055312841#medicalscholarlyarticle","name":"Machine learning and atherosclerotic cardiovascular disease risk prediction in a multi-ethnic population.","headline":"ASVD risk prediction in multi-ethnic population.","abstract":"The pooled cohort equations (PCE) predict atherosclerotic cardiovascular disease (ASCVD) risk in patients with characteristics within prespecified ranges and has uncertain performance among Asians or Hispanics. It is unknown if machine learning (ML) models can improve ASCVD risk prediction across broader diverse, real-world populations. We developed ML models for ASCVD risk prediction for multi-ethnic patients using an electronic health record (EHR) database from Northern California. Our cohort included patients aged 18 years or older with no prior CVD and not on statins at baseline (n = 262,923), stratified by PCE-eligible (n = 131,721) or PCE-ineligible patients based on missing or out-of-range variables. We trained ML models [logistic regression with L2 penalty and L1 lasso penalty, random forest, gradient boosting machine (GBM), extreme gradient boosting] and determined 5-year ASCVD risk prediction, including with and without incorporation of additional EHR variables, and in Asian and Hispanic subgroups. A total of 4309 patients had ASCVD events, with 2077 in PCE-ineligible patients. GBM performance in the full cohort, including PCE-ineligible patients (area under receiver-operating characteristic curve (AUC) 0.835, 95% confidence interval (CI): 0.825-0.846), was significantly better than that of the PCE in the PCE-eligible cohort (AUC 0.775, 95% CI: 0.755-0.794). Among patients aged 40-79, GBM performed similarly before (AUC 0.784, 95% CI: 0.759-0.808) and after (AUC 0.790, 95% CI: 0.765-0.814) incorporating additional EHR data. Overall, ML models achieved comparable or improved performance compared to the PCE while allowing risk discrimination in a larger group of patients including PCE-ineligible patients. EHR-trained ML models may help bridge important gaps in ASCVD risk prediction.","description":"Machine learning models achieved comparable/improved performance compared to the pooled cohort equations & allowed risk discrimination in a larger group of pts.","keywords":["Cardiovascular Diseases","Medical Informatics"],"datePublished":"2020-09-23","url":"https://www.sutterhealth.org/research/publications/asvd-risk-prediction-in-multi-ethnic-population-1055312841","inLanguage":"en-US","identifier":[{"@type":"PropertyValue","propertyID":"PMID","value":"33043149"},{"@type":"PropertyValue","propertyID":"DOI","value":"10.1038/s41746-020-00331-1"}],"sameAs":["https://pubmed.ncbi.nlm.nih.gov/33043149/","https://doi.org/10.1038/s41746-020-00331-1"],"isPartOf":{"@type":"Periodical","name":"NPJ Digit Med"},"author":[{"@type":"Person","name":"Ward A"},{"@type":"Person","name":"Sarraju A"},{"@type":"Person","name":"Chung S"},{"@type":"Person","@id":"https://www.sutterhealth.org/research/investigators/jiang-li-phd-mph-1049681008","name":"Li J","url":"https://www.sutterhealth.org/research/investigators/jiang-li-phd-mph-1049681008"},{"@type":"Person","name":"Harrington R"},{"@type":"Person","name":"Heidenreich P"},{"@type":"Person","name":"Palaniappan L"},{"@type":"Person","name":"Scheinker D"},{"@type":"Person","name":"Rodriguez F"}],"about":[{"@type":"DefinedTerm","name":"Cardiovascular Diseases","url":"https://www.sutterhealth.org/research-search-results?facets=%5B%7B%22i%22%3A%22c_researchTopics.name%22%2C%22v%22%3A%5B%22Cardiovascular+Diseases%22%5D%7D%5D&verticalKey=research_publication"},{"@type":"DefinedTerm","name":"Medical Informatics","url":"https://www.sutterhealth.org/research-search-results?facets=%5B%7B%22i%22%3A%22c_researchTopics.name%22%2C%22v%22%3A%5B%22Medical+Informatics%22%5D%7D%5D&verticalKey=research_publication"}],"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.sutterhealth.org/research/publications/asvd-risk-prediction-in-multi-ethnic-population-1055312841","breadcrumb":{"@id":"https://www.sutterhealth.org/research/publications/asvd-risk-prediction-in-multi-ethnic-population-1055312841#breadcrumblist"}}} ```