1
|
Hrytsenko Y, Shea B, Elgart M, Kurniansyah N, Lyons G, Morrison AC, Carson AP, Haring B, Mitchell BD, Psaty BM, Jaeger BC, Gu CC, Kooperberg C, Levy D, Lloyd-Jones D, Choi E, Brody JA, Smith JA, Rotter JI, Moll M, Fornage M, Simon N, Castaldi P, Casanova R, Chung RH, Kaplan R, Loos RJF, Kardia SLR, Rich SS, Redline S, Kelly T, O'Connor T, Zhao W, Kim W, Guo X, Ida Chen YD, Sofer T. Machine learning models for predicting blood pressure phenotypes by combining multiple polygenic risk scores. Sci Rep 2024; 14:12436. [PMID: 38816422 PMCID: PMC11139858 DOI: 10.1038/s41598-024-62945-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Accepted: 05/22/2024] [Indexed: 06/01/2024] Open
Abstract
We construct non-linear machine learning (ML) prediction models for systolic and diastolic blood pressure (SBP, DBP) using demographic and clinical variables and polygenic risk scores (PRSs). We developed a two-model ensemble, consisting of a baseline model, where prediction is based on demographic and clinical variables only, and a genetic model, where we also include PRSs. We evaluate the use of a linear versus a non-linear model at both the baseline and the genetic model levels and assess the improvement in performance when incorporating multiple PRSs. We report the ensemble model's performance as percentage variance explained (PVE) on a held-out test dataset. A non-linear baseline model improved the PVEs from 28.1 to 30.1% (SBP) and 14.3% to 17.4% (DBP) compared with a linear baseline model. Including seven PRSs in the genetic model computed based on the largest available GWAS of SBP/DBP improved the genetic model PVE from 4.8 to 5.1% (SBP) and 4.7 to 5% (DBP) compared to using a single PRS. Adding additional 14 PRSs computed based on two independent GWASs further increased the genetic model PVE to 6.3% (SBP) and 5.7% (DBP). PVE differed across self-reported race/ethnicity groups, with primarily all non-White groups benefitting from the inclusion of additional PRSs. In summary, non-linear ML models improves BP prediction in models incorporating diverse populations.
Collapse
Affiliation(s)
- Yana Hrytsenko
- Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- CardioVascular Institute (CVI), Beth Israel Deaconess Medical Center, Boston, MA, USA
| | - Benjamin Shea
- CardioVascular Institute (CVI), Beth Israel Deaconess Medical Center, Boston, MA, USA
| | - Michael Elgart
- Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | | | - Genevieve Lyons
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Alanna C Morrison
- Department of Epidemiology, School of Public Health, Human Genetics Center, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - April P Carson
- Department of Medicine, University of Mississippi Medical Center, Jackson, MS, USA
| | - Bernhard Haring
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
- Department of Medicine III, Saarland University, Homburg, Saarland, Germany
| | - Braxton D Mitchell
- Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Bruce M Psaty
- Department of Medicine, University of Washington, Seattle, WA, USA
- Department of Epidemiology, University of Washington, Seattle, WA, USA
- Cardiovascular Health Research Unit, University of Washington, Seattle, WA, USA
- Health Systems and Population Health, University of Washington, Seattle, WA, USA
| | - Byron C Jaeger
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| | - C Charles Gu
- The Center for Biostatistics and Data Science, Washington University, St. Louis, USA
| | - Charles Kooperberg
- Division of Public Health Sciences, Fred Hutchinson Cancer Center, Seattle, WA, USA
| | - Daniel Levy
- The Population Sciences Branch of the National Heart, Lung and Blood Institute, Bethesda, MD, USA
- The Framingham Heart Study, Framingham, MA, USA
| | - Donald Lloyd-Jones
- Department of Preventive Medicine, Northwestern University, Chicago, IL, USA
| | - Eunhee Choi
- Columbia Hypertension Laboratory, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA
| | - Jennifer A Brody
- Department of Medicine, University of Washington, Seattle, WA, USA
- Cardiovascular Health Research Unit, University of Washington, Seattle, WA, USA
| | - Jennifer A Smith
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI, USA
- Survey Research Center, Institute for Social Research, University of Michigan, Ann Arbor, MI, USA
| | - Jerome I Rotter
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Matthew Moll
- Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- VA Boston Healthcare System, West Roxbury, MA, USA
- Channing Division of Network Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, USA
| | - Myriam Fornage
- Department of Epidemiology, School of Public Health, Human Genetics Center, The University of Texas Health Science Center at Houston, Houston, TX, USA
- Brown Foundation Institute of Molecular Medicine, McGovern Medical School, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Noah Simon
- Department of Biostatistics, School of Public Health, University of Washington, Seattle, WA, USA
| | - Peter Castaldi
- Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Ramon Casanova
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| | - Ren-Hua Chung
- Division of Biostatistics and Bioinformatics, Institute of Population Health Sciences, National Health Research Institutes, Taipei City, Taiwan
| | - Robert Kaplan
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
- Division of Public Health Sciences, Fred Hutchinson Cancer Center, Seattle, WA, USA
| | - Ruth J F Loos
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Novo Nordisk Foundation Center for Basic Metabolic Research, Faculty for Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark
| | - Sharon L R Kardia
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI, USA
| | - Stephen S Rich
- Center for Public Health Genomics, University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Susan Redline
- Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- Division of Sleep and Circadian Disorders, Brigham and Women's Hospital, Boston, MA, USA
| | - Tanika Kelly
- Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA
| | - Timothy O'Connor
- Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
- Institute for Genome Sciences, University of Maryland School of Medicine, Baltimore, MD, USA
- Program in Health Equity and Population Health, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Wei Zhao
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI, USA
- Survey Research Center, Institute for Social Research, University of Michigan, Ann Arbor, MI, USA
| | - Wonji Kim
- Channing Division of Network Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, USA
| | - Xiuqing Guo
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Yii-Der Ida Chen
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Tamar Sofer
- Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA.
- Department of Medicine, Harvard Medical School, Boston, MA, USA.
- CardioVascular Institute (CVI), Beth Israel Deaconess Medical Center, Boston, MA, USA.
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
- Center for Life Sciences CLS-934, 3 Blackfan St., Boston, MA, 02115, USA.
| |
Collapse
|
2
|
Schjerven FE, Lindseth F, Steinsland I. Prognostic risk models for incident hypertension: A PRISMA systematic review and meta-analysis. PLoS One 2024; 19:e0294148. [PMID: 38466745 PMCID: PMC10927109 DOI: 10.1371/journal.pone.0294148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Accepted: 10/26/2023] [Indexed: 03/13/2024] Open
Abstract
OBJECTIVE Our goal was to review the available literature on prognostic risk prediction for incident hypertension, synthesize performance, and provide suggestions for future work on the topic. METHODS A systematic search on PUBMED and Web of Science databases was conducted for studies on prognostic risk prediction models for incident hypertension in generally healthy individuals. Study-quality was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST) checklist. Three-level meta-analyses were used to obtain pooled AUC/C-statistic estimates. Heterogeneity was explored using study and cohort characteristics in meta-regressions. RESULTS From 5090 hits, we found 53 eligible studies, and included 47 in meta-analyses. Only four studies were assessed to have results with low risk of bias. Few models had been externally validated, with only the Framingham risk model validated more than thrice. The pooled AUC/C-statistics were 0.82 (0.77-0.86) for machine learning models and 0.78 (0.76-0.80) for traditional models, with high heterogeneity in both groups (I2 > 99%). Intra-class correlations within studies were 60% and 90%, respectively. Follow-up time (P = 0.0405) was significant for ML models and age (P = 0.0271) for traditional models in explaining heterogeneity. Validations of the Framingham risk model had high heterogeneity (I2 > 99%). CONCLUSION Overall, the quality of included studies was assessed as poor. AUC/C-statistic were mostly acceptable or good, and higher for ML models than traditional models. High heterogeneity implies large variability in the performance of new risk models. Further, large heterogeneity in validations of the Framingham risk model indicate variability in model performance on new populations. To enable researchers to assess hypertension risk models, we encourage adherence to existing guidelines for reporting and developing risk models, specifically reporting appropriate performance measures. Further, we recommend a stronger focus on validation of models by considering reasonable baseline models and performing external validations of existing models. Hence, developed risk models must be made available for external researchers.
Collapse
Affiliation(s)
- Filip Emil Schjerven
- Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
| | - Frank Lindseth
- Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
| | - Ingelin Steinsland
- Department of Mathematical Sciences, Norwegian University of Science and Technology, Trondheim, Norway
| |
Collapse
|
3
|
Schjerven FE, Ingeström EML, Steinsland I, Lindseth F. Development of risk models of incident hypertension using machine learning on the HUNT study data. Sci Rep 2024; 14:5609. [PMID: 38454041 PMCID: PMC10920790 DOI: 10.1038/s41598-024-56170-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2023] [Accepted: 03/03/2024] [Indexed: 03/09/2024] Open
Abstract
In this study, we aimed to create an 11-year hypertension risk prediction model using data from the Trøndelag Health (HUNT) Study in Norway, involving 17 852 individuals (20-85 years; 38% male; 24% incidence rate) with blood pressure (BP) below the hypertension threshold at baseline (1995-1997). We assessed 18 clinical, behavioral, and socioeconomic features, employing machine learning models such as eXtreme Gradient Boosting (XGBoost), Elastic regression, K-Nearest Neighbor, Support Vector Machines (SVM) and Random Forest. For comparison, we used logistic regression and a decision rule as reference models and validated six external models, with focus on the Framingham risk model. The top-performing models consistently included XGBoost, Elastic regression and SVM. These models efficiently identified hypertension risk, even among individuals with optimal baseline BP (< 120/80 mmHg), although improvement over reference models was modest. The recalibrated Framingham risk model outperformed the reference models, approaching the best-performing ML models. Important features included age, systolic and diastolic BP, body mass index, height, and family history of hypertension. In conclusion, our study demonstrated that linear effects sufficed for a well-performing model. The best models efficiently predicted hypertension risk, even among those with optimal or normal baseline BP, using few features. The recalibrated Framingham risk model proved effective in our cohort.
Collapse
Affiliation(s)
- Filip Emil Schjerven
- Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway.
| | - Emma Maria Lovisa Ingeström
- Department of Circulation and Medical Imaging, Norwegian University of Science and Technology, Trondheim, Norway
| | - Ingelin Steinsland
- Department of Mathematical Sciences, Norwegian University of Science and Technology, Trondheim, Norway
| | - Frank Lindseth
- Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway
| |
Collapse
|
4
|
Hrytsenko Y, Shea B, Elgart M, Kurniansyah N, Lyons G, Morrison AC, Carson AP, Haring B, Mitchel BD, Psaty BM, Jaeger BC, Gu CC, Kooperberg C, Levy D, Lloyd-Jones D, Choi E, Brody JA, Smith JA, Rotter JI, Moll M, Fornage M, Simon N, Castaldi P, Casanova R, Chung RH, Kaplan R, Loos RJ, Kardia SLR, Rich SS, Redline S, Kelly T, O’Connor T, Zhao W, Kim W, Guo X, Der Ida Chen Y, Sofer T. Machine learning models for blood pressure phenotypes combining multiple polygenic risk scores. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.12.13.23299909. [PMID: 38168328 PMCID: PMC10760279 DOI: 10.1101/2023.12.13.23299909] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/05/2024]
Abstract
We construct non-linear machine learning (ML) prediction models for systolic and diastolic blood pressure (SBP, DBP) using demographic and clinical variables and polygenic risk scores (PRSs). We developed a two-model ensemble, consisting of a baseline model, where prediction is based on demographic and clinical variables only, and a genetic model, where we also include PRSs. We evaluate the use of a linear versus a non-linear model at both the baseline and the genetic model levels and assess the improvement in performance when incorporating multiple PRSs. We report the ensemble model's performance as percentage variance explained (PVE) on a held-out test dataset. A non-linear baseline model improved the PVEs from 28.1% to 30.1% (SBP) and 14.3% to 17.4% (DBP) compared with a linear baseline model. Including seven PRSs in the genetic model computed based on the largest available GWAS of SBP/DBP improved the genetic model PVE from 4.8% to 5.1% (SBP) and 4.7% to 5% (DBP) compared to using a single PRS. Adding additional 14 PRSs computed based on two independent GWASs further increased the genetic model PVE to 6.3% (SBP) and 5.7% (DBP). PVE differed across self-reported race/ethnicity groups, with primarily all non-White groups benefitting from the inclusion of additional PRSs.
Collapse
Affiliation(s)
- Yana Hrytsenko
- Department of Medicine, Brigham and Women’s Hospital, Boston, MA
- Department of Medicine, Harvard Medical School, Boston, MA
- CardioVascular Institute (CVI), Beth Israel Deaconess Medical Center, Boston, MA
| | - Benjamin Shea
- CardioVascular Institute (CVI), Beth Israel Deaconess Medical Center, Boston, MA
| | - Michael Elgart
- Department of Medicine, Brigham and Women’s Hospital, Boston, MA
- Department of Medicine, Harvard Medical School, Boston, MA
| | | | - Genevieve Lyons
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA
| | - Alanna C. Morrison
- Human Genetics Center, Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - April P. Carson
- Department of Medicine, University of Mississippi Medical Center, Jackson, MS, USA
| | - Bernhard Haring
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
- Department of Medicine III, Saarland University, Homburg, Saarland, Germany
| | - Braxton D. Mitchel
- Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Bruce M. Psaty
- Department of Medicine, University of Washington, Seattle, WA, USA
- Department of Epidemiology, University of Washington, Seattle, WA, USA
- Cardiovascular Health Research Unit, University of Washington, Seattle, WA, USA
- Health Systems and Population Health, University of Washington, Seattle, WA, USA
| | - Byron C. Jaeger
- Department of Biostatistics and Data Science, Wake Forest University School of Medicine, Winston-Salem, NC, USA
| | - C Charles Gu
- The Center for Biostatistics and Data Science, Washington University, St. Louis, USA
| | - Charles Kooperberg
- Division of Public Health Sciences, Fred Hutchinson Cancer Center, Seattle, WA, USA
| | - Daniel Levy
- The Population Sciences Branch of the National Heart, Lung and Blood Institute, Bethesda, MD, USA
- The Framingham Heart Study, Framingham, MA, USA
| | - Donald Lloyd-Jones
- Department of Preventive Medicine, Northwestern University, Chicago, IL, USA
| | - Eunhee Choi
- Columbia Hypertension Laboratory, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA
| | - Jennifer A Brody
- Department of Medicine, University of Washington, Seattle, WA, USA
- Cardiovascular Health Research Unit, University of Washington, Seattle, WA, USA
| | - Jennifer A Smith
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI, USA
- Survey Research Center, Institute for Social Research, University of Michigan, Ann Arbor, MI, USA
| | - Jerome I. Rotter
- The Institute for Translational Genomics and Population Sciences, Department of Pediatrics, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Matthew Moll
- Department of Medicine, Brigham and Women’s Hospital, Boston, MA
- Department of Medicine, Harvard Medical School, Boston, MA
- VA Boston Healthcare System, West Roxbury, MA, USA
| | - Myriam Fornage
- Human Genetics Center, Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA
- Brown Foundation Institute of Molecular Medicine, McGovern Medical School, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Noah Simon
- Department of Biostatistics, School of Public Health, University of Washington, Seattle, WA
| | - Peter Castaldi
- Department of Medicine, Brigham and Women’s Hospital, Boston, MA
- Department of Medicine, Harvard Medical School, Boston, MA
| | - Ramon Casanova
- Health Systems and Population Health, University of Washington, Seattle, WA, USA
| | - Ren-Hua Chung
- Division of Biostatistics and Bioinformatics, Institute of Population Health Sciences, National Health Research Institutes, Taipei City, Taiwan
| | - Robert Kaplan
- Division of Public Health Sciences, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Ruth J.F. Loos
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Novo Nordisk Foundation Center for Basic Metabolic Research, Faculty for Health and Medical Sciences, University of Copenhagen, Denmark, DK
| | - Sharon L. R. Kardia
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI, USA
| | - Stephen S. Rich
- Center for Public Health Genomics, University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Susan Redline
- Department of Medicine, Harvard Medical School, Boston, MA
- Division of Sleep and Circadian Disorders, Brigham and Women’s Hospital, Boston, MA, USA
| | - Tanika Kelly
- Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA
| | - Timothy O’Connor
- Department of Medicine III, Saarland University, Homburg, Saarland, Germany
| | - Wei Zhao
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI, USA
- Survey Research Center, Institute for Social Research, University of Michigan, Ann Arbor, MI, USA
| | - Wonji Kim
- Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital
| | - Xiuqing Guo
- The Institute for Translational Genomics and Population Sciences, Department of Pediatrics, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Yii Der Ida Chen
- The Institute for Translational Genomics and Population Sciences, Department of Pediatrics, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | | | - Tamar Sofer
- Department of Medicine, Brigham and Women’s Hospital, Boston, MA
- Department of Medicine, Harvard Medical School, Boston, MA
- CardioVascular Institute (CVI), Beth Israel Deaconess Medical Center, Boston, MA
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA
| |
Collapse
|
5
|
Kurniansyah N, Goodman MO, Khan AT, Wang J, Feofanova E, Bis JC, Wiggins KL, Huffman JE, Kelly T, Elfassy T, Guo X, Palmas W, Lin HJ, Hwang SJ, Gao Y, Young K, Kinney GL, Smith JA, Yu B, Liu S, Wassertheil-Smoller S, Manson JE, Zhu X, Chen YDI, Lee IT, Gu CC, Lloyd-Jones DM, Zöllner S, Fornage M, Kooperberg C, Correa A, Psaty BM, Arnett DK, Isasi CR, Rich SS, Kaplan RC, Redline S, Mitchell BD, Franceschini N, Levy D, Rotter JI, Morrison AC, Sofer T. Evaluating the use of blood pressure polygenic risk scores across race/ethnic background groups. Nat Commun 2023; 14:3202. [PMID: 37268629 PMCID: PMC10238525 DOI: 10.1038/s41467-023-38990-9] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/21/2022] [Accepted: 05/24/2023] [Indexed: 06/04/2023] Open
Abstract
We assess performance and limitations of polygenic risk scores (PRSs) for multiple blood pressure (BP) phenotypes in diverse population groups. We compare "clumping-and-thresholding" (PRSice2) and LD-based (LDPred2) methods to construct PRSs from each of multiple GWAS, as well as multi-PRS approaches that sum PRSs with and without weights, including PRS-CSx. We use datasets from the MGB Biobank, TOPMed study, UK biobank, and from All of Us to train, assess, and validate PRSs in groups defined by self-reported race/ethnic background (Asian, Black, Hispanic/Latino, and White). For both SBP and DBP, the PRS-CSx based PRS, constructed as a weighted sum of PRSs developed from multiple independent GWAS, perform best across all race/ethnic backgrounds. Stratified analysis in All of Us shows that PRSs are better predictive of BP in females compared to males, individuals without obesity, and middle-aged (40-60 years) compared to older and younger individuals.
Collapse
Affiliation(s)
- Nuzulul Kurniansyah
- Division of Sleep and Circadian Disorders, Brigham and Women's Hospital, Boston, MA, USA
| | - Matthew O Goodman
- Division of Sleep and Circadian Disorders, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Brigham and Women's Hospital, Boston, MA, USA
| | - Alyna T Khan
- Department of Biostatistics, University of Washington, Seattle, WA, USA
| | - Jiongming Wang
- Department of Biostatistics, University of Michigan, Ann Arbor, MI, USA
| | - Elena Feofanova
- Human Genetics Center, Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Joshua C Bis
- Cardiovascular Health Research Unit, Department of Medicine, University of Washington, Seattle, WA, USA
| | - Kerri L Wiggins
- Cardiovascular Health Research Unit, Department of Medicine, University of Washington, Seattle, WA, USA
| | - Jennifer E Huffman
- Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, USA
| | - Tanika Kelly
- Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA
| | - Tali Elfassy
- Department of Public Health Sciences, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Xiuqing Guo
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Walter Palmas
- Department of Medicine, Columbia University Medical Center, New York, NY, USA
| | - Henry J Lin
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Shih-Jen Hwang
- The Population Sciences Branch of the National Heart, Lung and Blood Institute, Bethesda, MD, USA
- The Framingham Heart Study, Framingham, MA, USA
| | - Yan Gao
- The Jackson Heart Study, University of Mississippi Medical Center, Jackson, MS, USA
| | - Kendra Young
- Department of Epidemiology, Colorado School of Public Health, Aurora, CO, USA
| | - Gregory L Kinney
- Department of Epidemiology, Colorado School of Public Health, Aurora, CO, USA
| | - Jennifer A Smith
- Department of Epidemiology, University of Michigan School of Public Health, Ann Arbor, MI, USA
| | - Bing Yu
- Human Genetics Center, Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Simin Liu
- Center for Global Cardiometabolic Health, Department of Epidemiology, Brown University, Providence, RI, USA
- Department of Medicine, Brown University, Providence, RI, USA
| | - Sylvia Wassertheil-Smoller
- Department of Pediatrics, Albert Einstein College of Medicine, Bronx, NY, USA
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - JoAnn E Manson
- Department of Medicine, Harvard Medical School, Brigham and Women's Hospital, Boston, MA, USA
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Xiaofeng Zhu
- Department of Population and Quantitative Health Sciences, School of Medicine, Case Western Reserve University, Cleveland, OH, USA
| | - Yii-Der Ida Chen
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - I-Te Lee
- Division of Endocrinology and Metabolism, Department of Internal Medicine, Taichung Veterans General Hospital, Taichung City, 40705, Taiwan
- School of Medicine, National Yang Ming Chiao Tung University, Taipei, 11221, Taiwan
| | - C Charles Gu
- Division of Biostatistics, Washington University School of Medicine, St. Louis, MO, USA
| | | | - Sebastian Zöllner
- Department of Biostatistics, University of Michigan, Ann Arbor, MI, USA
- Department of Psychiatry, University of Michigan, Ann Arbor, MI, USA
| | - Myriam Fornage
- Human Genetics Center, Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA
- Brown Foundation Institute of Molecular Medicine, McGovern Medical School, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Charles Kooperberg
- Division of Public Health Sciences, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Adolfo Correa
- Departments of Medicine and Pediatrics, University of Mississippi Medical Center, Jackson, MS, USA
| | - Bruce M Psaty
- Department of Medicine, University of Washington, Seattle, WA, USA
- Department of Epidemiology, University of Washington, Seattle, WA, USA
- Cardiovascular Health Research Unit, University of Washington, Seattle, WA, USA
- Health Systems and Population Health, University of Washington, Seattle, WA, USA
| | - Donna K Arnett
- Office of the Provost, University of South Carolina, Columbia, SC, USA
| | - Carmen R Isasi
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
| | - Stephen S Rich
- Center for Public Health Genomics, University of Virginia School of Medicine, Charlottesville, VA, USA
| | - Robert C Kaplan
- Department of Epidemiology & Population Health, Albert Einstein College of Medicine, Bronx, NY, USA
- Division of Public Health Sciences, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Susan Redline
- Division of Sleep and Circadian Disorders, Brigham and Women's Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Brigham and Women's Hospital, Boston, MA, USA
| | - Braxton D Mitchell
- Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Nora Franceschini
- Department of Epidemiology, University of North Carolina, Chapel Hill, NC, USA
| | - Daniel Levy
- The Population Sciences Branch of the National Heart, Lung and Blood Institute, Bethesda, MD, USA
- The Framingham Heart Study, Framingham, MA, USA
| | - Jerome I Rotter
- Department of Pediatrics, The Institute for Translational Genomics and Population Sciences, The Lundquist Institute for Biomedical Innovation at Harbor-UCLA Medical Center, Torrance, CA, USA
| | - Alanna C Morrison
- Human Genetics Center, Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Tamar Sofer
- Division of Sleep and Circadian Disorders, Brigham and Women's Hospital, Boston, MA, USA.
- Department of Medicine, Harvard Medical School, Brigham and Women's Hospital, Boston, MA, USA.
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
- CardioVascular Institute, Beth Israel Deaconess Medical Center, Boston, MA, USA.
| |
Collapse
|
6
|
Kresoja KP, Unterhuber M, Wachter R, Thiele H, Lurz P. A cardiologist's guide to machine learning in cardiovascular disease prognosis prediction. Basic Res Cardiol 2023; 118:10. [PMID: 36939941 PMCID: PMC10027799 DOI: 10.1007/s00395-023-00982-7] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Revised: 02/21/2023] [Accepted: 02/26/2023] [Indexed: 03/21/2023]
Abstract
A modern-day physician is faced with a vast abundance of clinical and scientific data, by far surpassing the capabilities of the human mind. Until the last decade, advances in data availability have not been accompanied by analytical approaches. The advent of machine learning (ML) algorithms might improve the interpretation of complex data and should help to translate the near endless amount of data into clinical decision-making. ML has become part of our everyday practice and might even further change modern-day medicine. It is important to acknowledge the role of ML in prognosis prediction of cardiovascular disease. The present review aims on preparing the modern physician and researcher for the challenges that ML might bring, explaining basic concepts but also caveats that might arise when using these methods. Further, a brief overview of current established classical and emerging concepts of ML disease prediction in the fields of omics, imaging and basic science is presented.
Collapse
Affiliation(s)
- Karl-Patrik Kresoja
- Department of Internal Medicine/Cardiology, Heart Center Leipzig at University of Leipzig, Struempellstr. 39, 04289, Leipzig, Germany
- Leipzig Heart Institute, Leipzig Heart Science at Heart Center Leipzig, Leipzig, Germany
| | - Matthias Unterhuber
- Department of Internal Medicine/Cardiology, Heart Center Leipzig at University of Leipzig, Struempellstr. 39, 04289, Leipzig, Germany
- Leipzig Heart Institute, Leipzig Heart Science at Heart Center Leipzig, Leipzig, Germany
| | - Rolf Wachter
- Department of Cardiology, University Hospital Leipzig, Leipzig, Germany
- Clinic for Cardiology and Pneumology, University Medicine Göttingen, Göttingen, Germany
- German Cardiovascular Research Center (DZHK), Partner Site Göttingen, Göttingen, Germany
| | - Holger Thiele
- Department of Internal Medicine/Cardiology, Heart Center Leipzig at University of Leipzig, Struempellstr. 39, 04289, Leipzig, Germany.
- Leipzig Heart Institute, Leipzig Heart Science at Heart Center Leipzig, Leipzig, Germany.
| | - Philipp Lurz
- Department of Internal Medicine/Cardiology, Heart Center Leipzig at University of Leipzig, Struempellstr. 39, 04289, Leipzig, Germany.
- Leipzig Heart Institute, Leipzig Heart Science at Heart Center Leipzig, Leipzig, Germany.
| |
Collapse
|
7
|
Nurkkala J, Kauko A, FinnGen, Laivuori H, Saarela T, Tyrmi JS, Vaura F, Cheng S, Bello NA, Aittokallio J, Niiranen T. Associations of polygenic risk scores for preeclampsia and blood pressure with hypertensive disorders of pregnancy. J Hypertens 2023; 41:380-387. [PMID: 36947680 PMCID: PMC9894151 DOI: 10.1097/hjh.0000000000003336] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
BACKGROUND Preexisting hypertension increases risk for preeclampsia. We examined whether a generic blood pressure polygenic risk score (BP-PRS), compared with a preeclampsia-specific polygenic risk score (PE-PRS), could better predict hypertensive disorders of pregnancy. METHODS Our study sample included 141 298 genotyped FinnGen study participants with at least one childbirth and followed from 1969 to 2021. We calculated PRSs for SBP and preeclampsia using summary statistics for greater than 1.1 million single nucleotide polymorphisms. RESULTS We observed 8488 cases of gestational hypertension (GHT) and 6643 cases of preeclampsia. BP-PRS was associated with GHT [multivariable-adjusted hazard ratio for 1SD increase in PRS (hazard ratio 1.38; 95% CI 1.35-1.41)] and preeclampsia (1.26, 1.23-1.29), respectively. The PE-PRS was also associated with GHT (1.16; 1.14-1.19) and preeclampsia (1.21, 1.18-1.24), but with statistically more modest magnitudes of effect (P = 0.01). The model c-statistic for preeclampsia improved when PE-PRS was added to clinical risk factors (P = 4.6 × 10-15). Additional increment in the c-statistic was observed when BP-PRS was added to a model already including both clinical risk factors and PE-PRS (P = 1.1 × 10-14). CONCLUSION BP-PRS is strongly associated with hypertensive disorders of pregnancy. Our current observations suggest that the BP-PRS could capture the genetic architecture of preeclampsia better than the current PE-PRSs. These findings also emphasize the common pathways in the development of all BP disorders. The clinical utility of a BP-PRS for preeclampsia prediction warrants further investigation.
Collapse
Affiliation(s)
- Jouko Nurkkala
- Division of Perioperative Services, Intensive Care and Pain Medicine, Turku University Hospital
- Department of Anesthesiology and Intensive Care
| | - Anni Kauko
- Department of Internal Medicine, University of Turku, Turku
| | | | - Hannele Laivuori
- Department of Obstetrics and Gynecology, Tampere University Hospital
- Center for Child, Adolescent, and Maternal Health Research, Faculty of Medicine and Health Technology, Tampere University, Tampere
- Institute for Molecular Medicine Finland (FIMM), Helsinki Institute of Life Science, University of Helsinki
- Medical and Clinical Genetics, University of Helsinki and Helsinki University Hospital, Helsinki
| | - Tanja Saarela
- Department of Clinical Genetics, Kuopio University Hospital, Kuopio
| | - Jaakko S Tyrmi
- Faculty of Medicine and Health Technology, University of Tampere, Tampere, Finland
| | - Felix Vaura
- Department of Internal Medicine, University of Turku, Turku
| | - Susan Cheng
- Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
- Division of Cardiology Brigham and Women's Hospital, Boston, Massachusetts, USA
| | - Natalie A Bello
- Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, California
| | - Jenni Aittokallio
- Division of Perioperative Services, Intensive Care and Pain Medicine, Turku University Hospital
- Department of Anesthesiology and Intensive Care
| | - Teemu Niiranen
- Department of Internal Medicine, University of Turku, Turku
- Division of Medicine, Turku University Hospital
- Department of Public Health Solutions, Finnish Institute for Health and Welfare, Turku, Finland
| |
Collapse
|
8
|
O'Sullivan JW, Ashley EA, Elliott PM. Polygenic risk scores for the prediction of cardiometabolic disease. Eur Heart J 2023; 44:89-99. [PMID: 36478054 DOI: 10.1093/eurheartj/ehac648] [Citation(s) in RCA: 16] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/08/2021] [Revised: 08/28/2022] [Accepted: 10/27/2022] [Indexed: 12/12/2022] Open
Abstract
Cardiometabolic diseases contribute more to global morbidity and mortality than any other group of disorders. Polygenic risk scores (PRSs), the weighted summation of individually small-effect genetic variants, represent an advance in our ability to predict the development and complications of cardiometabolic diseases. This article reviews the evidence supporting the use of PRS in seven common cardiometabolic diseases: coronary artery disease (CAD), stroke, hypertension, heart failure and cardiomyopathies, obesity, atrial fibrillation (AF), and type 2 diabetes mellitus (T2DM). Data suggest that PRS for CAD, AF, and T2DM consistently improves prediction when incorporated into existing clinical risk tools. In other areas such as ischaemic stroke and hypertension, clinical application appears premature but emerging evidence suggests that the study of larger and more diverse populations coupled with more granular phenotyping will propel the translation of PRS into practical clinical prediction tools.
Collapse
Affiliation(s)
- Jack W O'Sullivan
- Stanford Center for Inherited Cardiovascular Disease, Stanford University School of Medicine, Stanford, CA, USA
- Division of Cardiology, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA
| | - Euan A Ashley
- Stanford Center for Inherited Cardiovascular Disease, Stanford University School of Medicine, Stanford, CA, USA
- Division of Cardiology, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA
| | - Perry M Elliott
- UCL Institute of Cardiovascular Science, Gower Street, London WC1E 6BT, UK
- St. Bartholomew's Hospital, W Smithfield, London EC1A 7BE, UK
| |
Collapse
|
9
|
Chen N, Fan F, Geng J, Yang Y, Gao Y, Jin H, Chu Q, Yu D, Wang Z, Shi J. Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms. Front Public Health 2022; 10:984621. [PMID: 36267989 PMCID: PMC9577109 DOI: 10.3389/fpubh.2022.984621] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2022] [Accepted: 09/12/2022] [Indexed: 01/25/2023] Open
Abstract
Objective The prevention of hypertension in primary care requires an effective and suitable hypertension risk assessment model. The aim of this study was to develop and compare the performances of three machine learning algorithms in predicting the risk of hypertension for residents in primary care in Shanghai, China. Methods A dataset of 40,261 subjects over the age of 35 years was extracted from Electronic Healthcare Records of 47 community health centers from 2017 to 2019 in the Pudong district of Shanghai. Embedded methods were applied for feature selection. Machine learning algorithms, XGBoost, random forest, and logistic regression analyses were adopted in the process of model construction. The performance of models was evaluated by calculating the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, accuracy and F1-score. Results The XGBoost model outperformed the other two models and achieved an AUC of 0.765 in the testing set. Twenty features were selected to construct the model, including age, diabetes status, urinary protein level, BMI, elderly health self-assessment, creatinine level, systolic blood pressure measured on the upper right arm, waist circumference, smoking status, low-density lipoprotein cholesterol level, high-density lipoprotein cholesterol level, frequency of drinking, glucose level, urea nitrogen level, total cholesterol level, diastolic blood pressure measured on the upper right arm, exercise frequency, time spent engaged in exercise, high salt consumption, and triglyceride level. Conclusions XGBoost outperformed random forest and logistic regression in predicting the risk of hypertension in primary care. The integration of this risk assessment model into primary care facilities may improve the prevention and management of hypertension in residents.
Collapse
Affiliation(s)
- Ning Chen
- School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Feng Fan
- School of Medicine, Tongji University, Shanghai, China
| | - Jinsong Geng
- School of Medicine, Nantong University, Nantong, China
| | - Yan Yang
- School of Economics and Management, Tongji University, Shanghai, China
| | - Ya Gao
- School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Hua Jin
- Department of General Practice, Yangpu Hospital, Tongji University School of Medicine, Shanghai, China,Shanghai General Practice and Community Health Development Research Center, Shanghai, China,Academic Department of General Practice, Tongji University School of Medicine, Shanghai, China,Clinical Research Center for General Practice, Tongji University, Shanghai, China
| | - Qiao Chu
- School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Dehua Yu
- Department of General Practice, Yangpu Hospital, Tongji University School of Medicine, Shanghai, China,Shanghai General Practice and Community Health Development Research Center, Shanghai, China,Academic Department of General Practice, Tongji University School of Medicine, Shanghai, China,Clinical Research Center for General Practice, Tongji University, Shanghai, China,*Correspondence: Dehua Yu
| | - Zhaoxin Wang
- The First Affiliated Hospital of Hainan Medical University, Haikou, China,Department of Social Medicine and Health Management, School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China,School of Management, Hainan Medical University, Haikou, China,Zhaoxin Wang
| | - Jianwei Shi
- Department of General Practice, Yangpu Hospital, Tongji University School of Medicine, Shanghai, China,Shanghai General Practice and Community Health Development Research Center, Shanghai, China,Department of Social Medicine and Health Management, School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai, China,Jianwei Shi
| |
Collapse
|
10
|
Hathaway QA, Yanamala N, Sengupta PP. Multimodal data for systolic and diastolic blood pressure prediction: The hypertension conscious artificial intelligence. EBioMedicine 2022; 84:104261. [PMID: 36113186 PMCID: PMC9483570 DOI: 10.1016/j.ebiom.2022.104261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Accepted: 08/25/2022] [Indexed: 12/02/2022] Open
Affiliation(s)
- Quincy A Hathaway
- Heart and Vascular Institute, West Virginia University School of Medicine, Morgantown, WV, USA.
| | - Naveena Yanamala
- Division of Cardiovascular Diseases, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| | - Partho P Sengupta
- Division of Cardiovascular Diseases, Rutgers Robert Wood Johnson Medical School, New Brunswick, NJ, USA
| |
Collapse
|
11
|
Life-Course Associations between Blood Pressure-Related Polygenic Risk Scores and Hypertension in the Bogalusa Heart Study. Genes (Basel) 2022; 13:genes13081473. [PMID: 36011384 PMCID: PMC9408577 DOI: 10.3390/genes13081473] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2022] [Revised: 07/30/2022] [Accepted: 08/15/2022] [Indexed: 11/16/2022] Open
Abstract
Genetic information may help to identify individuals at increased risk for hypertension in early life, prior to the manifestation of elevated blood pressure (BP) values. We examined 369 Black and 832 White Bogalusa Heart Study (BHS) participants recruited in childhood and followed for approximately 37 years. The multi-ancestry genome-wide polygenic risk scores (PRSs) for systolic BP (SBP), diastolic BP (DBP), and hypertension were tested for an association with incident hypertension and stage 2 hypertension using Cox proportional hazards models. Race-stratified analyses were adjusted for baseline age, age2, sex, body mass index, genetic principal components, and BP. In Black participants, each standard deviation increase in SBP and DBP PRS conferred a 38% (p = 0.009) and 22% (p = 0.02) increased risk of hypertension and a 74% (p < 0.001) and 50% (p < 0.001) increased risk of stage 2 hypertension, respectively, while no association was observed with the hypertension PRSs. In Whites, each standard deviation increase in SBP, DBP, and hypertension PRS conferred a 24% (p < 0.05), 29% (p = 0.01), and 25% (p < 0.001) increased risk of hypertension, and a 27% (p = 0.08), 29% (0.01), and 42% (p < 0.001) increased risk of stage 2 hypertension, respectively. The addition of BP PRSs to the covariable-only models generally improved the C-statistics (p < 0.05). Multi-ancestry BP PRSs demonstrate the utility of genomic information in the early life prediction of hypertension.
Collapse
|
12
|
Chowdhury MZI, Naeem I, Quan H, Leung AA, Sikdar KC, O’Beirne M, Turin TC. Prediction of hypertension using traditional regression and machine learning models: A systematic review and meta-analysis. PLoS One 2022; 17:e0266334. [PMID: 35390039 PMCID: PMC8989291 DOI: 10.1371/journal.pone.0266334] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Accepted: 03/19/2022] [Indexed: 11/19/2022] Open
Abstract
OBJECTIVE We aimed to identify existing hypertension risk prediction models developed using traditional regression-based or machine learning approaches and compare their predictive performance. METHODS We systematically searched MEDLINE, EMBASE, Web of Science, Scopus, and the grey literature for studies predicting the risk of hypertension among the general adult population. Summary statistics from the individual studies were the C-statistic, and a random-effects meta-analysis was used to obtain pooled estimates. The predictive performance of pooled estimates was compared between traditional regression-based models and machine learning-based models. The potential sources of heterogeneity were assessed using meta-regression, and study quality was assessed using the PROBAST (Prediction model Risk Of Bias ASsessment Tool) checklist. RESULTS Of 14,778 articles, 52 articles were selected for systematic review and 32 for meta-analysis. The overall pooled C-statistics was 0.75 [0.73-0.77] for the traditional regression-based models and 0.76 [0.72-0.79] for the machine learning-based models. High heterogeneity in C-statistic was observed. The age (p = 0.011), and sex (p = 0.044) of the participants and the number of risk factors considered in the model (p = 0.001) were identified as a source of heterogeneity in traditional regression-based models. CONCLUSION We attempted to provide a comprehensive evaluation of hypertension risk prediction models. Many models with acceptable-to-good predictive performance were identified. Only a few models were externally validated, and the risk of bias and applicability was a concern in many studies. Overall discrimination was similar between models derived from traditional regression analysis and machine learning methods. More external validation and impact studies to implement the hypertension risk prediction model in clinical practice are required.
Collapse
Affiliation(s)
- Mohammad Ziaul Islam Chowdhury
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Family Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Psychiatry, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Iffat Naeem
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Hude Quan
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Alexander A. Leung
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Khokan C. Sikdar
- Health Status Assessment, Surveillance, and Reporting, Public Health Surveillance and Infrastructure, Population, Public and Indigenous Health, Alberta Health Services, Calgary, Alberta, Canada
| | - Maeve O’Beirne
- Department of Family Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| | - Tanvir C. Turin
- Department of Community Health Sciences, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
- Department of Family Medicine, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
| |
Collapse
|
13
|
Niu M, Wang Y, Zhang L, Tu R, Liu X, Hou J, Huo W, Mao Z, Wang C, Bie R. Identifying the predictive effectiveness of a genetic risk score for incident hypertension using machine learning methods among populations in rural China. Hypertens Res 2021; 44:1483-1491. [PMID: 34480134 DOI: 10.1038/s41440-021-00738-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2021] [Revised: 07/31/2021] [Accepted: 08/04/2021] [Indexed: 12/17/2022]
Abstract
Current studies have shown the controversial effect of genetic risk scores (GRSs) in hypertension prediction. Machine learning methods are used extensively in the medical field but rarely in the mining of genetic information. This study aims to determine whether genetic information can improve the prediction of incident hypertension using machine learning approaches in a prospective study. The study recruited 4592 subjects without hypertension at baseline from a cohort study conducted in rural China. A polygenic risk score (PGGRS) was calculated using 13 SNPs. According to a ratio of 7:3, subjects were randomly allocated to the train and test datasets. Models with and without the PGGRS were established using the train dataset with Cox regression, artificial neural network (ANN), random forest (RF), and gradient boosting machine (GBM) methods. The discrimination and reclassification of models were estimated using the test dataset. The PGGRS showed a significant association with the risk of incident hypertension (HR (95% CI), 1.046 (1.004, 1.090), P = 0.031) irrespective of baseline blood pressure. Models that did not include the PGGRS achieved AUCs (95% CI) of 0.785 (0.763, 0.807), 0.790 (0.768, 0.811), 0.838 (0.817, 0.857), and 0.854 (0.835, 0.873) for the Cox, ANN, RF, and GBM methods, respectively. The addition of the PGGRS led to the improvement of the AUC by 0.001, 0.008, 0.023, and 0.017; IDI by 1.39%, 2.86%, 4.73%, and 4.68%; and NRI by 25.05%, 13.01%, 44.87%, and 22.94%, respectively. Incident hypertension risk was better predicted by the traditional+PGGRS model, especially when machine learning approaches were used, suggesting that genetic information may have the potential to identify new hypertension cases using machine learning methods in resource-limited areas. CLINICAL TRIAL REGISTRATION: The Henan Rural Cohort Study has been registered at the Chinese Clinical Trial Register (Registration number: ChiCTR-OOC-15006699). http://www.chictr.org.cn/showproj.aspx?proj=11375 .
Collapse
Affiliation(s)
- Miaomiao Niu
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Yikang Wang
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Liying Zhang
- School of Information Engineering, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Runqi Tu
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Xiaotian Liu
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Jian Hou
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Wenqian Huo
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Zhenxing Mao
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China
| | - Chongjian Wang
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China.
| | - Ronghai Bie
- Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, Henan, PR China.
| |
Collapse
|
14
|
Lin C, Li C, Liu C, Lin C, Wang M, Yang S, Li T. A risk scoring system to predict the risk of new-onset hypertension among patients with type 2 diabetes. J Clin Hypertens (Greenwich) 2021; 23:1570-1580. [PMID: 34251744 PMCID: PMC8678759 DOI: 10.1111/jch.14322] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Revised: 06/28/2021] [Accepted: 06/30/2021] [Indexed: 12/01/2022]
Abstract
Hypertension (HTN), which frequently co-exists with diabetes mellitus, is the leading major cause of cardiovascular disease and death globally. This study aimed to develop and validate a risk scoring system considering the effects of glycemic and blood pressure (BP) variabilities to predict HTN incidence in patients with type 2 diabetes. This research is a retrospective cohort study that included 3416 patients with type 2 diabetes without HTN and who were enrolled in a managed care program in 2001-2015. The patients were followed up until April 2016, new-onset HTN event, or death. HTN was defined as diastolic BP (DBP) ≥ 90 mm Hg, systolic BP (SBP) ≥ 140 mm Hg, or the initiation of antihypertensive medication. Cox proportional hazard regression model was used to develop the risk scoring system for HTN. Of the patients, 1738 experienced new-onset HTN during an average follow-up period of 3.40 years. Age, sex, physical activity, body mass index, type of DM treatment, family history of HTN, baseline SBP and DBP, variabilities of fasting plasma glucose, SBP, and DBP and macroalbuminuria were significant variables for the prediction of new-onset HTN. Using these predictors, the prediction models for 1-, 3-, and 5-year periods demonstrated good discrimination, with AUC values of 0.70-0.76. Our HTN scoring system for patients with type 2 DM, which involves innovative predictors of glycemic and BP variabilities, has good classification accuracy and identifies risk factors available in clinical settings for prevention of the progression to new-onset HTN.
Collapse
Affiliation(s)
- Cheng‐Chieh Lin
- School of MedicineCollege of MedicineChina Medical UniversityTaichungTaiwan
- Department of Family MedicineChina Medical University HospitalTaichungTaiwan
- Department of Medical ResearchChina Medical University HospitalTaichungTaiwan
| | - Chia‐Ing Li
- School of MedicineCollege of MedicineChina Medical UniversityTaichungTaiwan
- Department of Medical ResearchChina Medical University HospitalTaichungTaiwan
| | - Chiu‐Shong Liu
- School of MedicineCollege of MedicineChina Medical UniversityTaichungTaiwan
- Department of Family MedicineChina Medical University HospitalTaichungTaiwan
| | - Chih‐Hsueh Lin
- School of MedicineCollege of MedicineChina Medical UniversityTaichungTaiwan
- Department of Family MedicineChina Medical University HospitalTaichungTaiwan
| | - Mu‐Cyun Wang
- School of MedicineCollege of MedicineChina Medical UniversityTaichungTaiwan
- Department of Family MedicineChina Medical University HospitalTaichungTaiwan
| | - Shing‐Yu Yang
- Department of Public HealthCollege of Public HealthChina Medical UniversityTaichungTaiwan
| | - Tsai‐Chung Li
- Department of Public HealthCollege of Public HealthChina Medical UniversityTaichungTaiwan
- Department of Healthcare AdministrationCollege of Medical and Health ScienceAsia UniversityTaichungTaiwan
| |
Collapse
|
15
|
Cheng CF, Hsieh AR, Liang WM, Chen CC, Chen CH, Wu JY, Lin TH, Liao CC, Huang SM, Huang YC, Ban B, Lin YJ, Tsai FJ. Genome-Wide and Candidate Gene Association Analyses Identify a 14-SNP Combination for Hypertension in Patients With Type 2 Diabetes. Am J Hypertens 2021; 34:651-661. [PMID: 33276381 DOI: 10.1093/ajh/hpaa203] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2020] [Revised: 10/19/2020] [Accepted: 12/02/2020] [Indexed: 01/11/2023] Open
Abstract
BACKGROUND High blood pressure is common and comorbid with type 2 diabetes (T2D). Almost 50% of patients with T2D have high blood pressure. Patients with both conditions of hypertension (HTN) and T2D are at risk for cardiovascular diseases and mortality. The study aim was to investigate genetic risk factors for HTN in T2D patients. METHODS This study included 999 T2D (cohort 1) patients for the first genome scan stage and 922 T2D (cohort 2) patients for the replication stage. Here, we investigated the genetic susceptibility and cumulative weighted genetic risk score for HTN in T2D patients of Han Chinese descent in Taiwan. RESULTS Thirty novel genetic single nucleotide polymorphisms (SNPs) were associated with HTN in T2D after adjusting for age and body mass index (P value <1 × 10-4). Eight blood pressure-related and/or HTN-related genetic SNPs were associated with HTN in T2D after adjusting for age and body mass index (P value <0.05). Linkage disequilibrium and cumulative weighted genetic risk score analyses showed that 14 of the 38 SNPs were associated with risk of HTN in a dose-dependent manner in T2D (Cochran-Armitage trend test: P value <0.0001). The 14-SNP cumulative weighted genetic risk score was also associated with increased regression tendency of systolic blood pressure in T2D (SBP = 122.05 + 0.8 × weighted genetic risk score; P value = 0.0001). CONCLUSIONS A cumulative weighted genetic risk score composed of 14 SNPs is important for HTN, increased tendency of systolic blood pressure, and may contribute to HTN risk in T2D in Taiwan.
Collapse
Affiliation(s)
- Chi-Fung Cheng
- Graduate Institute of Biostatistics, School of Public Health, China Medical University, Taichung, Taiwan
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Ai-Ru Hsieh
- Department of Statistics, Tamkang University, New Taipei City, Taiwan
| | - Wen-Miin Liang
- Graduate Institute of Biostatistics, School of Public Health, China Medical University, Taichung, Taiwan
| | - Ching-Chu Chen
- Division of Endocrinology and Metabolism, Department of Medicine, China Medical University Hospital, Taichung, Taiwan
| | - Chien-Hsiun Chen
- Institute of Biomedical Sciences, Academia Sinica, Taipei, Taiwan
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
| | - Jer-Yuarn Wu
- Institute of Biomedical Sciences, Academia Sinica, Taipei, Taiwan
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
| | - Ting-Hsu Lin
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Chiu-Chu Liao
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Shao-Mei Huang
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
| | - Yu-Chuen Huang
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
| | - Bo Ban
- Chinese Research Center for Behavior Medicine in Growth and Development, Jining, Shandong, China
| | - Ying-Ju Lin
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
| | - Fuu-Jen Tsai
- Genetic Center, Department of Medical Research, China Medical University Hospital, Taichung, Taiwan
- School of Chinese Medicine, China Medical University, Taichung, Taiwan
- Department of Biotechnology and Bioinformatics, Asia University, Taichung, Taiwan
| |
Collapse
|
16
|
Vaura F, Kauko A, Suvila K, Havulinna AS, Mars N, Salomaa V, FinnGen, Cheng S, Niiranen T. Polygenic Risk Scores Predict Hypertension Onset and Cardiovascular Risk. Hypertension 2021; 77:1119-1127. [PMID: 33611940 PMCID: PMC8025831 DOI: 10.1161/hypertensionaha.120.16471] [Citation(s) in RCA: 50] [Impact Index Per Article: 16.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
[Figure: see text].
Collapse
Affiliation(s)
- Felix Vaura
- From the Department of Internal Medicine, University of Turku, Finland (F.V., A.K., K.S., T.N.)
| | - Anni Kauko
- From the Department of Internal Medicine, University of Turku, Finland (F.V., A.K., K.S., T.N.)
| | - Karri Suvila
- From the Department of Internal Medicine, University of Turku, Finland (F.V., A.K., K.S., T.N.).,Division of Medicine, Turku University Hospital, Finland (K.S., T.N.)
| | - Aki S Havulinna
- Department of Public Health Solutions, Finnish Institute for Health and Welfare, Helsinki, Finland (A.S.H., V.S., T.N.).,Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki (A.S.H., N.M.)
| | - Nina Mars
- Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki (A.S.H., N.M.)
| | - Veikko Salomaa
- Department of Public Health Solutions, Finnish Institute for Health and Welfare, Helsinki, Finland (A.S.H., V.S., T.N.)
| | | | - Susan Cheng
- Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA (S.C.).,Division of Cardiology, Brigham and Women's Hospital, Boston, MA (S.C.)
| | - Teemu Niiranen
- From the Department of Internal Medicine, University of Turku, Finland (F.V., A.K., K.S., T.N.).,Division of Medicine, Turku University Hospital, Finland (K.S., T.N.).,Department of Public Health Solutions, Finnish Institute for Health and Welfare, Helsinki, Finland (A.S.H., V.S., T.N.)
| |
Collapse
|
17
|
Ren Z, Rao B, Xie S, Li A, Wang L, Cui G, Li T, Yan H, Yu Z, Ding S. A novel predicted model for hypertension based on a large cross-sectional study. Sci Rep 2020; 10:10615. [PMID: 32606332 PMCID: PMC7327010 DOI: 10.1038/s41598-020-64980-8] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/07/2019] [Accepted: 04/24/2020] [Indexed: 12/28/2022] Open
Abstract
Hypertension is a global public health issue and leading risk for death and disability. It is urgent to search novel methods predicting hypertension. Herein, we chose 73158 samples of physical examiners in central China from June 2008 to June 2018. After strict exclusion processes, 33570 participants with hypertension and 35410 healthy controls were included. We randomly chose 70% samples as the train set and the remaining 30% as the test set. Clinical parameters including age, gender, height, weight, body mass index, triglyceride, total cholesterol, low-density lipoprotein, blood urea nitrogen, uric acid, and creatinine were significantly increased, while high-density lipoprotein was decreased in the hypertension group versus controls. Nine optimal markers were identified by a logistic regression model, and achieved AUC value of 76.52% in the train set and 75.81% in the test set for hypertension. In conclusions, this study is the first to establish predicted models for hypertension using the logistic regression model in Central China, which provide risk factors and novel prediction method to predict and prevent hypertension.
Collapse
Affiliation(s)
- Zhigang Ren
- Department of Infectious Diseases, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
- Gene Hospital of Henan Province; Precision Medicine Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Benchen Rao
- Department of Infectious Diseases, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
- Gene Hospital of Henan Province; Precision Medicine Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Siqi Xie
- Health Management Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Ang Li
- Department of Infectious Diseases, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
- Gene Hospital of Henan Province; Precision Medicine Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Lijun Wang
- Health Management Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Guangying Cui
- Department of Infectious Diseases, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
- Gene Hospital of Henan Province; Precision Medicine Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Tiantian Li
- Health Management Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Hang Yan
- Health Management Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China
| | - Zujiang Yu
- Department of Infectious Diseases, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China.
- Gene Hospital of Henan Province; Precision Medicine Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China.
| | - Suying Ding
- Health Management Center, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China.
| |
Collapse
|
18
|
Sun D, Zhou T, Li X, Heianza Y, Liang Z, Bray GA, Sacks FM, Qi L. Genetic Susceptibility, Dietary Protein Intake, and Changes of Blood Pressure: The POUNDS Lost Trial. Hypertension 2019; 74:1460-1467. [PMID: 31656094 PMCID: PMC6854315 DOI: 10.1161/hypertensionaha.119.13510] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2019] [Accepted: 07/18/2019] [Indexed: 02/06/2023]
Abstract
High blood pressure (BP) is closely related to obesity, and weight loss lowers BP. Evidence has shown considerable interpersonal variation of changes in BP among people experiencing weight loss, and such variation might be partly determined by genetic factors. We assessed the changes in systolic and diastolic BP (SBP/DBP) among 692 participants randomly assigned to 1 of 4 diets varying in macronutrient content for 2 years. Two separate polygenic scores (SBP/DBP-PGS derived from 52/50 single nucleotide polymorphisms) were built for each participant based on 66 BP-associated single nucleotide polymorphisms. During a 2-year intervention, participants in the bottom versus upper tertile of SBP/DBP-PGS had a greater decrease in SBP (△SBP at 6, 12, and 24 months: -3.84 versus -1.61, -4.76 versus -2.75, -2.49 versus -1.63; P=0.001) or in DBP (△DBP at 6, 12, and 24 months: -3.09 versus -1.34, -2.69 versus -1.44, -1.82 versus -0.53; P<0.001). We also found gene-diet interaction on changes in SBP from baseline to 24 months (Pinteraction=0.009). Among participants assigned to a high-protein diet, those with a lower SBP-polygenic scores had greater decreases in SBP at months 6 (P=0.018), months 12 (P=0.007), and months 24 (P=0.089); while no significant difference was observed across the SBP-polygenic scores tertile groups among those assigned to an average-protein diet (all P values >0.05). Our data indicate that genetic susceptibility may affect BP changes in response to weight-loss diet interventions, and protein intake may modify the genetic associations with changes in BP. This trial was registered at URL: http://www.clinicaltrials.gov. Unique identifier: NCT00072995.
Collapse
Affiliation(s)
- Dianjianyi Sun
- From the Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA (D.S., T.Z., X.L., Y.H., Z.L., L.Q.)
- Department of Epidemiology and Biostatistics, School of Public Health, Peking University Health Science Center, Beijing, China (D.S.)
| | - Tao Zhou
- From the Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA (D.S., T.Z., X.L., Y.H., Z.L., L.Q.)
| | - Xiang Li
- From the Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA (D.S., T.Z., X.L., Y.H., Z.L., L.Q.)
| | - Yoriko Heianza
- From the Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA (D.S., T.Z., X.L., Y.H., Z.L., L.Q.)
| | - Zhaoxia Liang
- From the Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA (D.S., T.Z., X.L., Y.H., Z.L., L.Q.)
- Department of Obstetrics, Women's Hospital, Zhejiang University School of Medicine, Hangzhou, China (Z.L.)
- Key Laboratory of Reproductive Genetics, Ministry of Education, China (Z.L.)
| | - George A Bray
- Pennington Biomedical Research Center, Louisiana State University, Baton Rouge, LA (G.A.B.)
| | - Frank M Sacks
- Department of Nutrition, Harvard T.H. Chan School of Public Health, Boston, MA (F.M.S., L.Q.)
- Channing Division of Network Medicine, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA (F.M.S., L.Q.)
| | - Lu Qi
- From the Department of Epidemiology, School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA (D.S., T.Z., X.L., Y.H., Z.L., L.Q.)
- Department of Nutrition, Harvard T.H. Chan School of Public Health, Boston, MA (F.M.S., L.Q.)
- Channing Division of Network Medicine, Department of Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA (F.M.S., L.Q.)
| |
Collapse
|
19
|
Li C, Sun D, Liu J, Li M, Zhang B, Liu Y, Wang Z, Wen S, Zhou J. A Prediction Model of Essential Hypertension Based on Genetic and Environmental Risk Factors in Northern Han Chinese. Int J Med Sci 2019; 16:793-799. [PMID: 31337952 PMCID: PMC6643104 DOI: 10.7150/ijms.33967] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/11/2019] [Accepted: 04/22/2019] [Indexed: 11/06/2022] Open
Abstract
Background: Essential hypertension (EH) is a chronic disease of universal high prevalence and a well-established independent risk factor for cardiovascular and cerebrovascular events. The regulation of blood pressure is crucial for improving life quality and prognoses in patients with EH. Therefore, it is of important clinical significance to develop prediction models to recognize individuals with high risk for EH. Methods: In total, 965 subjects were recruited. Clinical parameters and genetic information, namely EH related SNPs were collected for each individual. Traditional statistic methods such as t-test, chi-square test and multi-variable logistic regression were applied to analyze baseline information. A machine learning method, mainly support vector machine (SVM), was adopted for the development of the present prediction models for EH. Results: Two models were constructed for prediction of systolic blood pressure (SBP) and diastolic blood pressure (DBP), respectively. The model for SBP consists of 6 environmental factors (age, BMI, waist circumference, exercise [times per week], parental history of hypertension [either or both]) and 1 SNP (rs7305099); model for DBP consists of 6 environmental factors (weight, drinking, exercise [times per week], TG, parental history of hypertension [either and both]) and 3 SNPs (rs5193, rs7305099, rs3889728). AUC are 0.673 and 0.817 for SBP and DBP model, respectively. Conclusions: The present study identified environmental and genetic risk factors for EH in northern Han Chinese population and constructed prediction models for SBP and DBP.
Collapse
Affiliation(s)
- Chuang Li
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Dongdong Sun
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Jielin Liu
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Mei Li
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Bei Zhang
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Ya Liu
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Zuoguang Wang
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Shaojun Wen
- Department of Hypertension Research, Beijing Anzhen Hospital, Capital Medical University and Beijing Institute of Herat Lung and Blood Vessel Diseases, Beijing, People's Republic of China.,Beijing Lab for Cardiovascular Precision Medicine, Beijing, People's Republic of China
| | - Jiapeng Zhou
- College of Life Sciences, Hunan Normal University, Changsha, People's Republic of China.,Beijing Mygenostics Co., Ltd., Beijing, People's Republic of China
| |
Collapse
|
20
|
Richard MA, Huan T, Ligthart S, Gondalia R, Jhun MA, Brody JA, Irvin MR, Marioni R, Shen J, Tsai PC, Montasser ME, Jia Y, Syme C, Salfati EL, Boerwinkle E, Guan W, Mosley TH, Bressler J, Morrison AC, Liu C, Mendelson MM, Uitterlinden AG, van Meurs JB, Franco OH, Zhang G, Li Y, Stewart JD, Bis JC, Psaty BM, Chen YDI, Kardia SLR, Zhao W, Turner ST, Absher D, Aslibekyan S, Starr JM, McRae AF, Hou L, Just AC, Schwartz JD, Vokonas PS, Menni C, Spector TD, Shuldiner A, Damcott CM, Rotter JI, Palmas W, Liu Y, Paus T, Horvath S, O'Connell JR, Guo X, Pausova Z, Assimes TL, Sotoodehnia N, Smith JA, Arnett DK, Deary IJ, Baccarelli AA, Bell JT, Whitsel E, Dehghan A, Levy D, Fornage M. DNA Methylation Analysis Identifies Loci for Blood Pressure Regulation. Am J Hum Genet 2017; 101:888-902. [PMID: 29198723 PMCID: PMC5812919 DOI: 10.1016/j.ajhg.2017.09.028] [Citation(s) in RCA: 138] [Impact Index Per Article: 19.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2017] [Accepted: 09/28/2017] [Indexed: 12/13/2022] Open
Abstract
Genome-wide association studies have identified hundreds of genetic variants associated with blood pressure (BP), but sequence variation accounts for a small fraction of the phenotypic variance. Epigenetic changes may alter the expression of genes involved in BP regulation and explain part of the missing heritability. We therefore conducted a two-stage meta-analysis of the cross-sectional associations of systolic and diastolic BP with blood-derived genome-wide DNA methylation measured on the Infinium HumanMethylation450 BeadChip in 17,010 individuals of European, African American, and Hispanic ancestry. Of 31 discovery-stage cytosine-phosphate-guanine (CpG) dinucleotides, 13 replicated after Bonferroni correction (discovery: N = 9,828, p < 1.0 × 10-7; replication: N = 7,182, p < 1.6 × 10-3). The replicated methylation sites are heritable (h2 > 30%) and independent of known BP genetic variants, explaining an additional 1.4% and 2.0% of the interindividual variation in systolic and diastolic BP, respectively. Bidirectional Mendelian randomization among up to 4,513 individuals of European ancestry from 4 cohorts suggested that methylation at cg08035323 (TAF1B-YWHAQ) influences BP, while BP influences methylation at cg00533891 (ZMIZ1), cg00574958 (CPT1A), and cg02711608 (SLC1A5). Gene expression analyses further identified six genes (TSPAN2, SLC7A11, UNC93B1, CPT1A, PTMS, and LPCAT3) with evidence of triangular associations between methylation, gene expression, and BP. Additional integrative Mendelian randomization analyses of gene expression and DNA methylation suggested that the expression of TSPAN2 is a putative mediator of association between DNA methylation at cg23999170 and BP. These findings suggest that heritable DNA methylation plays a role in regulating BP independently of previously known genetic variants.
Collapse
Affiliation(s)
- Melissa A Richard
- Brown Foundation Institute of Molecular Medicine, University of Texas Health Science Center, Houston, TX 77030, USA.
| | - Tianxiao Huan
- Population Sciences Branch, National Heart, Lung, and Blood Institute, NIH, Bethesda, MD 20892, USA; Framingham Heart Study, Framingham, MA 01702, USA
| | - Symen Ligthart
- Department of Epidemiology, Erasmus University Medical Center, Rotterdam 3000, the Netherlands
| | - Rahul Gondalia
- Department of Epidemiology, University of North Carolina, Chapel Hill, NC 27599, USA
| | - Min A Jhun
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI 48108, USA
| | - Jennifer A Brody
- Cardiovascular Health Research Unit, Department of Medicine, University of Washington, Seattle, WA 98195, USA
| | - Marguerite R Irvin
- Department of Epidemiology, University of Alabama at Birmingham, Birmingham, AL 35294, USA
| | - Riccardo Marioni
- Centre for Cognitive Ageing and Cognitive Epidemiology, University of Edinburgh, Edinburgh EH8 9JZ, UK; Medical Genetics Section, Centre for Genomic and Experimental Medicine, Institute of Genetics and Molecular Medicine, University of Edinburgh, Edinburgh EH4 2XU, UK; Queensland Brain Institute, The University of Queensland, Brisbane, QLD 4072, Australia
| | - Jincheng Shen
- Department of Population Health Sciences, University of Utah School of Medicine, Salt Lake City, UT 84108, USA
| | - Pei-Chien Tsai
- Department of Twin Research and Genetic Epidemiology, Kings College London, SE17EH London, UK
| | - May E Montasser
- Division of Endocrinology, Diabetes, and Nutrition, Program for Personalized and Genomic Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA
| | - Yucheng Jia
- Institute for Translational Genomics and Population Sciences, Departments of Pediatrics and Medicine, Los Angeles BioMedical Research Institute at Harbor-UCLA Medical Center, Torrance, CA 90502, USA
| | - Catriona Syme
- Hospital for Sick Children, University of Toronto, Toronto, ON M5G 0A4, Canada
| | - Elias L Salfati
- Department of Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - Eric Boerwinkle
- Human Genetics Center, School of Public Health, University of Texas Health Science Center, Houston, TX 77030, USA; Human Genome Sequencing Center, Baylor College of Medicine, Houston, TX 77030, USA
| | - Weihua Guan
- Department of Biostatistics, University of Minnesota, Minneapolis, MN 55454, USA
| | - Thomas H Mosley
- Department of Medicine, University of Mississippi Medical Center, Jackson, MS 39216, USA
| | - Jan Bressler
- Human Genetics Center, School of Public Health, University of Texas Health Science Center, Houston, TX 77030, USA
| | - Alanna C Morrison
- Human Genetics Center, School of Public Health, University of Texas Health Science Center, Houston, TX 77030, USA
| | - Chunyu Liu
- Population Sciences Branch, National Heart, Lung, and Blood Institute, NIH, Bethesda, MD 20892, USA; Framingham Heart Study, Framingham, MA 01702, USA; Department of Biostatistics, Boston University, Boston, MA 02118, USA
| | - Michael M Mendelson
- Population Sciences Branch, National Heart, Lung, and Blood Institute, NIH, Bethesda, MD 20892, USA; Framingham Heart Study, Framingham, MA 01702, USA; Department of Cardiology, Boston Children's Hospital, Boston, MA 02115, USA
| | - André G Uitterlinden
- Department of Internal Medicine, Erasmus University Medical Center, Rotterdam 3000, the Netherlands
| | - Joyce B van Meurs
- Department of Internal Medicine, Erasmus University Medical Center, Rotterdam 3000, the Netherlands
| | - Oscar H Franco
- Department of Epidemiology, Erasmus University Medical Center, Rotterdam 3000, the Netherlands
| | - Guosheng Zhang
- Department of Genetics, University of North Carolina, Chapel Hill, NC 27514, USA; Curriculum in Bioinformatics and Computational Biology, University of North Carolina, Chapel Hill, NC 27514, USA; Department of Statistics, University of North Carolina, Chapel Hill, NC 27514, USA
| | - Yun Li
- Department of Genetics, University of North Carolina, Chapel Hill, NC 27514, USA; Department of Biostatistics, University of North Carolina, Chapel Hill, NC 27599, USA
| | - James D Stewart
- Department of Epidemiology, University of North Carolina, Chapel Hill, NC 27599, USA; Carolina Population Center, University of North Carolina, Chapel Hill, NC 27514, USA
| | - Joshua C Bis
- Cardiovascular Health Research Unit, Department of Medicine, University of Washington, Seattle, WA 98195, USA
| | - Bruce M Psaty
- Cardiovascular Health Research Unit, Departments of Medicine, Epidemiology, and Health Services, University of Washington, Seattle, WA 98101, USA; Kaiser Permanente Washington Health Research Unit, Seattle, WA 98101, USA
| | - Yii-Der Ida Chen
- Institute for Translational Genomics and Population Sciences, Departments of Pediatrics and Medicine, Los Angeles BioMedical Research Institute at Harbor-UCLA Medical Center, Torrance, CA 90502, USA
| | - Sharon L R Kardia
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI 48108, USA
| | - Wei Zhao
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI 48108, USA
| | - Stephen T Turner
- Division of Nephrology and Hypertension, Mayo Clinic, Rochester, MN 55905, USA
| | - Devin Absher
- HudsonAlpha Institute for Biotechnology, Huntsville, AL 35806, USA
| | - Stella Aslibekyan
- Department of Epidemiology, University of Alabama at Birmingham, Birmingham, AL 35294, USA
| | - John M Starr
- Centre for Cognitive Ageing and Cognitive Epidemiology, University of Edinburgh, Edinburgh EH8 9JZ, UK; Alzheimer Scotland Dementia Research Centre, University of Edinburgh, Edinburgh EH8 9JZ, UK
| | - Allan F McRae
- Queensland Brain Institute, The University of Queensland, Brisbane, QLD 4072, Australia; Institute for Molecular Bioscience, The University of Queensland, Brisbane, QLD 4072, Australia
| | - Lifang Hou
- Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL 60611, USA
| | - Allan C Just
- Department of Preventive Medicine, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA
| | - Joel D Schwartz
- Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
| | - Pantel S Vokonas
- Veterans Affairs Normative Aging Study, Veterans Affairs Boston Healthcare System, Department of Medicine, Boston University School of Medicine, Boston, MA 02118, USA
| | - Cristina Menni
- Department of Twin Research and Genetic Epidemiology, Kings College London, SE17EH London, UK
| | - Tim D Spector
- Department of Twin Research and Genetic Epidemiology, Kings College London, SE17EH London, UK
| | - Alan Shuldiner
- Division of Endocrinology, Diabetes, and Nutrition, Program for Personalized and Genomic Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA; The Regeneron Genetics Center, Regeneron Pharmaceuticals, Tarrytown, NY 10591, USA
| | - Coleen M Damcott
- Division of Endocrinology, Diabetes, and Nutrition, Program for Personalized and Genomic Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA
| | - Jerome I Rotter
- Institute for Translational Genomics and Population Sciences, Departments of Pediatrics and Medicine, Los Angeles BioMedical Research Institute at Harbor-UCLA Medical Center, Torrance, CA 90502, USA
| | - Walter Palmas
- Department of Medicine, Columbia University, New York, NY 10032, USA
| | - Yongmei Liu
- Wake Forest School of Medicine, Winston-Salem, NC 27157, USA
| | - Tomáš Paus
- Departments of Psychology and Psychiatry, University of Toronto, Toronto, ON M5S 3G3, Canada; Rotman Research Institute, Baycrest, Toronto, ON M6A 2E1, Canada; Child Mind Institute, New York, NY 10022, USA
| | - Steve Horvath
- Department of Human Genetics, Gonda Research Center, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA 90095, USA
| | - Jeffrey R O'Connell
- Division of Endocrinology, Diabetes, and Nutrition, Program for Personalized and Genomic Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA
| | - Xiuqing Guo
- Institute for Translational Genomics and Population Sciences, Departments of Pediatrics and Medicine, Los Angeles BioMedical Research Institute at Harbor-UCLA Medical Center, Torrance, CA 90502, USA
| | - Zdenka Pausova
- Hospital for Sick Children, University of Toronto, Toronto, ON M5G 0A4, Canada; Departments of Physiology and Nutritional Sciences, University of Toronto, Toronto, ON M5S 1A8, Canada
| | | | - Nona Sotoodehnia
- Cardiovascular Health Research Unit, Division of Cardiology, University of Washington, Seattle, WA 98195, USA
| | - Jennifer A Smith
- Department of Epidemiology, School of Public Health, University of Michigan, Ann Arbor, MI 48108, USA
| | - Donna K Arnett
- University of Kentucky, College of Public Health, Lexington, KY 40563, USA
| | - Ian J Deary
- Centre for Cognitive Ageing and Cognitive Epidemiology, University of Edinburgh, Edinburgh EH8 9JZ, UK; Department of Psychology, University of Edinburgh, Edinburgh EH9 8JZ, UK
| | - Andrea A Baccarelli
- Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA
| | - Jordana T Bell
- Department of Twin Research and Genetic Epidemiology, Kings College London, SE17EH London, UK
| | - Eric Whitsel
- Department of Epidemiology, University of North Carolina, Chapel Hill, NC 27599, USA; Department of Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC 27514, USA
| | - Abbas Dehghan
- Department of Epidemiology, Erasmus University Medical Center, Rotterdam 3000, the Netherlands; Department of Biostatistics and Epidemiology, MRC-PHE Centre for Environment and Health, School of Public Health, Imperial College London, London W2 1PG, UK
| | - Daniel Levy
- Population Sciences Branch, National Heart, Lung, and Blood Institute, NIH, Bethesda, MD 20892, USA; Framingham Heart Study, Framingham, MA 01702, USA
| | - Myriam Fornage
- Brown Foundation Institute of Molecular Medicine, University of Texas Health Science Center, Houston, TX 77030, USA; Human Genetics Center, School of Public Health, University of Texas Health Science Center, Houston, TX 77030, USA.
| |
Collapse
|
21
|
Recent development of risk-prediction models for incident hypertension: An updated systematic review. PLoS One 2017; 12:e0187240. [PMID: 29084293 PMCID: PMC5662179 DOI: 10.1371/journal.pone.0187240] [Citation(s) in RCA: 52] [Impact Index Per Article: 7.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2017] [Accepted: 09/29/2017] [Indexed: 01/11/2023] Open
Abstract
BACKGROUND Hypertension is a leading global health threat and a major cardiovascular disease. Since clinical interventions are effective in delaying the disease progression from prehypertension to hypertension, diagnostic prediction models to identify patient populations at high risk for hypertension are imperative. METHODS Both PubMed and Embase databases were searched for eligible reports of either prediction models or risk scores of hypertension. The study data were collected, including risk factors, statistic methods, characteristics of study design and participants, performance measurement, etc. RESULTS From the searched literature, 26 studies reporting 48 prediction models were selected. Among them, 20 reports studied the established models using traditional risk factors, such as body mass index (BMI), age, smoking, blood pressure (BP) level, parental history of hypertension, and biochemical factors, whereas 6 reports used genetic risk score (GRS) as the prediction factor. AUC ranged from 0.64 to 0.97, and C-statistic ranged from 60% to 90%. CONCLUSIONS The traditional models are still the predominant risk prediction models for hypertension, but recently, more models have begun to incorporate genetic factors as part of their model predictors. However, these genetic predictors need to be well selected. The current reported models have acceptable to good discrimination and calibration ability, but whether the models can be applied in clinical practice still needs more validation and adjustment.
Collapse
|
22
|
Wang X, Snieder H. Assessing genetic risk of hypertension at an early age: future research directions. Expert Rev Cardiovasc Ther 2017; 15:809-812. [PMID: 28893096 DOI: 10.1080/14779072.2017.1376656] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Affiliation(s)
- Xiaoling Wang
- a Georgia Prevention Institute , Medical College of Georgia, Augusta University , Augusta , GA , USA
| | - Harold Snieder
- b Unit of Genetic Epidemiology and Bioinformatics, Department of Epidemiology , University Medical Center Groningen, University of Groningen , Groningen , The Netherlands
| |
Collapse
|
23
|
|