Predictive Accuracy of Stroke Risk Prediction Models Across Black and White Race, Sex, and Age Groups
Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention strategies. To compare the performance of stroke-specific...
Gespeichert in:
| Veröffentlicht in: | JAMA : the journal of the American Medical Association Jg. 329; H. 4; S. 306 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
United States
24.01.2023
|
| Schlagworte: | |
| ISSN: | 1538-3598, 1538-3598 |
| Online-Zugang: | Weitere Angaben |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention strategies.
To compare the performance of stroke-specific algorithms with pooled cohort equations developed for atherosclerotic cardiovascular disease for the prediction of new-onset stroke across different subgroups (race, sex, and age) and to determine the added value of novel machine learning techniques.
Retrospective cohort study on combined and harmonized data from Black and White participants of the Framingham Offspring, Atherosclerosis Risk in Communities (ARIC), Multi-Ethnic Study for Atherosclerosis (MESA), and Reasons for Geographical and Racial Differences in Stroke (REGARDS) studies (1983-2019) conducted in the US. The 62 482 participants included at baseline were at least 45 years of age and free of stroke or transient ischemic attack.
Published stroke-specific algorithms from Framingham and REGARDS (based on self-reported risk factors) as well as pooled cohort equations for atherosclerotic cardiovascular disease plus 2 newly developed machine learning algorithms.
Models were designed to estimate the 10-year risk of new-onset stroke (ischemic or hemorrhagic). Discrimination concordance index (C index) and calibration ratios of expected vs observed event rates were assessed at 10 years. Analyses were conducted by race, sex, and age groups.
The combined study sample included 62 482 participants (median age, 61 years, 54% women, and 29% Black individuals). Discrimination C indexes were not significantly different for the 2 stroke-specific models (Framingham stroke, 0.72; 95% CI, 0.72-073; REGARDS self-report, 0.73; 95% CI, 0.72-0.74) vs the pooled cohort equations (0.72; 95% CI, 0.71-0.73): differences 0.01 or less (P values >.05) in the combined sample. Significant differences in discrimination were observed by race: the C indexes were 0.76 for all 3 models in White vs 0.69 in Black women (all P values <.001) and between 0.71 and 0.72 in White men and between 0.64 and 0.66 in Black men (all P values ≤.001). When stratified by age, model discrimination was better for younger (<60 years) vs older (≥60 years) adults for both Black and White individuals. The ratios of observed to expected 10-year stroke rates were closest to 1 for the REGARDS self-report model (1.05; 95% CI, 1.00-1.09) and indicated risk overestimation for Framingham stroke (0.86; 95% CI, 0.82-0.89) and pooled cohort equations (0.74; 95% CI, 0.71-0.77). Performance did not significantly improve when novel machine learning algorithms were applied.
In this analysis of Black and White individuals without stroke or transient ischemic attack among 4 US cohorts, existing stroke-specific risk prediction models and novel machine learning techniques did not significantly improve discriminative accuracy for new-onset stroke compared with the pooled cohort equations, and the REGARDS self-report model had the best calibration. All algorithms exhibited worse discrimination in Black individuals than in White individuals, indicating the need to expand the pool of risk factors and improve modeling techniques to address observed racial disparities and improve model performance. |
|---|---|
| AbstractList | Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention strategies.ImportanceStroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention strategies.To compare the performance of stroke-specific algorithms with pooled cohort equations developed for atherosclerotic cardiovascular disease for the prediction of new-onset stroke across different subgroups (race, sex, and age) and to determine the added value of novel machine learning techniques.ObjectiveTo compare the performance of stroke-specific algorithms with pooled cohort equations developed for atherosclerotic cardiovascular disease for the prediction of new-onset stroke across different subgroups (race, sex, and age) and to determine the added value of novel machine learning techniques.Retrospective cohort study on combined and harmonized data from Black and White participants of the Framingham Offspring, Atherosclerosis Risk in Communities (ARIC), Multi-Ethnic Study for Atherosclerosis (MESA), and Reasons for Geographical and Racial Differences in Stroke (REGARDS) studies (1983-2019) conducted in the US. The 62 482 participants included at baseline were at least 45 years of age and free of stroke or transient ischemic attack.Design, Setting, and ParticipantsRetrospective cohort study on combined and harmonized data from Black and White participants of the Framingham Offspring, Atherosclerosis Risk in Communities (ARIC), Multi-Ethnic Study for Atherosclerosis (MESA), and Reasons for Geographical and Racial Differences in Stroke (REGARDS) studies (1983-2019) conducted in the US. The 62 482 participants included at baseline were at least 45 years of age and free of stroke or transient ischemic attack.Published stroke-specific algorithms from Framingham and REGARDS (based on self-reported risk factors) as well as pooled cohort equations for atherosclerotic cardiovascular disease plus 2 newly developed machine learning algorithms.ExposuresPublished stroke-specific algorithms from Framingham and REGARDS (based on self-reported risk factors) as well as pooled cohort equations for atherosclerotic cardiovascular disease plus 2 newly developed machine learning algorithms.Models were designed to estimate the 10-year risk of new-onset stroke (ischemic or hemorrhagic). Discrimination concordance index (C index) and calibration ratios of expected vs observed event rates were assessed at 10 years. Analyses were conducted by race, sex, and age groups.Main Outcomes and MeasuresModels were designed to estimate the 10-year risk of new-onset stroke (ischemic or hemorrhagic). Discrimination concordance index (C index) and calibration ratios of expected vs observed event rates were assessed at 10 years. Analyses were conducted by race, sex, and age groups.The combined study sample included 62 482 participants (median age, 61 years, 54% women, and 29% Black individuals). Discrimination C indexes were not significantly different for the 2 stroke-specific models (Framingham stroke, 0.72; 95% CI, 0.72-073; REGARDS self-report, 0.73; 95% CI, 0.72-0.74) vs the pooled cohort equations (0.72; 95% CI, 0.71-0.73): differences 0.01 or less (P values >.05) in the combined sample. Significant differences in discrimination were observed by race: the C indexes were 0.76 for all 3 models in White vs 0.69 in Black women (all P values <.001) and between 0.71 and 0.72 in White men and between 0.64 and 0.66 in Black men (all P values ≤.001). When stratified by age, model discrimination was better for younger (<60 years) vs older (≥60 years) adults for both Black and White individuals. The ratios of observed to expected 10-year stroke rates were closest to 1 for the REGARDS self-report model (1.05; 95% CI, 1.00-1.09) and indicated risk overestimation for Framingham stroke (0.86; 95% CI, 0.82-0.89) and pooled cohort equations (0.74; 95% CI, 0.71-0.77). Performance did not significantly improve when novel machine learning algorithms were applied.ResultsThe combined study sample included 62 482 participants (median age, 61 years, 54% women, and 29% Black individuals). Discrimination C indexes were not significantly different for the 2 stroke-specific models (Framingham stroke, 0.72; 95% CI, 0.72-073; REGARDS self-report, 0.73; 95% CI, 0.72-0.74) vs the pooled cohort equations (0.72; 95% CI, 0.71-0.73): differences 0.01 or less (P values >.05) in the combined sample. Significant differences in discrimination were observed by race: the C indexes were 0.76 for all 3 models in White vs 0.69 in Black women (all P values <.001) and between 0.71 and 0.72 in White men and between 0.64 and 0.66 in Black men (all P values ≤.001). When stratified by age, model discrimination was better for younger (<60 years) vs older (≥60 years) adults for both Black and White individuals. The ratios of observed to expected 10-year stroke rates were closest to 1 for the REGARDS self-report model (1.05; 95% CI, 1.00-1.09) and indicated risk overestimation for Framingham stroke (0.86; 95% CI, 0.82-0.89) and pooled cohort equations (0.74; 95% CI, 0.71-0.77). Performance did not significantly improve when novel machine learning algorithms were applied.In this analysis of Black and White individuals without stroke or transient ischemic attack among 4 US cohorts, existing stroke-specific risk prediction models and novel machine learning techniques did not significantly improve discriminative accuracy for new-onset stroke compared with the pooled cohort equations, and the REGARDS self-report model had the best calibration. All algorithms exhibited worse discrimination in Black individuals than in White individuals, indicating the need to expand the pool of risk factors and improve modeling techniques to address observed racial disparities and improve model performance.Conclusions and RelevanceIn this analysis of Black and White individuals without stroke or transient ischemic attack among 4 US cohorts, existing stroke-specific risk prediction models and novel machine learning techniques did not significantly improve discriminative accuracy for new-onset stroke compared with the pooled cohort equations, and the REGARDS self-report model had the best calibration. All algorithms exhibited worse discrimination in Black individuals than in White individuals, indicating the need to expand the pool of risk factors and improve modeling techniques to address observed racial disparities and improve model performance. Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals. Quality risk prediction algorithms, free of bias, are key for comprehensive prevention strategies. To compare the performance of stroke-specific algorithms with pooled cohort equations developed for atherosclerotic cardiovascular disease for the prediction of new-onset stroke across different subgroups (race, sex, and age) and to determine the added value of novel machine learning techniques. Retrospective cohort study on combined and harmonized data from Black and White participants of the Framingham Offspring, Atherosclerosis Risk in Communities (ARIC), Multi-Ethnic Study for Atherosclerosis (MESA), and Reasons for Geographical and Racial Differences in Stroke (REGARDS) studies (1983-2019) conducted in the US. The 62 482 participants included at baseline were at least 45 years of age and free of stroke or transient ischemic attack. Published stroke-specific algorithms from Framingham and REGARDS (based on self-reported risk factors) as well as pooled cohort equations for atherosclerotic cardiovascular disease plus 2 newly developed machine learning algorithms. Models were designed to estimate the 10-year risk of new-onset stroke (ischemic or hemorrhagic). Discrimination concordance index (C index) and calibration ratios of expected vs observed event rates were assessed at 10 years. Analyses were conducted by race, sex, and age groups. The combined study sample included 62 482 participants (median age, 61 years, 54% women, and 29% Black individuals). Discrimination C indexes were not significantly different for the 2 stroke-specific models (Framingham stroke, 0.72; 95% CI, 0.72-073; REGARDS self-report, 0.73; 95% CI, 0.72-0.74) vs the pooled cohort equations (0.72; 95% CI, 0.71-0.73): differences 0.01 or less (P values >.05) in the combined sample. Significant differences in discrimination were observed by race: the C indexes were 0.76 for all 3 models in White vs 0.69 in Black women (all P values <.001) and between 0.71 and 0.72 in White men and between 0.64 and 0.66 in Black men (all P values ≤.001). When stratified by age, model discrimination was better for younger (<60 years) vs older (≥60 years) adults for both Black and White individuals. The ratios of observed to expected 10-year stroke rates were closest to 1 for the REGARDS self-report model (1.05; 95% CI, 1.00-1.09) and indicated risk overestimation for Framingham stroke (0.86; 95% CI, 0.82-0.89) and pooled cohort equations (0.74; 95% CI, 0.71-0.77). Performance did not significantly improve when novel machine learning algorithms were applied. In this analysis of Black and White individuals without stroke or transient ischemic attack among 4 US cohorts, existing stroke-specific risk prediction models and novel machine learning techniques did not significantly improve discriminative accuracy for new-onset stroke compared with the pooled cohort equations, and the REGARDS self-report model had the best calibration. All algorithms exhibited worse discrimination in Black individuals than in White individuals, indicating the need to expand the pool of risk factors and improve modeling techniques to address observed racial disparities and improve model performance. |
| Author | Pencina, Michael J Xian, Ying Henao, Ricardo Cary, Michael Berchuck, Samuel Hong, Chuan Judd, Suzanne E Howard, George Kissela, Brett Hall, Jennifer L Engelhard, Matthew M Wojdyla, Daniel M D'Agostino, Sr, Ralph |
| Author_xml | – sequence: 1 givenname: Chuan surname: Hong fullname: Hong, Chuan organization: Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Durham, North Carolina – sequence: 2 givenname: Michael J surname: Pencina fullname: Pencina, Michael J organization: Duke Clinical Research Institute, Durham, North Carolina – sequence: 3 givenname: Daniel M surname: Wojdyla fullname: Wojdyla, Daniel M organization: Duke Clinical Research Institute, Durham, North Carolina – sequence: 4 givenname: Jennifer L surname: Hall fullname: Hall, Jennifer L organization: American Heart Association, Dallas, Texas – sequence: 5 givenname: Suzanne E surname: Judd fullname: Judd, Suzanne E organization: School of Public Health, University of Alabama at Birmingham, Birmingham, Alabama – sequence: 6 givenname: Michael surname: Cary fullname: Cary, Michael organization: Duke University School of Nursing, Durham, North Carolina – sequence: 7 givenname: Matthew M surname: Engelhard fullname: Engelhard, Matthew M organization: Department of Biostatistics & Bioinformatics, Duke University School of Medicine, Durham, North Carolina – sequence: 8 givenname: Samuel surname: Berchuck fullname: Berchuck, Samuel organization: Department of Statistical Science, Duke University School of Medicine, Durham, North Carolina – sequence: 9 givenname: Ying surname: Xian fullname: Xian, Ying organization: Department of Neurology, University of Texas Southwestern Medical Center, Dallas – sequence: 10 givenname: Ralph surname: D'Agostino, Sr fullname: D'Agostino, Sr, Ralph organization: Department of Mathematics & Statistics, Boston University Arts and Sciences, Boston, Massachusetts – sequence: 11 givenname: George surname: Howard fullname: Howard, George organization: School of Public Health, University of Alabama at Birmingham, Birmingham, Alabama – sequence: 12 givenname: Brett surname: Kissela fullname: Kissela, Brett organization: College of Medicine, University of Cincinnati, Cincinnati, Ohio – sequence: 13 givenname: Ricardo surname: Henao fullname: Henao, Ricardo organization: Department of Electrical and Computer Engineering, Duke University, Durham, North Carolina |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36692561$$D View this record in MEDLINE/PubMed |
| BookMark | eNpN0D1PwzAQBmALFdEPmNmQR4am-COJ7bFUUJCKQBTEGLn2BdImcbETRP89EbQSt9yr06N3uCHq1a4GhM4pmVBC6NVaV3rCCGMTFqeSH6EBTbiMeKJk71_uo2EIa9IN5eIE9XmaKpakdIDgyYMtTFN8AZ4a03ptdtjleNl4twH8XIQNPhBX4wdnoQyd9C4EfF1qs8G6tvjto2g6rQ2M8RK-x7_H6TvguXftNpyi41yXAc72e4Reb29eZnfR4nF-P5suIhMz1kSWaLtKrFSUx4QasEwTZagQTHBm85UxMokJ5CyhsbRU5oammislhU01lSkbocu_3q13ny2EJquKYKAsdQ2uDRkTqeKCC8U6erGn7aoCm219UWm_yw6vYT_AIWaL |
| CitedBy_id | crossref_primary_10_1136_bmjqs_2022_015874 crossref_primary_10_5498_wjp_v15_i3_99152 crossref_primary_10_1002_jhm_13294 crossref_primary_10_1002_VIW_20240059 crossref_primary_10_1177_10784535231211682 crossref_primary_10_2196_75608 crossref_primary_10_1007_s00330_025_11979_2 crossref_primary_10_1177_17474930241293408 crossref_primary_10_1016_j_atherosclerosis_2023_117275 crossref_primary_10_3390_life15010094 crossref_primary_10_1016_j_ejrad_2024_111357 crossref_primary_10_1097_CCE_0000000000001059 crossref_primary_10_3390_bioengineering11020140 crossref_primary_10_1161_JAHA_124_036946 crossref_primary_10_2196_72497 crossref_primary_10_1016_j_artmed_2025_103130 crossref_primary_10_1161_STR_0000000000000475 crossref_primary_10_1016_j_jns_2024_123367 crossref_primary_10_1161_CIR_0000000000001209 crossref_primary_10_1093_eurjpc_zwaf164 crossref_primary_10_1016_j_compbiomed_2024_108632 crossref_primary_10_1016_j_jbi_2024_104664 crossref_primary_10_1038_s43856_025_00939_y crossref_primary_10_1016_j_ejrad_2024_111867 crossref_primary_10_1016_j_ucl_2025_07_005 crossref_primary_10_1097_IJG_0000000000002367 crossref_primary_10_1161_CIRCOUTCOMES_123_009938 crossref_primary_10_1097_IJG_0000000000002449 crossref_primary_10_1093_jamia_ocae056 crossref_primary_10_1016_j_outlook_2025_102395 crossref_primary_10_7759_cureus_68150 crossref_primary_10_1016_j_jbi_2023_104532 crossref_primary_10_1001_jamanetworkopen_2023_31460 crossref_primary_10_1007_s00383_025_06163_y crossref_primary_10_1002_mco2_70234 crossref_primary_10_3389_fneur_2025_1668420 crossref_primary_10_1080_07853890_2025_2506482 crossref_primary_10_1007_s00464_025_11751_z crossref_primary_10_1038_s44325_024_00031_9 crossref_primary_10_1001_jama_2023_20099 crossref_primary_10_1093_ajh_hpae008 crossref_primary_10_1177_10784535241249193 crossref_primary_10_1038_s41598_025_91157_y crossref_primary_10_1038_s41598_024_51402_2 crossref_primary_10_1161_CIR_0000000000001303 crossref_primary_10_1515_labmed_2023_0037 crossref_primary_10_1038_s41551_025_01413_9 crossref_primary_10_1161_CIR_0000000000001191 crossref_primary_10_3389_fnins_2024_1411538 crossref_primary_10_1111_dom_16241 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1001/jama.2022.24683 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1538-3598 |
| ExternalDocumentID | 36692561 |
| Genre | Journal Article Comparative Study Research Support, N.I.H., Extramural |
| GeographicLocations | United States |
| GeographicLocations_xml | – name: United States |
| GrantInformation_xml | – fundername: NIMH NIH HHS grantid: K01 MH127309 – fundername: NINDS NIH HHS grantid: U01 NS041588 – fundername: NINDS NIH HHS grantid: R61 NS120246 |
| GroupedDBID | --- -ET -~X .55 .XZ 0R~ 0WA 186 18M 29J 2CT 2FS 2KS 2WC 354 39C 4.4 53G 5GY 5RE 6TJ 85S AAIKC AAMNW AAQQT AAWTL ABBLC ABCQX ABEHJ ABIVO ABOCM ABPMR ABPPZ ABRSH ABWJO ACAHW ACGFS ACNCT ACPRK ADBBV ADUKH ADXHL AFCHL AFFNX AFRAH AGHSJ AHMBA ALMA_UNASSIGNED_HOLDINGS AMJDE ANMPU ARBJA BKOMP BRYMA C45 CGR CJ0 CS3 CUY CVF EAM EBD EBS ECM EIF EJD EMOBN EX3 F5P H13 HF~ KOO KQ8 L7B MVM N4W N9A NEJ NPM OBH OCB OGEVE OHH OMK OVD P2P PQQKQ RAJ RNS SJN SV3 TEORI TN5 UHB UKR UPT VVN WH7 WOW X7M XHN XSW XZL YFH YOC YPV YQT YQY YR2 YR5 YSK YYM YZZ ZCA ~H1 7X8 |
| ID | FETCH-LOGICAL-c422t-d0adb5d8913401ced2a09c1772732dfbcc8540ef25148d18fc16a39987d6a1862 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 57 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000987382900019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1538-3598 |
| IngestDate | Thu Sep 04 20:30:02 EDT 2025 Mon Jul 21 05:32:24 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c422t-d0adb5d8913401ced2a09c1772732dfbcc8540ef25148d18fc16a39987d6a1862 |
| Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/10408266 |
| PMID | 36692561 |
| PQID | 2769373792 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2769373792 pubmed_primary_36692561 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-01-24 20230124 |
| PublicationDateYYYYMMDD | 2023-01-24 |
| PublicationDate_xml | – month: 01 year: 2023 text: 2023-01-24 day: 24 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | JAMA : the journal of the American Medical Association |
| PublicationTitleAlternate | JAMA |
| PublicationYear | 2023 |
| References | 37747715 - JAMA. 2023 Oct 17;330(15):1494. doi: 10.1001/jama.2023.20099 |
| References_xml | – reference: 37747715 - JAMA. 2023 Oct 17;330(15):1494. doi: 10.1001/jama.2023.20099 |
| SSID | ssj0000137 |
| Score | 2.6012344 |
| Snippet | Stroke is the fifth-highest cause of death in the US and a leading cause of serious long-term disability with particularly high risk in Black individuals.... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 306 |
| SubjectTerms | Age Factors Atherosclerosis - epidemiology Bias Black or African American Black People - statistics & numerical data Cardiovascular Diseases - epidemiology Computer Simulation - standards Computer Simulation - statistics & numerical data Female Healthcare Disparities - ethnology Healthcare Disparities - standards Healthcare Disparities - statistics & numerical data Humans Ischemic Attack, Transient - epidemiology Machine Learning - standards Male Middle Aged Prejudice - prevention & control Race Factors - statistics & numerical data Reproducibility of Results Retrospective Studies Risk Assessment - standards Sex Factors Stroke - diagnosis Stroke - epidemiology Stroke - ethnology United States - epidemiology White People - statistics & numerical data |
| Title | Predictive Accuracy of Stroke Risk Prediction Models Across Black and White Race, Sex, and Age Groups |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/36692561 https://www.proquest.com/docview/2769373792 |
| Volume | 329 |
| WOSCitedRecordID | wos000987382900019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwGA3qRHzxfpk3IvhotU3TJH2SIQ4f3Bibwt5GrjIm7Ww30X9vkrXMF0HwpZSQQkm-y8n3hXMAuBLCEJtHaIBkiAMsYhkIZP1RRIZglVAcar_TT7TbZcNh2qsKbmV1rbKOiT5Qq1y6GvktcqJ9NKYpupu-B041ynVXKwmNVdCILZRxVk2H7Ad9lOfM9E7tmOpqap8l6xBCNwgTxxn4G770eaa9_d8_3AFbFcKErYVJ7IIVne2BjU7VQ98Hule4dxfmYEvKecHlF8wNHMyKfKJhf1xOYD0lz6ATS3sr7UyXTqGv90GeKeiV9WCfS30NB_rz2g-2XjX01azyALy0H57vH4NKbCGQGKFZoEKuRKJc19IeuaRWiIepjKjDN0gZISWz4E4bi4cwUxEzMiLcLjmjivDInosOwVqWZ_oYQMqjhCqL2okRmBPKE0bSRDM7qhmJdRNc1gs4ssbsOhQ80_m8HC2XsAmOFrswmi5YN0YxIanFZ9HJH74-BZtOFt6VShA-Aw1jXVmfg3X5MRuXxYW3Evvs9jrfCerFFA |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Predictive+Accuracy+of+Stroke+Risk+Prediction+Models+Across+Black+and+White+Race%2C+Sex%2C+and+Age+Groups&rft.jtitle=JAMA+%3A+the+journal+of+the+American+Medical+Association&rft.au=Hong%2C+Chuan&rft.au=Pencina%2C+Michael+J&rft.au=Wojdyla%2C+Daniel+M&rft.au=Hall%2C+Jennifer+L&rft.date=2023-01-24&rft.eissn=1538-3598&rft.volume=329&rft.issue=4&rft.spage=306&rft_id=info:doi/10.1001%2Fjama.2022.24683&rft_id=info%3Apmid%2F36692561&rft_id=info%3Apmid%2F36692561&rft.externalDocID=36692561 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1538-3598&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1538-3598&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1538-3598&client=summon |