Abstract
BACKGROUND: The incidence of stroke is increasing in young to middle-aged adults. Assessing risk factors is important in this large population whose comorbidities may differ from older adults. METHODS: In this retrospective cohort analysis of adults aged between 20 and 50 presenting to the Stanford Healthcare system from 1 January 2000 through 31 December 2021, with no prior history of stroke or transient ischemic attack, we studied the effects of 30 risk factors on the primary endpoint of incident ischemic stroke, defined by the presence of the International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10) codes for stroke and confirmed by brain imaging. The secondary endpoint was incident cerebrovascular events defined by the presence of ICD-10 codes for stroke or transient ischemic attacks (TIAs). Associations were measured with time-varying multivariable survival regression. RESULTS: From an overall population of 1.3 million, we identified 540,999 individuals aged 20-50 years. Over the study period, 802 experienced the primary endpoint and 5734 the secondary endpoint. On multivariable analysis, non-cardiovascular risk factors were independently associated with the primary endpoint, adjusting for established cardiovascular risk factors, including sleep apnea [1.44, (1.19, 1.74)], bipolar disorder [1.88, (1.23, 2.86)], cancer [2.07 (1.71, 2.51)], and chronic kidney disease (CKD) [2.2, (1.73, 2.81)]. Other non-cardiovascular associations included ethno-racial subgroups of Black [2.05, (1.60, 2.64)], Pacific Islander [2.56, (1.70, 3.84)], and Hispanic [1.71, (1.37, 2.15)] versus white non-Hispanics. Combining non-cardiovascular risk factors significant on multivariable analysis with established cardiovascular factors significantly improved the C-index for de novo stroke to 0.814 over that obtained in either group alone (P < 0.05). CONCLUSIONS: In this large population of young adults, several non-cardiovascular factors conferred risk for incident stroke independent of known cardiovascular risk factors and, in combination, significantly improved the prediction of incident stroke over those based on either group of factors alone. These findings may have implications for assessing risk in younger patients with distinct comorbidities.