This dataset documents rates and trends in heart disease and stroke mortality. Specifically, this report presents county (or county equivalent) estimates of heart disease and stroke death rates in 2000-2019 and trends during two intervals (2000-2010, 2010-2019) by age group (ages 35–64 years, ages 65 years and older), race/ethnicity (non-Hispanic American Indian/Alaska Native, non-Hispanic Asian/Pacific Islander, non-Hispanic Black, Hispanic, non-Hispanic White), and sex (women, men). The rates and trends were estimated using a Bayesian spatiotemporal model and a smoothed over space, time, and demographic group. Rates are age-standardized in 10-year age groups using the 2010 US population. Data source: National Vital Statistics System.

From 2017 to 2020, around 14 percent of males and females in the United States aged 80 years and older suffered from a stroke. This statistic shows the prevalence of stroke among U.S. adults from 2017 to 2020, by age and gender.

2020 - 2022, county-level U.S. stroke death rates. Dataset developed by the Centers for Disease Control and Prevention, Division for Heart Disease and Stroke Prevention.Create maps of U.S. stroke death rates by county. Data can be stratified by age, race/ethnicity, and sex.Visit the CDC Atlas of Heart Disease and Stroke for additional data and maps. Atlas of Heart Disease and StrokeData SourceMortality data were obtained from the National Vital Statistics System. Bridged-Race Postcensal Population Estimates were obtained from the National Center for Health Statistics. International Classification of Diseases, 10th Revision (ICD-10) codes: I60-I69; underlying cause of death.Data DictionaryData for counties with small populations are not displayed when a reliable rate could not be generated. These counties are represented in the data with values of '-1.' CDC excludes these values when classifying the data on a map, indicating those counties as 'Insufficient Data.'Data field names and descriptionsstcty_fips: state FIPS code + county FIPS codeOther fields use the following format: RRR_S_aaaa (e.g., API_M_35UP)  RRR: 3 digits represent race/ethnicity    All - Overall    AIA - American Indian and Alaska Native, non-Hispanic    ASN - Asian, non-Hispanic    BLK - Black, non-Hispanic    HIS - Hispanic NHP – Native Hawaiian or Other Pacific Islander, non-Hispanic MOR – More than one race, non-Hispanic    WHT - White, non-Hispanic  S: 1 digit represents sex    A - All    F - Female    M - Male  aaaa: 4 digits represent age. The first 2 digits are the lower bound for age and the last 2 digits are the upper bound for age. 'UP' indicates the data includes the maximum age available and 'LT' indicates ages less than the upper bound. Example: The column 'BLK_M_65UP' displays rates per 100,000 black men aged 65 years and older.MethodologyRates are calculated using a 3-year average and are age-standardized in 10-year age groups using the 2000 U.S. Standard Population. Rates are calculated and displayed per 100,000 population. Rates were spatially smoothed using a Local Empirical Bayes algorithm to stabilize risk by borrowing information from neighboring geographic areas, making estimates more statistically robust and stable for counties with small populations. Data for counties with small populations are coded as '-1' when a reliable rate could not be generated. County-level rates were generated when the following criteria were met over a 3-year time period within each of the filters (e.g., age, race, and sex).At least one of the following 3 criteria:At least 20 events occurred within the county and its adjacent neighbors.ORAt least 16 events occurred within the county.ORAt least 5,000 population years within the county.AND all 3 of the following criteria:At least 6 population years for each age group used for age adjustment if that age group had 1 or more event.The number of population years in an age group was greater than the number of events.At least 100 population years within the county.More Questions?Interactive Atlas of Heart Disease and StrokeData SourcesStatistical Methods

2016 to 2018, 3-year average. Rates are age-standardized. County rates are spatially smoothed. The data can be viewed by sex and race/ethnicity. Data source: National Vital Statistics System. Additional data, maps, and methodology can be viewed on the Interactive Atlas of Heart Disease and Stroke https://www.cdc.gov/heart-disease-stroke-atlas/about/index.html

In 2022, Delaware had the highest rate of death due to stroke of any U.S. state, with around 57 deaths per 100,000 population. This statistic shows the death rate for stroke in the United States in 2022, by state.

Create maps of U.S. stroke death rates by county. Data can be stratified by age, race/ethnicity, and sex. Visit the CDC/DHDSP Atlas of Heart Disease and Stroke for additional data and maps. Atlas of Heart Disease and StrokeData SourceMortality data were obtained from the National Vital Statistics System. Bridged-Race Postcensal Population Estimates were obtained from the National Center for Health Statistics. International Classification of Diseases, 10th Revision (ICD-10) codes: I60-I69; underlying cause of death.Data DictionaryData for counties with small populations are not displayed when a reliable rate could not be generated. These counties are represented in the data with values of '-1.' CDC/DHDSP excludes these values when classifying the data on a map, indicating those counties as 'Insufficient Data.' Data field names and descriptionsstcty_fips: state FIPS code + county FIPS codeOther fields use the following format: RRR_S_aaaa (e.g., API_M_35UP)   RRR: 3 digits represent race/ethnicity     All - Overall     AIA - American Indian and Alaska Native, non-Hispanic     API - Asian and Pacific Islander, non-Hispanic     BLK - Black, non-Hispanic     HIS - Hispanic     WHT - White, non-Hispanic   S: 1 digit represents sex     A - All    F - Female     M - Male  aaaa: 4 digits represent age. The first 2 digits are the lower bound for age and the last 2 digits are the upper bound for age. 'UP' indicates the data includes the maximum age available and 'LT' indicates ages less than the upper bound.  Example: The column 'BLK_M_65UP' displays rates per 100,000 black men aged 65 years and older.MethodologyRates are calculated using a 3-year average and are age-standardized in 10-year age groups using the 2000 U.S. Standard Population. Rates are calculated and displayed per 100,000 population. Rates were spatially smoothed using a Local Empirical Bayes algorithm to stabilize risk by borrowing information from neighboring geographic areas, making estimates more statistically robust and stable for counties with small populations. Data for counties with small populations are coded as '-1' when a reliable rate could not be generated. County-level rates were generated when the following criteria were met over a 3-year time period within each of the filters (e.g., age, race, and sex).At least one of the following 3 criteria: At least 20 events occurred within the county and its adjacent neighbors.ORAt least 16 events occurred within the county.ORAt least 5,000 population years within the county.AND all 3 of the following criteria:At least 6 population years for each age group used for age adjustment if that age group had 1 or more event.The number of population years in an age group was greater than the number of events.At least 100 population years within the county.More Questions?Interactive Atlas of Heart Disease and StrokeData SourcesStatistical Methods

This statistic displays the number of deaths from stroke in England and Wales in 2022, by gender and age. In this year, over 3.8 thousand women aged 85 years and over died of stroke in England and Wales, compared to two thousand men of the same age.

This dataset contains risk-adjusted 30-day mortality and 30-day readmission rates, quality ratings, and number of deaths / readmissions and cases for ischemic stroke treated in California hospitals. This dataset does not include ischemic stroke treated in outpatient settings.

2015 to 2017, 3-year average. Rates are age-standardized. County rates are spatially smoothed. The data can be viewed by sex and race/ethnicity. Data source: National Vital Statistics System. Additional data, maps, and methodology can be viewed on the Interactive Atlas of Heart Disease and Stroke. http://www.cdc.gov/dhdsp/maps/atlas

To reduce deaths from stroke.

As of 2021, there were 20.5 deaths per 100 hospital admissions for stroke among those aged 45 years and older in Latvia. The statistic shows the thirty-day mortality after admission to hospital for ischaemic stroke in selected OECD countries as of 2021, per 100 admissions among adults aged 45 years and older.

In 2022, there were around 45 stroke deaths reported per 100,000 Black women in the West of the United States aged 45 to 64 years. This was the highest stroke death rate for women in this age group among all regions and races/ethnicities that year. Furthermore, the stroke death rate was significantly higher among Black women compared to any other races/ethnicities across all regions.

Stroke Risk Prediction Dataset (Version 2)

Medically Validated, Age-Accurate, and Balanced
Samples: 35,000 | Features: 16 | Targets: 2 (Binary + Regression)

📌 Overview

This dataset is designed for predicting stroke risk using symptoms, demographics, and medical literature-inspired risk modeling. Version 2 significantly improves upon Version 1 by incorporating age-dependent symptom probabilities, gender-specific risk modifiers, and medically validated feature engineering.

Key Enhancements in Version 2:

1. Age-Accurate Risk Modeling:

   • Stroke risk now follows a sigmoidal curve (sharp increase after age 50), reflecting real-world epidemiological trends.
   • Symptom probabilities (e.g., hypertension, chest pain) scale with age (see Medical Validity).

2. Gender-Specific Risk:

   • Males under 60 have 1.5× higher risk, while females over 60 have 1.8× higher risk (post-menopausal hormonal changes).

3. Balanced and Expanded Data:

   • 35,000 samples (vs. 10,000 in Version 1) to improve model generalizability and capture rare symptom combinations.
   • 50% at-risk (stroke risk ≥50%) and 50% not-at-risk (stroke risk <50%).

📊 Dataset Statistics

Age distribution in Version 2 vs. Version 1
https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F21100322%2F6317df05bc7526268853e24a5ce831ba%2FAge%20Distribution%20Plot.png?generation=1740875866152537&alt=media" alt="">

🔬 Medical Validity

This dataset is grounded in peer-reviewed medical literature, with symptom probabilities, risk weights, and demographic relationships directly derived from clinical guidelines and epidemiological studies. Below is a detailed breakdown of how medical knowledge was translated into dataset parameters:

1. Age-Dependent Symptom Probabilities

The prevalence of symptoms increases with age, reflecting real-world clinical observations. Probabilities are calibrated using population-level data from medical literature:

Hypertension (High Blood Pressure)

• Probability by Age: 10% (18–30), 25% (31–50), 45% (51–70), 60% (71–90).
• Source: WHO Global Report on Stroke (2023) identifies hypertension as the leading modifiable stroke risk factor, with prevalence rising from ~12% in adults <30 to ~65% in adults >70.
• Clinical Basis: Arterial stiffness and cumulative vascular damage over time explain the age-dependent increase (Chapter 4, Harrison’s Principles of Internal Medicine).

Chest Pain

• Probability by Age: 5% (18–30), 15% (31–50), 25% (51–70), 35% (71–90).
• Source: The Stroke Book (Cambridge Medicine) notes that chest pain is rare in young adults but becomes prevalent in older populations due to atherosclerosis and coronary artery disease.
• Clinical Basis: Atherosclerotic plaque buildup accelerates after age ...

In 2021, the death rate from stroke among Black non-Hispanic men in the United States aged 35 years and older was almost 126 per 100,000 population. In comparison, the stroke death rate among non-Hispanic white men was about 77 per 100,000 population. This statistic shows the rate of stroke death among Black and White men in the United States aged 35 years and older from 2015 to 2021.

This dataset documents rates and trends in local hypertension-related cardiovascular disease (CVD) death rates. Specifically, this report presents county (or county equivalent) estimates of hypertension-related CVD death rates in 2000-2019 and trends during two intervals (2000-2010, 2010-2019) by age group (ages 35–64 years, ages 65 years and older), race/ethnicity (non-Hispanic American Indian/Alaska Native, non-Hispanic Asian/Pacific Islander, non-Hispanic Black, Hispanic, non-Hispanic White), and sex (female, male). The rates and trends were estimated using a Bayesian spatiotemporal model and a smoothed over space, time, and demographic group. Rates are age-standardized in 10-year age groups using the 2010 US population. Data source: National Vital Statistics System.

This dataset documents cardiovascular disease (CVD) death rates, relative and absolute excess death rates, and trends. Specifically, this report presents county (or county equivalent) estimates of CVD death rates in 2000-2020, trends during 2010-2019, and relative and absolute excess death rates in 2020 by age group (ages 35–64 years, ages 65 years and older). All estimates were generated using a Bayesian spatiotemporal model and a smoothed over space, time, and 10-year age groups. Rates are age-standardized in 10-year age groups using the 2010 US population. Data source: National Vital Statistics System.

Analysis of ‘Stroke Mortality Data Among US Adults (35+) by State/Territory and County’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://catalog.data.gov/dataset/a555fdcf-e15b-4813-b232-e5ef863a272e on 12 February 2022.

--- Dataset description provided by original source is as follows ---

2012 to 2014, 3-year average. Rates are age-standardized. County rates are spatially smoothed. The data can be viewed by gender and race/ethnicity. Data source: National Vital Statistics System. Additional data, maps, and methodology can be viewed on the Interactive Atlas of Heart Disease and Stroke http://www.cdc.gov/dhdsp/maps/atlas

--- Original source retains full ownership of the source dataset ---

2017 to 2019, 3-year average. Rates are age-standardized. County rates are spatially smoothed. The data can be viewed by sex and race/ethnicity. Data source: National Vital Statistics System. Additional data, maps, and methodology can be viewed on the Interactive Atlas of Heart Disease and Stroke https://www.cdc.gov/heart-disease-stroke-atlas/about/index.html

Analysis of ‘Stroke Mortality Data Among US Adults (35+) by State/Territory and County – 2017-2019’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://catalog.data.gov/dataset/6e009bb0-ee1b-4243-a6dc-6c3986422e09 on 12 February 2022.

--- Dataset description provided by original source is as follows ---

2017 to 2019, 3-year average. Rates are age-standardized. County rates are spatially smoothed. The data can be viewed by gender and race/ethnicity. Data source: National Vital Statistics System. Additional data, maps, and methodology can be viewed on the Interactive Atlas of Heart Disease and Stroke http://www.cdc.gov/dhdsp/maps/atlas

--- Original source retains full ownership of the source dataset ---

Strokes, also referred to as Cerebrovascular Disease, was the cause of 51 deaths per 100,000 population in the United Kingdom in 2022. Scotland had the highest rate of mortality across the UK, with 72 deaths from strokes per 100,000.