Arrow
use cases

Predict Cardiovascular Diseases

CVDs cause millions of deaths and high costs; AI can identify high-risk patients, improve care, and reduce expenses.

Problem

Cardiovascular diseases (CVDs) encompass a broad spectrum of disorders affecting the heart and blood vessels, including coronary artery disease, stroke, heart failure, and peripheral artery disease. These conditions collectively stand as the leading cause of mortality globally, surpassing deaths from all cancers and chronic lower respiratory diseases combined (1)(2). In the United States alone, CVDs annually claim approximately 19 million lives. The economic impact is substantial, with these diseases costing the U.S. economy an estimated $378 billion in 2018, encompassing direct healthcare costs, productivity losses, and premature death (3)(4). The prevalence of CVDs among American adults is staggering, with an estimated 126.9 million affected individuals. Key risk factors such as hypertension, high cholesterol, diabetes, obesity, physical inactivity, smoking, and unhealthy dietary habits significantly contribute to the onset and progression of CVDs (5)(6). Moreover, disparities in healthcare access and socioeconomic factors exacerbate the burden, disproportionately affecting underserved populations and minority communities (7).

Why it matters

  • Leading global cause of death, exceeding cancer and chronic lower respiratory diseases combined.
  • In the US, annually causes 19 million deaths and costs $378 billion, impacting productivity and healthcare expenditure.
  • 126.9 million adults in the US affected, linked to hypertension, high cholesterol, diabetes, obesity, inactivity, smoking, and poor diets.
  • Disparities in healthcare access and socioeconomic factors worsen burdens on underserved and minority groups.

Solution

CardioRiskAI: An AI model that predicts cardiovascular disease risk using patient data, integrating age, sex, blood pressure, cholesterol levels and lifestyle factors to early identify people at risk and tailor interventions.

User person:  Cardiologists, Internal Medicine Specialists, Hospital and Healthcare Administrators, Cardiovascular Health Researchers.

Discover more and interact with our AI!

Datasources

A heart disease dataset was used, from a multi-specialty hospital in India and available on Kaggle, which covers essential features for research and early detection of heart diseases. With data from 1000 subjects and 12 key attributes, including age, sex, resting blood pressure, serum cholesterol levels and various clinical indicators.

Citations

  1. S. Bahendeka, S. Colagiuri, S Mendis. (2013). Organización mundial de la salud, “Enfermedades cardiovasculares”Organización mundial de la salud. https://iris.who.int/bitstream/handle/10665/112396/9789243548395_spa.pdf
  2. Connie W. MD, Aaron, W. Aday, MD. (2022). Actualización de estadísticas sobre enfermedades cardíacas y ataques o derrames cerebrales. American Heart Association. https://professional.heart.org/-/media/PHD-Files-2/Science-News/2/2022-Heart-and-Stroke-Stat-Update/Translated-Materials/2022-Stat-Update-at-a-Glance-Spanish.pdf
  3. Adam, T. Nick T. Aleksandra T. (2019). European Society of Cardiology: Cardiovascular Disease Statistics.European Society of Cardiology: Cardiovascular Disease Statistics. European Herat Jornual. https://professional.heart.org/-/media/PHD-Files-2/Science-News/2/2022-Heart-and-Stroke-Stat-Update/Translated-Materials/2022-Stat-Update-at-a-Glance-Spanish.pdf
  4. K. Saikumar, V. Rajesh. (2022). A machine intelligence technique for predicting cardiovascular disease (CVD) using Radiology Dataset. Springer Link. https://link.springer.com/article/10.1007/s13198-022-01681-7
  5. Aqsa, R. Yawar R. Farooque, A. (2021). An Integrated Machine Learning Framework for Effective Prediction of Cardiovascular Diseases. IEEE Xplore. https://ieeexplore.ieee.org/abstract/document/9491140
  6. Eduardo. P, Yawar, R. Farooque, A. (2017). Burden, anxiety and depression in the caregiver of cerebrovascular disease patients. Sciencedirect. https://www.sciencedirect.com/science/article/pii/S0121737217300493
  7. (2019). World Health Organization cardiovascular disease risk charts: revised models to estimate risk in 21 global regions. The Lancet Global Health. https://www.thelancet.com/journals/langlo/article/PIIS2214-109X(19)30318-3/fulltex

Book a Free Consultation

Trusted by the world's top healthcare institutions