-
Effective risk detection and prevention.
-
Personalized medicine and Treatment planning.
-
Public health interventions.
-
https://www.kaggle.com/datasets/sulianova/cardiovascular-disease-dataset
-
The dataset consists of 70,000 records of patients data, 12 features + target. There are 3 types of input features:
Objective: Factual information
Examination: Results of medical examination
Subjective: Information given by the patient
- Accuracy Precision Recall F1_score
DecisionTree 0.715 0.769 0.626 0.6904
**Random Forest 0.733 0.727 0.727 0.724**
KNN 0.682 0.682 0.682 0.682
NN 0.618 0.701 0.618 0.570
Naïve Bayes 0.586 0.642 0.586 0.537
Random Forest wins!
What is a leading cause of death worldwide? Cardiovascular disease (CVD) is indeed a leading cause of death worldwide.
-
According to the World Health Organization (WHO), CVDs were responsible for an estimated 17.9 million deaths in 2019, accounting for 32% of all global deaths.
-
In contrast, cancer was responsible for an estimated 9.6 million deaths in the same year, accounting for 17% of all global deaths.
-
"In 2016, CVD cost America $555 billion. By 2035, the cost will skyrocket to $1.1 trillion."
-
Cardiovascular disease not only exacts a heavy toll on the health of Americans, its economic burden is enormous. It is America's costliest disease, and it will soar in the coming decades.
-
Artificial intelligence (AI) has the potential to revolutionize the prevention, diagnosis, and management of CVD in a number of ways.
-
Risk prediction and prevention: AI can help predict an individual's risk of developing CVD by analyzing large amounts of patient data which is highly valuable in research institutions.
-
Treatment planning : AI can help healthcare providers develop personalized treatment plans for patients with CVD based on their individual characteristics, such as their age, sex, and medical history.
- Journal The Lancet Digital Health in 2017 found that a machine learning algorithm was able to accurately predict cardiovascular events. Using machine learning for routine clinical data of 378,256 patients from UK in risk prediction could lead to cost savings save £132 million over ten years in UK.
-
CARDIOVASCULAR DISEASE: A COSTLY BURDEN FOR AMERICA PROJECTIONS THROUGH 2035. (2017). American Heart Association. Retrieved April 21, 2023, from https://www.heart.org/-/media/Files/About-Us/Policy-Research/Fact-Sheets/Public-Health-Advocacy-and-Research/CVD-A-Costly-Burden-for-America-Projections-Through-2035.pdf
-
Weng, S., Reps, J., Kai, J., Garibaldi, J. M., & Qureshi, N. (2017). Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLOS ONE, 12(4), e0174944. https://doi.org/10.1371/journal.pone.0174944
-
World Health Organization: WHO. (2019a). Cancer. www.who.int. https://www.who.int/health-topics/cancer#tab=tab_1
-
World Health Organization: WHO. (2021, June 11). Cardiovascular diseases (CVDs). www.who.int. Retrieved April 21, 2023, from https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds){.uri}