Heart Failure Prediction using Machine Learning with Exploratory Data Analysis

Agrawal, Harsh; Chandiwala, Janki; Agrawal, Sarvesh; Goyal, Yash

doi:10.1109/conit51480.2021.9498561

Cited by 13 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further examine the effects of binning verses using continuous variables in a model a second dataset was evaluated with supervised learning. The Framingham dataset was downloader from Kaggle on February 20, 2022 [21], and it has been used in several recent studies [22]- [24]. The Framingham heart study is a longitudinal cohort study of cardiovascular disease risk, which includes continuous variables for age, cholesterol, SBP, BMI and fasting plasma glucose [25].…”

Section: Discussionmentioning

confidence: 99%

Predicting cardiovascular disease using different blood pressure guidelines

Bopp

Briggs

Orlando

et al. 2023

IJPHS

View full text Add to dashboard Cite

The criteria used to categorize patients as either hypertensive or normotensive were changed in 2017 by the American Heart Association and the American College of Cardiology (AHA/ACC). The updated guidelines lowered the criteria by which individuals are classified as hypertensive; systolic blood pressure (SBP) cut-off from ≥140 mmHg to ≥130 mmHg and diastolic blood pressure from ≥90 mmHg to ≥80 mmHg. The purpose of this study was to investigate what effect these changes in diagnostic criteria had on the ability of supervised learning to predict cardiovascular disease. Three models were developed and tested. Two models using a binned hypertension measure based on either the AHA/ACC new released guidelines or the Joint National Committee on the Prevention, Detection, Evaluation, and Treatment of High Blood Pressure (JNC7) original guidelines. The third model used SBP as a continuous variable. Data from 68,657 patients was processed through decision tree algorithm to determine which model offered the best accuracy. For both female and male subjects, the model with SBP returned the best area under the receiver operator characteristic curve and overall better sensitivity and specificity values. Our results showed that changing the criteria by which individuals are classified as hypertensive or normotensive negatively impacted the ability of decision tree to predict cardiovascular disease in both females and males.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting cardiovascular disease using different blood pressure guidelines

Bopp

Briggs

Orlando

et al. 2023

IJPHS

View full text Add to dashboard Cite

show abstract

“…Unfortunately, the requirement of knowing the propensities of logged actions disqualifies some bandit algorithms from data collection. For example, the posterior distributions of some Bayesian bandits (such as linear Thompson sampling (Agrawal and Goyal 2013)) do not allow for efficient computation of propensities. They can be approximated using Monte Carlo methods, but this can bias offline evaluation.…”

Section: Practical Considerations and Challengesmentioning

confidence: 99%

Recommendations as treatments

Joachims

London

et al. 2021

AI Magazine

View full text Add to dashboard Cite

In recent years, a new line of research has taken an interventional view of recommender systems, where recommendations are viewed as actions that the system takes to have a desired effect. This interventional view has led to the development of counterfactual inference techniques for evaluating and optimizing recommendation policies. This article explains how these techniques enable unbiased offline evaluation and learning despite biased data, and how they can inform considerations of fairness and equity in recommender systems.

show abstract

“…Heart disease is also known as coronary artery disease. Common symptoms of heart disease, such as chest pain and high or low blood pressure, vary from person to person [4].…”

Section: Introductionmentioning

confidence: 99%

“…If the clot is large, it will block blood flow through the blood vessels to the heart arteries. Causes of cardiac muscle death are chemical elements and nutrition (ischemia) [4]. Heart disease is the main cause of death every year in the world.…”

Section: Introductionmentioning

confidence: 99%

K Value Effect on Accuracy Using the K-NN for Heart Failure Dataset

Masitha,

Biddinika,

Herman

2023

matrik

View full text Add to dashboard Cite

Heart failure is included in the category of cardiovascular disease. Heart disease is not easy to detect, and its detection needs to be done by experienced and skilled medical professionals. Most patients with heart failure require hospitalization. Common symptoms of heart disease, such as chest pain and high or low blood pressure, vary from person to person. This study aims to find the most optimal k value based on the accuracy obtained based on calculations by testing different k values, namely 1, 3, 5, 7, and 9. After getting the results of the accuracy of the five k values, compare which accuracy has the highest value, best for K-Nearest Neighbor (K-NN) models. The classification process uses the K-NN algorithm. This algorithm is quite easy to use because some parameters work using distance metrics and k values. Therefore, the value of k in the K-NN algorithm greatly affects the accuracy that will be produced. In the results of this study, the accuracy obtained was k = 7 and k = 9, which are the most optimal results because they have the highest accuracy compared to other k values, with an accuracy of 88%. The expected benefit of this research is that it can make a scientific contribution to research in the field of machine learning classification, especially in predicting heart failure

show abstract

Heart Failure Prediction using Machine Learning with Exploratory Data Analysis

Cited by 13 publications

References 10 publications

Predicting cardiovascular disease using different blood pressure guidelines

Predicting cardiovascular disease using different blood pressure guidelines

Recommendations as treatments

K Value Effect on Accuracy Using the K-NN for Heart Failure Dataset

Contact Info

Product

Resources

About