|
|
Cardiovascular Disease Prediction for Early Diagnosis
medical

Cardiovascular Disease Prediction for Early Diagnosis

Cardiovascular disease (CVD) prediction is a diagnosis tool which can help cardiologists and physicians face the hurdle of catching CVD threats early on. Indeed, 80% of morbid events due to CVD are preventable. TADA helps physicians diagnose cardiovascular disease earlier.

Industry

Healthcare

Project Duration and Effort

One day

Type of Prediction

Binary Classification

Customer Benefits

  1. 83% accuracy in identifying cardiovascular disease based on standard medical examinations and symptoms: stress test, blood pressure, angina, fluoroscopy.
  2. Results available in a few minutes.
  3. Rapid identification of crucial diagnosis criteria in minutes.

Problem to solve

Cardiovascular diseases are the first cause of lethality in the world today. CVD accounts for 45% of all deaths in Europe, 46 times the number of deaths caused by AIDS, tuberculosis, and malaria combined. There are 2,353 deaths from CVD each day in the U.S., based on 2017 data. 

The General Practitioner (GP) is the first physician to diagnose heart diseases based on chest pain symptoms. An independent study shows that the GP’s diagnosis yields 69% of sensitivity and 89% specificity. The next physician in line for diagnosis is the cardiologist. He/She can perform several tests, including electrocardiogram (ECG), exercise stress tests, X-rays, echocardiogram, blood tests, coronary angiography, radionuclide tests, MRI scans, CT scans. ECG, stress tests, and fluoroscopy are standard exams performed on patients suspected of CVD. 

Some of these test results, combined with patient information and symptoms, constitute a data set from which we intend to extract an early CVD diagnosis using TADA. The dataset is composed of 303 patients and includes the following 13 variables: 

  1. Resting blood pressure,
  2. Fasting blood pressure, 
  3. Resting ECG values,
  4. Stress test depression induced by exercise,
  5. Shape of the stress test segment, 
  6. Sex, 
  7. Age,
  8. Chest pain type,
  9. Serum cholesterol,
  10. Exercise-induced angina,
  11. Number of major vessels blocked,
  12. Thalassemia,
  13. Maximum heart rate achieved.

So far, the diagnosis of CVD has been mostly dependent on the traditional approaches, using trained professionals’ expertise, particularly cardiologists. 

TADA’s Machine Learning platform can help automate, in part, the CVD risk prediction. Thus General Practitioners and Cardiologists can get indications extracted from the patient information and test results.

Objectives

  • Quickly identify in minutes someone with a high chance of CVD based on tests results
  • Improve the accuracy of CVD prediction and diagnosis
  • Identify the most critical medical exams to perform to spot CVD.

 

It poses the following cardiology question:

Can cardiovascular disease prediction identify a person at risk?

Solution

The TADA predictive models’ results reach an 83% accuracy based on real data for cardiovascular disease prediction. The model’s MCC (Matthews Correlation Coefficient) is 65%, and its AUC (Area Under Curve) is 86%.

Among the thirteen variables mentioned earlier and available in the dataset, TADA has selected and identified four main criteria to predict CVD. They bear different weights relative to their global influence on the final decision:

  • The ST depression induced by exercise, with a weight of 41%,
  • The chest pain type, with a weight of 32%,
  • The number of significant blood vessels colored by fluoroscopy, with a weight of 22%.
  • The exercise-induced angina, with a weight of 5%.
TADA obtains a 83% accuracy in the identification of CVD cases. The artificial intelligence tool distinguishes patients at high risk of CVD with excellent efficiency. It can also help the General Practitioner and the Cardiologists understand how each element measured impacts the diagnosis. It shows the dependency between the ST depression induced by exercise and CVD chances.

Live Predict

Customer Benefits

In one day, cardiologists gained significant support in their cardiovascular disease diagnosis and their fight against strokes by:

  • Identifying in a few minutes which patients were at higher risks of CVD with a 93% accuracy.
  • Immediately obtaining an idea of which medical exams were critical in recognizing CVD, for instance, the number of significant blood vessels colored by fluoroscopy.

References