Coronary Artery Disease

Machine learning analysis of integrated ABP and PPG signals towards early detection of coronary artery disease

Every year, Coronary Artery Disease (CAD) claims lives of over a million people. CAD occurs when the coronary arteries, responsible for supplying oxygenated blood to the heart, get occluded due to plaque deposits on their inner walls. The most critical fact about this disease is that it develops gradually over the years and by the time symptomatic changes such as angina or shortness of breath appear, the disease has already become severe. The overall aim of the proposed work is to detect CAD efficiently in its early stage while utilizing (radial) arterial blood pressure (ABP) along with photoplethysmogram (PPG) signals so that necessary clinical measures may be taken timely.

To achieve this objective, firstly, ABP and PPG data of 73 CAD and 64 non-CAD (not suffering from any cardiac condition) subjects have been collected from MIMIC-II waveform database with matched subset. Secondly, the collected data is pre-processed using band pass filters having bandwidths of 2.5 to 16 Hz and 1.5 to 16 Hz for ABP and PPG respectively. Thirdly, nineteen features have been extracted from each of the two signals; some of the key features include mean of pulse duration, mean of rising slope and ratio of low frequency to high frequency. Finally, extensive analysis on CAD and non-CAD classification is carried out on the basis of extracted features while employing state-of-the-art classifiers such as support vector machines (SVM), K-nearest neighbors (KNN) and neural networks(NN).

The numerical experiments have led to the interpretation that neural network outperforms other classifiers, claiming an accuracy of about 90%. Moreover, accuracy of the proposed approach is found to be better than the state-of-the-art works reported in literature where one of or combinations of cardiovascular signals, namely, electrocardiogram (ECG), phonocardiogram (PCG) and photoplethysmogram (PPG) have been utilized for the CAD detection.

The global mortality rate due to cardiovascular diseases (CVDs) cause a major concern, approximately 17.9 million deaths in 2019 is being attributed to CVDs. Coronary artery disease is one of the major CVDs; in this pathological condition, the coronary arteries, responsible for supplying oxygenated blood to the heart, get occluded due to plaque deposits on their inner walls. This may further lead to symptoms such as chest pain, shortness of breath, heart attack in the advanced stage of disease development.

The risk factors include high blood pressure, high cholesterols, diabetes, smoking, obesity and a family history of heart disease. Treatment options for the said condition range from lifestyle changes, medication to surgery. It may be noted that once the disease has become severe, it requires clinical intervention, else, it may prove to be fatal. While coronary catheterization is a gold standard for diagnosing CAD, it is an invasive and expensive procedure conducted by skilled cardiologists.

A comparison can demonstrate the effectiveness of our proposed method over other techniques used. Firstly, validation using external datasets from different institutions or equipment was not conducted. Secondly, the proposed method could not be compared with previous methods within the same analytical environment. Additionally, in this study we have extracted the features manually further the use of deep neural networks for classification on CAD can be implemented.

For future work, enhancements can focus on improving the generalization of the dataset and incorporating deep learning methodologies. Additionally, a more comprehensive analysis of other potential features could be explored to further refine the model’s performance.

Coronary heart disease, atherosclerosis, cardiovascular disease, heart attack, myocardial infarction, angina, ischemia, plaque buildup, cholesterol, hypertension, blood pressure, arterial blockage, heart failure, risk factors, prevention, lifestyle changes, heart health, cardiology, medical treatment, diagnosis

#HeartDisease, #CardiovascularHealth, #HeartAttack, #Atherosclerosis, #Hypertension, #Cholesterol, #BloodPressure, #HeartHealth, #Cardiology, #Prevention, #HealthyLifestyle, #Angina, #Ischemia, #PlaqueBuildup, #MedicalTreatment, #Diagnosis, #RiskFactors, #HeartFailure, #ArterialBlockage

International Conference on Genetics and Genomics of Diseases

Visit: genetics-conferences.healthcarek.com

Award Nomination: genetics-conferences.healthcarek.com/award-nomination/?ecategory=Awards&rcategory=Awardee

Award registration: genetics-conferences.healthcarek.com/award-registration/

For Enquiries: contact@healthcarek.com

Get Connected Here
---------------------------------
---------------------------------
in.pinterest.com/Dorita0211
twitter.com/Dorita_02_11_
facebook.com/profile.php?id=61555903296992
instagram.com/p/C4ukfcOsK36
genetics-awards.blogspot.com/
youtube.com/@GeneticsHealthcare