2022

Permanent URI for this collection

https://escholar.umt.edu.pk/handle/123456789/5574

Browse

Browsing 2022 by Author "SAMAN PERVEZ MALIK"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    Prediction of cardiovascular disease in logistic regression of Artificial Intelligence
    (UMT, Lahore, 2022) SAMAN PERVEZ MALIK
    In contemporary healthcare, cardiovascular disease is one of the most urgent worldwide health ]challenges. The contemporary adage asserts that there has been a tremendous increase in global life expectancy due to cardiovascular disease. If heart abnormalities are discovered early, they are less likely to be life-threatening; nevertheless, if treatment is delayed, they may develop rapidly. Utilizing technology like as body area networks and electronic health records, medical sensors and wearable devices are implanted throughout patients' bodies in order to continually monitor and diagnose their health concerns. As the data generated by body area networks is both continuous and huge in volume, machine learning methods are used to efficiently classify health data. The most challenging aspect, however, is accurately identifying health data with an eye toward early detection of cardiac problems. Consequently, the absence of a more accurate and quick method for identifying cardiac problems is a fundamental drawback of the current methodologies. In this thesis, we create a highly accurate and performance-oriented categorization-based system for the early prediction of heart disease. This dissertation's significant contribution is divided into two sections. First, a technique that has proved useful in the early diagnosis and categorization of cardiovascular disease is described. Then, we provide a medical recommendation model based on the Fourier transform that we think will assist in the early diagnosis of heart disorders. To classify health data, models using the naive bayes classifier are used. Accuracy, sensitivity, precision, and specificity are assessed in conjunction with the results. According to the study, the suggested technique gives more accuracy and prediction measures than the methods currently in use.