European Journal of Molecular & Clinical Medicine

Chronic kidney disease (CKD) is a major problem on the healthcare system because of its high increasing prevalence and poor morbidity. Artificial Intelligence peculating its role in every field of research including healthcare and diagnosis of diseases. Recently, machine learning approaches are applied to raise consciousness about key health hazards including chronic kidney disease (CKD). When kidneys are damaged, they are unable to perform their normal role of filtering blood. Therefore, it is tough to anticipate, recognize, and prevent such a sickness, which may result in long-term health repercussions. Machine learning methods aid in more precise forecasting to tackle this problem at an early stage. With the increase of technology aids, it makes an ambiguity on which algorithm to apply for prediction of CKD. To address these issues several machine learning algorithms such as Logistic Regression, Naive Bayes, and Decision Tree are applied. Experiments are conducted utilizing the rich set of data in a MATLAB environment. Logistic Regression shows potential for reducing mortality from chronic kidney disease by enhancing prognosis and diagnostic accuracy at an early stage

Stroke is a medical disorder that harms the brain by rupturing the blood vessels there. It can also happen when the passage of blood and other nutrients to the brain is interrupted The World Health Organization (WHO) claims that stroke is the main global cause of mortality and disability. The prediction of heart attacks has been studied, however likelihood of a brain stroke is depicted in very few works. Due to this evertheless, numerous machine learning models are created to forecast the potential for a brain stroke. This essay contains a variety of physiological variables with machine learning techniques, such as Decision Tree Classification, Random Forest, and Logistic Regression K-Nearest Neighbors, support vector machines, and classification likewise Naive Bayes.

IoT The rapid growth in the E-Commerce industry has led to an exponential increase in the use of credit cards for online purchases and consequently they have been surging in the fraud related to it. In recent years, it has become very difficult to detect fraud in credit card systems. For predicting these transactions banks make use of various machine learning methodologies, past data has been collected and new features are being used for enhancing the predictive power. The performance of fraud detecting in credit card transactions is greatly affected by the sampling approach on dataset, selection of variables and detection techniques used. This paper investigates the performance of logistic regression, decision tree and random forest for credit card fraud detection. The three techniques are applied for the dataset and work is implemented in R language.

Corona virus disease ( COVID 19 pandemic has become a major threat to the
entire world. Antidotes and proper medication s are still not found and determined to get
cure from such virus . The report from World Health Organization ( WHO ) remits the
COVID 19 as severe acute respiratory syndrome (SARS). Such virus is transmitted into
human body via a respiratory droplets. Even, major symptoms fo r coronavirus patience are
tiredness, severe fever and dry cough but in most of the cases such symtoms are not
found. This variety of coronavirus symptoms are termed as asymptomatic sym p toms. The
identification for such disease is very important into hum an body so that this can be
stopped as community spread and reduces the effect of this as global pandemic. T his paper
provides an extensive study and predicts the outbreak of this disease with the aid of
classification techniques of under machine learning. So that, the number of cases related
to COVID 19 can be identified and subsequent arrangements have been made from the
respective governments and medical doctors for future . Initially, th is prediction model is
implemented for short term interval and later, such model based on internet of thing and
machine learning, can also be set for estimating into long term intervals for global as well
as Indian perspective. The logistic r egression and d ecisiont ree techniques have been used
for such cases predictions for this epidemic