Stroke is a health condition that causes damage by tearing the blood vessels in the brain. It can also occur when there is a halt in the blood flow and other nutrients to the brain. According to the World Health Organization (WHO), stroke is the leading cause of death and disability globally. Most of the work has been carried out on the prediction of heart stroke but very few works show the risk of a brain stroke. With this thought, various machine learning models are built to predict the possibility of stroke in the brain. This paper has taken various physiological factors and used machine learning algorithms like Logistic Regression, Decision Tree Classification, Random Forest Classification, K-Nearest Neighbors, Support Vector Machine and Naïve Bayes Classification to train five different models for accurate prediction. The algorithm that best performed this task is Naïve Bayes that gave an accuracy of approximately 82%.

Hyperglycemia arises due to diabetes mellitus, which is a persistent and life-threatening ailment. In this paper deep convolution neural network can be embedded to long short-term memory networks to recognize early prediction of diabetes and to decrease the complications that can be occurred through diabetes irrespective to the age. Diabetes problem is being gradually growing and presently, it is reported as a significant cause of death in the top spot. According to the recent studies 48% of overall world population will be affected by diabetes by 2045. If diabetes unidentified in early stages, it may cause other additional cardiac problems. In the proposed based work, a deep learning framework deep combination of convolution neural network and long short-term memory is proposed by embedding both to leverage their respective advantages for diabetes recognition and to allow early prediction of diabetes to avoid other complications. The experimental evolution on the bunch mark of diabetes data set demonstrates the proposed model embedded deep long short-term memory outperforms other machine learning and conventional deep learning approaches. The proposed algorithm in this paper outperforms existing techniques and evaluates total effectiveness and accuracy of predicting whether a person will suffer from diabetes.

Diabetes is the most prevalent condition worldwide, and diabetic retinopathy (DR) is a subsequent condition caused by acute diabetic cases. It causes severe degeneration of the retina. The compounding blood vessels bloat and often burst, causing fluid leaks in the aqueous humor. This, in turn, causes the creation of undesirable nerve fiber infractions from the occlusion of arteries. Diagnosis requires a manual retinal examination that can often be inconsistent and deliberate with potential flaws in the diagnosis. Early detection through an ophthalmologist is paramount to prevent the prognosis of severe vision loss. Considering the current leap of machine learning in the field of healthcare, early detection of DR can be potentially made efficient with intelligent systems. This research proposes methodologies to fine-tune the existing pre-trained architectures, attaining the classification accuracies of 98% to classify the ocular fundus images which identify early prediction of diabetes. Additionally, this study presents an exposition of other equally scrutinized approaches to ultimately showcase a deep neural network architecture that can precisely classify normal fundus and degenerated fundus from the lowest to the most severe hierarchy. Among several layers in the CNN model pre-tuning and post-tuning exception layers outperformed with good results.