Health is a primary concern of every human being. Continuous health monitoring is becoming more important nowadays. But going to the hospitals or doctors for a routine checkup can be costly and most of the time difficult for human being. Hence, a cost-effective and wireless health condition monitoring system can be an effective solution that can be monitored anytime from anywhere. Nowadays, IoT-enabled health monitoring system plays the critical role by the observation of health conditions and detecting early vital signs of diseases or ill-conditions through IoT. In this paper, we have proposed a health monitoring device on the amalgamation of Raspberry pi, and cloud IoT platform which is based on the Thingspeak server. The system monitors body temperature, heartbeat, Electrocardiogram (ECG), the variations of the electrical characteristics of the skin, motions, and blood oxygen level of every individual. The system is designed as user-friendly with low cost and potency. Experimental studies show the reliance and effectiveness of the proposed system concerning the existing models.

Parkinson's disease is one of the supreme neurodegenerative problems of the human's vital nervous organism. It is a matter of sorrow that no specific clinical tests were introduced to detect Parkinson's disease correctly. As Parkinson's disease is non-communicable, early-stage detection of Parkinson's can prevent further damages in humans suffering from it. However, it has been observed that PD's presence in a human is related to its hand-writing as well as hand-drawn subjects. From that perspective, several techniques have been proposed by researchers to detect Parkinson's disease from hand-drawn images of suspected people. But, the previous methods have their constraints. In this investigation, an approach to predict Parkinson's disease from hand-drawn wave and spiral images using computer vision and machine learning techniques has been recommended. Decision Tree, Gradient Boosting, K-Nearest Neighbor, Random Forest, and some other classification algorithms with the HOG feature descriptor algorithm was applied. The proposed strategy with Gradient Boosting and K-Nearest Neighbors accomplished better execution in accuracy, sensitivity, and specificity as well as in system design flexibility. Gradient Boosting algorithm got 86.67%, 93.33%, and 80.33% for accuracy, sensitivity, specificity and KNN got 89.33%, and 91.67% for accuracy, and sensitivity respectively.

Stroke is the second driving reason for death worldwide, answerable for around 11% of all out passings. Throughout the long term, scientists are attempting to connect up various elements to the onset of stroke. Early awareness of various threat issues of stroke can limit the chance of stroke. The prediction of stroke is essential to counter health damage or passing. In this research, machine learning has been utilized to predict stroke inpatients. A popular oversampling method called SMOTE with several machine learning classifiers (Logistic Regression, Random Forest, and XGBoost) has been applied to the dataset to predict the consequence. The random forest model achieved better performance among these algorithms with 99.07% of accuracy, 99.0% of precision and recall. The feature importance scores have been shown to understand the feature's impact on the model development. The proposed model outperformed the existing works with higher accuracy.

Hepatocellular Carcinoma (HCC) is the most crucial liver neoplasm and the subsequent driving reason for malignant growth demise worldwide. The survival rates for patients determined to have HCC and to distinguish prognostic components, which will help in picking ideal treatment for singular patients. Throughout the long term, and for the specific instance of HCC, some investigation contemplates have been creating procedures for helping physicians, employing machine learning methods to anticipate the survival rate after treatment. In this paper, we have applied machine learning calculations to anticipate the 1-year endurance of patients and discover the feature importance. We have employed an oversampling strategy named SMOTE, for adjusting the dataset to improve the model performance. We have shown the difference in model performance before and after using SMOTE. Our proposed system with the XGBoost classifier performed better with 87% accuracy in comparison with other existing models.

Coronavirus (COVID-19) has been one of the most dangerous and acute deadly diseases across the world recently. Researchers are trying to develop automated and feasible COVID-19 detection systems with the help of deep neural networks, machine learning techniques, etc. In this paper, a deep learning-based COVID-19 detection system called COV-VGX is proposed that contributes to detecting coronavirus disease automatically using chest X-ray images. The system introduces two types of classifiers, namely, a multiclass classifier that automatically predicts coronavirus, pneumonia, and normal classes and a binary classifier that predicts coronavirus and pneumonia classes. Using transfer learning, a deep CNN model is proposed to extract distinct and high-level features from X-ray images in collaboration with the pretrained model VGG-16. Despite the limitation of the COVID-19 dataset, the model is evaluated with sufficient COVID-19 images. Extensive experiments for multiclass classifier have achieved 98.91% accuracy, 97.31% precision, 99.50% recall, 98.39% F1-score, while 99.37% accuracy, 98.76% precision, 100% recall, 99.38% F1-score for binary classifier. The proposed system can contribute a lot in diagnosing COVID-19 effectively in the medical field.