Physiological Signals Of Patient Research Articles

A Superpower Tree Mapping and Tracing (STMT) Algorithm for OCA Sub-types Classification and Associated Risk Factors Identification

Medical data mining supports the experts for early prediction of diseases and identifying subtypes of disease is important for prognosis, management and recommended remedy. Here we imply data mining technology for the classification of various types of oculocutaneous albinism (OCA) and its severity. We introduce a new superpower tree mapping and tracing (STMT) classification algorithm which predicts the sub type of OCA using tree tracing method in every direction. Easy Linkage software is used to find out feature linkages. STMT involves in computing the sub tree DOCSCORE which is used to classify the concern OCA-type. According to the OCA type, our Stop Watch Go model determines the severity of the disease using confidential and credential limitation values. This approach recommends the required prevention to increase the lifespan of the patient. We evaluated our algorithm with 200 OCA clinical data records collected from central hospital, Chennai and classified the types of OCA with the selected features. We used external features like hypopigmentation of hair, skin, eye color and clinical features such as nystagmus, strabismus, photophobia, poor vision and impacts of disease. The classification accuracy of proposed STMT algorithm shows that 4% more effective than traditional classifier algorithms such as KNN classifier and Naive Bayesian classifier. A comparative study is also implemented with other existing works to check the superiority of the proposed method. Hence, it is revealed from the results of the classification algorithm that the proposed method can be used as a supplementary tool for the experts to diagnose the subtypes of oculocutaneous albinism and simplify the analysis of various physiological signals of patients.

Evaluating the sleep quality of obstructive sleep apnea patients after continuous positive airway pressure treatment

Continuous positive airway pressure treatment (CPAP) is administered to treat the common disorder of obstructive sleep apnea. However, patients receiving CPAP treatment without a sleep assessment and clinical diagnosis often do not feel or understand the improvement in their condition, necessitating a sleep quality improvement index for physicians to analyze improvements in patient treatment rapidly. This work presents a novel sleep quality evaluation system that calculates the improvement value for sleep quality using electroencephalogram and electrocardiogram signal features, as well as fuzzy inferences. Experimental results indicate that the sleep quality improvement rating of the proposed system and that of the apnea–hyponea index correlate with each other. Importantly, the proposed system can identify considerable levels of improvement in the physiological signals of patients having undergone CPAP treatment.