Effect of nanoparticle macroalgae in the treatment of fatty liver disease using logistic regression, and support vector machine.

One of the major health issues facing people worldwide is liver fibrosis. Liver fibrosis may be brought on by long-term exposure to harmful substances, medicines, and microorganisms. The development of liver fibrosis in children was particularly worrying due to their longer life-span, which was possibly related to a great risk of developing long-term complications. Marine algae species have provided a biological variety in the research phase of novel approaches to the treatment of numerous ailments. Marine macroalgae have recently been the subject of research due to their rich bioactive chemical composition and potential for the production of various nutraceuticals. Macroalgae are potentially excellent sources of bioactive substances with particular and distinct biological activity when compared to their terrestrial equivalents. Macroalgae in diverse marine cases offer a few biologically active metabolites, comprising sterols, polyunsaturated fatty acids, carotenoids, oligosaccharides, polysaccharides, proteins, polyphenols, vitamins, and minerals. Accordingly, there is great interest in their high potential for supporting immunomodulatory, antimicrobial, antidiabetic, antitumoral, anti-inflammatory, antiangiogenic, and neuroprotective properties. Using an experimental model, the current research intends to collect data on the therapeutic value of macroalgae nanoparticles for fatty liver disease. The researchers' goal of predicting illnesses from the extensive medical datasets is quite difficult. The purpose of this research is to assess the protective effects of a seaweed, Padina pavonia (PP), on liver fibrosis caused by carbon tetrachloride (CCl4). This research presents two models of logistic regression (LR) and support vector machines (SVM) for predicting the likelihood of liver disease incidence. The performance of the model was evaluated using a dataset. PP macro-algae considerably reduce the high blood concentrations of aminotransferases, alkaline phosphatases, and lactate dehydrogenases, as well as causing a considerable (p < 0.05) decrease in serum bilirubin levels. In addition to improving kidney function (urea and creatinine), algal extracts enhance fat metabolism (triglycerides and cholesterol). With an accuracy rate of 70.2%, a sensitivity of 92.3%, a specificity of 74.7%, a type I error of 9.1%, and a type II error of 21.0%, the predictive model has demonstrated excellent performance. The model validated laboratory tests' ability to predict illness (age; direct bilirubin (DB), total proteins (TP), and albumin (ALB). These classifier methods are compared on the basis of their execution time and classification accuracy.