Revista de Saúde e Informática Médica

Malaria remains one of the major challenges faced in healthcare in Africa, especially in Nigeria with an estimated 300,000 children killed by malaria annually. Apart from low doctor to patient ratio in Nigeria, poor diagnosis is another major cause of increase in malaria death rate.

This research developed a Clinical Decision Support System (CDSS) to detect malaria infected patients using deep and machine learning technique. For this, we developed an in-depth learning method from camera captured Giemsa-stained thin blood smear slides from 150 Plasmodium Falciparum infected and 50 non-infected patients from a national center for biomedical communications. The dataset contains 27,558 cell images with equal number of malaria infected and non-infected cell images which are 13,779. The architecture of the proposed model predicted patient’s malaria status and was evaluated using 5-fold cross-validation. The images were preprocessed and resized after which the learning stage began. Deep learning and classification were carried out using Convolutional Neural Network (CNN). The CNN model was trained by using Stochastic Gradient Descent (SGD) and Nesterov’s momentum to optimizing the multinomial logistic regression objective. The proposed model achieved a training accuracy of 99%, validation accuracy of 97%, 40% train loss, 35% validation loss a 98% prediction.

Alcoholic hepatitis is a significant wellbeing and monetary weight around the world. Glucocorticoids (GCs) are the main first-line drugs prescribed to treat serious alcoholic hepatitis (sAH), with restricted transient adequacy and huge incidental effects. In this survey, I sum up the significant advantages and results of GC treatment in sAH and the likely basic components. The survey of the writing and information mining plainly show that the hepatic motioning of glucocorticoid receptor (GR) is uniquely debilitated in sAH patients. The disabled GR flagging causes hepatic downguideline of qualities fundamental for gluconeogenesis, lipid catabolism, cytoprotection, and against irritation in sAH patients. The viability of GCs in sAH might be undermined by GC opposition or potentially GC's extrahepatic aftereffects, especially the results of digestive epithelial GR on stomach porousness and irritation in AH. Prednisolone, a significant GC utilized for sAH, enacts both the GR and mineralocorticoid receptor (MR). At the point when GC non-responsiveness happens in sAH patients, the enactment of MR by prednisolone could expand the gamble of liquor misuse, liver fibrosis, and intense kidney injury. To further develop the GC treatment of sAH, the work ought to be centered on fostering the biomarker(s) for GC responsiveness, liver-focusing on GR agonists, and techniques to defeat GC non-responsiveness and forestall liquor backslide in sAH patients.

Lateral elbow tendinopathy (LET) is a typical excruciating outer muscle problem. A few medicines have been proposed to give torment decrease and practical recuperation, including laser treatment, hyaluronic corrosive peritendinous infusion (Hy-A), and restorative activity (TE). The review means to evaluate the viability of a joined methodology with extreme focus laser treatment (Handle) and Hy-An infusions contrasted with TE on torment, muscle strength, and handicap in patients with excruciating LET. A review longitudinal review was completed by counseling the clinical records of patients with a conclusion of excruciating LET formed by clinical and instrumental discoveries that got utilitarian assessments, including the Patient-Evaluated Tennis Elbow Assessment (PRTEE) and muscle strength estimation no less than multiple times: T0 ("gauge"), 1-month (T1), 3-month (T2), and half year subsequent meet-ups (T3). Clinical records of 80 patients were broke down. In the Handle+HyA bunch, the Pinnacle strength (p<0.001) and mean strength (p<0.001) altogether expanded contrasted with the TE bunch between concentrate on times. For the PRTEE-complete score concerning the subscales, the Handle+HyA bunch announced genuinely huge decreases just for the correlations of standard versus T1 and benchmark versus T2. No serious antagonistic occasions happened. Our discoveries propose that Hy-A related with Handle may be more successful than TE for individuals with LET in the short-medium term.

One out of eight women over their lifetime will be diagnosed of breast cancer and it is recorded to be the world major cause of women’s deaths. Data mining methods are an effective way to classify data, especially in medical field, where those methods are widely used in diagnosis and analysis to make decisions. In this study, a performance comparison between five different data mining technique: Random forest, random tree, Bayes net, Naïve Bayes and J48 on the breast cancer Wisconsin (Diagnostic) data set is conducted. It is aimed to assess the correctness in classifying data with respect to efficiency and effectiveness of each algorithm in terms of accuracy, precision, sensitivity/recall and specificity. Experimental outcome indicates that Bayes net and random forest gives the highest weighted average accuracy of 97.1% with lowest type I and II error rate. All experiments conducted in WEKA data mining tool.