Coronary heart disease classification using deep learning approach with feature selection for improved accuracy.

BACKGROUND: Coronary heart disease (CHD) is one of the deadliest diseases and a risk prediction model for cardiovascular conditions is needed. Due to the huge number of features that lead to heart problems, it is often difficult for an expert to evaluate these huge features into account. So, there is a need of appropriate feature selection for the given CHD dataset. For early CHD detection, deep learning modes (DL) show promising results in the existing studies. OBJECTIVE: This study aimed to develop a deep convolution neural network (CNN) model for classification with a selected number of efficient features using the LASSO (least absolute shrinkage and selection operator) technique. Also, aims to compare the model with similar studies and analyze the performance of the proposed model using accuracy measures. METHODS: The CHD dataset of NHANES (National Health and Nutritional Examination Survey) was examined with 49 features using LASSO technique. This research work is an attempt to apply an improved CNN model for the classification of the CHD dataset with huge features CNN model with feature extractor consists of a fully connected layer with two convolution 1D layers, and classifier part consists of two fully connected layers with SoftMax function was trained on this dataset. Metrics like accuracy recall, specificity, and ROC were used for the evaluation of the proposed model. RESULTS: The feature selection was performed by applying the LASSO model. The proposed CNN model achieved 99.36% accuracy, while previous studies model achieved over 80 to 92% accuracy. CONCLUSION: The application of the proposed CNN with the LASSO model for the classification of CHD can speed up the diagnosis of CHD and appears to be effective in predicting cardiovascular disease based on risk features.

Lung cancer histopathology image classification using transfer learning with convolution neural network model.

BACKGROUND: Lung cancer (LC) is a harmful malignant tumor and potentially lethal illness. Therefore, early detection of LC is an urgent need, and dependent on the type of histology and the type of disease. The use of deep learning algorithms (DL) is required to analyse the histopathology images of LC and make treatment decisions accordingly. OBJECTIVE: This study aimed to apply pretrained EfficientNetB7 model to facilitate the process of classifying LC histopathology images as primary malignancy categories (adenocarcinoma, squamous cell carcinoma and large cell carcinoma) for early treatment of LC patients. Also, aims to analyse the performance of the proposed model using the accuracy measure. METHODS: The dataset of 15000 histopathology images of lung cancer were examined. EfficientNetB7, a special type of convolution neural network (CNN), pretrained with ImageNet for transfer learning were trained on this dataset. Accuracy metric was used for the evaluation of the proposed model RESULTS: The feature extraction was performed by applying transfer learning using EfficientNetB7 as pretrained model. The proposed model achieved 99.77% accuracy, while previous studies model achieved over 90 to 99% accuracy. CONCLUSION: The employment of CNN based EfficientNetB7 model for the classification of LC based on histopathology images can speed up the diagnosis of LC and reduce the burden on pathologists for the early treatment of patients.

Pharmacogenetics of CYP2C19 genetic polymorphism on clopidogrel response in patients with ischemic stroke from Saudi Arabia.

OBJECTIVE: To elucidate the degree of genetic polymorphisms CYP2C19 (CYP2C19*2, CYP2C19*3) of key drug metabolizing enzymes on the antiplatelet effect of clopidogrel response in patients with acute ischemic stroke from Saudi Arabia. METHODS: A case-control study carried out at Neurology Clinics at Asser Central Hospital, Abha, Kingdom of Saudi Arabia from October 2015 to January 2016 and included 25 stroke patients responding to clopidogrel therapy and 25 stroke patients non responding to clopidogrel monotherapy. After obtaining their informed consent, the blood samples were collected and genotyped for CYP2C19 polymorphisms by the polymerase chain reaction-restriction fragment length polymorphisms (PCR-RFLP Method). Allele frequencies were derived from genotypic data and platelet aggregation was measured using multiple electrode aggregometry on the multiplate analyser. Chi Square tests, p-values, odds ratio (OR) and corresponding confidence intervals were calculated for each polymorphism. RESULTS: The CYP2C19*2 (681G>A) and CYP2C19*3 (636 G>A) polymorphism were seen to be in Hardy-Weinberg equilibrium and showed significant allelic and genotypic association between responders and non-responders to clopidogrel (p<0.01). The CYP2C19*2: allelic chi-square=21.49, p=0.000036, OR=5.52 (2.42-12.83); Genotypic Chi-square=10.27, p=0.001, OR=7.88 (1.78-9.73). The CYP2C19*3: Allelic chi-square=11.66, p=0.0006, OR=3.45 (1.57-7.70); genotypic chi-square=4.37, p=0.036, OR=3.69 (0.90-5.81). The variant allele (homozygous and homozygous Mutant) showed significant influence on platelet inhibition and the antiplatelet effect of clopidogrel in ischemic stroke. CONCLUSION: Our findings provide certain evidence on the genetic effect of CYP2C19 on clopidogrel responsiveness in stroke patients from Saudi Arabia.

Protective Role of Ramipril and Candesartan against Myocardial Ischemic Reperfusion Injury: A Biochemical and Transmission Electron Microscopical Study.

The present study was designed to investigate the role of combined administration of Ramipril and Candesartan against in vitro myocardial ischemic reperfusion injury in rat. Male Wistar albino rats were divided into five groups (n = 6) and treated with saline (10 mL/kg), Ramipril (2 mg/kg), Candesartan (1 mg/kg), and the combination of both drugs, respectively 24 h before induction of global ischemia (5 min of stabilization, 9 min of global ischemia, and 12 min of reflow). Combination of Ramipril and Candesartan when compared to the monotherapy significantly increased the levels of superoxide dismutase, reduced glutathione, catalase, and nitric oxide and decreased the levels of thiobarbituric acid reactive substances. In addition, the superior protective role of combination of Ramipril and Candesartan on ischemia induced myocardial damage was further confirmed by well preserved myocardial tissue architecture in light microscopy and transmission electron microscopy analysis studies. The combination was proved to be effective in salvaging the myocardial tissue against ischemic reperfusion injury when compared to the monotherapy of individual drugs and further investigations on protective mechanism of drugs by increasing the nitric oxide level at molecular levels are needed.

Cardioprotective role of methanolic extract of bark of Terminalia arjuna against in-vitro model of myocardial ischemic-reperfusion injury.

BACKGROUND: The present study was designed to investigate the cardio protective role of chronic oral administration of methanolic extract of Terminalia arjuna bark in in-vitro myocardial ischemic reperfusion injury and the induction of HSP72. MATERIALS AND METHODS: Rats, divided into three groups, and were administered with the methanolic extract of the bark powder of Terminalia arjuna (TAME) by oral gavage (6.75 and 9.75 mg/kg: 6 days/week for 12 weeks). Control and TAME extract treated rat hearts were subjected to in-vitro global ischemic reperfusion injury (5 min perfusion, 9 min noflow and 12 min reperfusion). RESULTS: Oxidative stress in MIRI was evidenced by, raised levels of myocardial TBARS and depletion of endogenous myocardial antioxidants GSH, SOD and catalase. Western blot analysis showed a single band corresponding to 72 kDa in homogenates of hearts from rat treated with both the doses. In the methanolic extract of the bark powder of Terminalia arjuna treatment groups, both the doses had better recovery of myocardial function, with significant reduction in TBARS, and rise in SOD, GSH, catalase were observed. CONCLUSION: The results of the present study suggest that the methanolic extract of the bark powder of Terminalia arjuna in rat induces myocardial HSP72 and augments myocardial endogenous antioxidants, without causing any cellular injury and offers better cardioprotection against oxidative stress associated with myocardial IR injury.

Protective effect of methanolic extract of Annona squamosa Linn in isoniazid-rifampicin induced hepatotoxicity in rats.

The present study was made to investigate the protective effect of methanolic extract of Annona squamosa on isoniazid-rifampicin-induced hepatotoxicity in rats. Rats were divided into five different groups (n=6), group 1 served as a control, Group 2 received isoniazid (100 mg/kg, i.p.) and co-administered with rifampicin (100 mg/kg, i.p.), in sterile water, group 3 and 4 served as extract treatment groups and received 250 & 500 mg/kg bw, p.o methanolic extract of Annona squamosa and group 5 served as standard group and received silymarin 2.5 mg/kg bw, p.o. All the treatment protocols followed 21 days and after rats were sacrificed blood and liver were used for biochemical and histological studies, respectively. Administration of isoniazid and rifampicin caused a significant elevation in the levels of liver marker enzymes and thiobarbituric acid reactive substances (TBARS, oxidative stress markers) in experimental rats. Administration of methanolic extracts of Annona squamosa significantly prevented isoniazid-rifampicin-induced elevation in the levels of serum diagnostic liver marker enzymes (alanine amino transferase (ALT), aspartate amino transferase (AST), alkaline phosphatase (ALP) and gamma glutamate transpeptidase (γ-GT)), serum bilirubin, and TBARS level in experimental groups of rats. Moreover, total protein and reduced glutathione (GSH) levels were significantly increased in treatment group. The effect of extract was compared with a standard drug, silymarin. The changes in biochemical parameters were supported by histological profile. It is to be concluded that the methanolic extract of Annona squamosa protects against isoniazid and rifampicin-induced oxidative liver injury in rats.