Application of knowledge discovery process on the prediction of stroke

OBJECTIVE

Stroke is a prominent life-threatening disease in the world. The current study was performed to predict the outcome of stroke using knowledge discovery process (KDP) methods, artificial neural networks (ANN) and support vector machine (SVM) models.

MATERIALS AND METHODS

The records of 297 (130 sick and 167 healthy) individuals were acquired from the databases of the department of emergency medicine. Nine predictors (coronary artery disease, diabetes mellitus, hypertension, history of cerebrovascular disease, atrial fibrillation, smoking, the findings of carotid Doppler ultrasonography [normal, plaque, plaque+stenosis≥50%], the levels of cholesterol and C-reactive protein) were used for predicting the stroke. Feature selection based on the Cramer's V test was carried out for reducing the predictors. Multilayer perceptron (MLP) ANN and SVM with radial basis function (RBF) kernel were used for the prediction based on the selected predictors.

RESULTS

The accuracy values were 81.82% for ANN and 80.38% for SVM in the training dataset (n=209), and 85.9% for ANN and 84.62% for SVM in the testing dataset (n=78), respectively. ANN and SVM models yielded area under curve (AUC) values of 0.905 and 0.899 in the training dataset, and 0.928 and 0.91 in the testing dataset, consecutively.

CONCLUSION

The findings of the current study pointed out that ANN had more predictive performance when compared with SVM in predicting stroke. The proposed ANN model would be useful when making clinical decisions regarding stroke.

Prediction of death status on the course of treatment in SARS-COV-2 patients with deep learning and machine learning methods

BACKGROUND AND OBJECTIVE

The new type of Coronavirus (2019-nCov) epidemic spread rapidly, causing more than 250 thousand deaths worldwide. The virus, which first appeared as a sign of pneumonia, was later called the SARS-COV-2 with Severe Acute Respiratory Syndrome by the World Health Organization. The SARS-COV-2 virus is triggered by binding to the Angiotensin-Converting Enzyme 2 (ACE 2) inhibitor, which is vital in cardiovascular diseases and the immune system, especially in conditions such as cerebrovascular, hypertension, and diabetes. This study aims to evaluate the prediction performance of death status based on the demographic/clinical factors (including COVID-19 severity) by data mining methods.

METHODS

The dataset consists of 1603 SARS-COV-2 patients and 13 variables obtained from an open-source web address. The current dataset contains age, gender, chronic disease (hypertension, diabetes, renal, cardiovascular, etc.), some enzymes (ACE, angiotensin II receptor blockers), and COVID-19 severity, which are used to predict death status using deep learning and machine learning approaches (random forest, k-nearest neighbor, extreme gradient boosting [XGBoost]). A grid search algorithm tunes hyperparameters of the models, and predictions are assessed through performance metrics. Steps of knowledge discovery in databases are applied to obtain the relevant information.

RESULTS

The accuracy rate of deep learning (97.15%) was more successful than the accuracy rate based on classical machine learning (92.15% for RF and 93.4% for k-NN), but the ensemble classifier XGBoost method gave the highest accuracy (99.7%). While COVID-19 severity and age calculated from XGBoost were the two most important factors associated with death status, the most determining variables for death status estimated from deep learning were COVID-19 severity and hypertension.

CONCLUSIONS

The proposed model (XGBoost) achieved the best prediction of death status based on the factors as compared to the other algorithms. The results of this study can guide patients with certain variables to take early measures and access preventive health care services before they become infected with the virus.

Modeling Based on Ensemble Learning Methods for Detection of Diagnostic Biomarkers from LncRNA Data in Rats Treated with Cis-Platinum-Induced Hepatotoxicity

BACKGROUND

The first aim of this study is to perform bioinformatic analysis of lncRNAs obtained from liver tissue samples from rats treated with cisplatin hepatotoxicity and without pathology. Another aim is to identify possible biomarkers for the diagnosis/early diagnosis of hepatotoxicity by modeling the data obtained from bioinformatics analysis with ensemble learning methods.

METHODS

In the study, 20 female Sprague-Dawley rats were divided into a control group and a hepatotoxicity group. Liver samples were taken from rats, and transcriptomic and histopathological analyses were performed. The dataset achieved from the transcriptomic analysis was modeled with ensemble learning methods (stacking, bagging, and boosting). Modeling results were evaluated with accuracy (Acc), balanced accuracy (B-Acc), sensitivity (Se), specificity (Sp), positive predictive value (Ppv), negative predictive value (Npv), and F1 score performance metrics. As a result of the modeling, lncRNAs that could be biomarkers were evaluated with variable importance values.

RESULTS

According to histopathological and immunohistochemical analyses, a significant increase was observed in the sinusoidal dilatation and Hsp60 immunoreactivity values in the hepatotoxicity group compared to the control group (p < 0.0001). According to the results of the bioinformatics analysis, 589 lncRNAs showed different expressions in the groups. The stacking model had the best classification performance among the applied ensemble learning models. The Acc, B-Acc, Se, Sp, Ppv, Npv, and F1-score values obtained from this model were 90%, 90%, 80%, 100%, 100%, 83.3%, and 88.9%, respectively. lncRNAs with id rna-XR_005492522.1, rna-XR_005492536.1, and rna-XR_005505831.1 with the highest three values according to the variable importance obtained as a result of stacking modeling can be used as predictive biomarker candidates for hepatotoxicity.

CONCLUSIONS

Among the ensemble algorithms, the stacking technique yielded higher performance results as compared to the bagging and boosting methods on the transcriptomic data. More comprehensive studies can support the possible biomarkers determined due to the research and the decisive results for the diagnosis of drug-induced hepatotoxicity.

Clinical presentation, management, screening and surveillance for colorectal cancer during the COVID-19 pandemic

Management of colorectal cancer (CRC) was severely affected by the changes implemented during the pandemic, and this resulted in delayed elective presentation, increased emergency presentation, reduced screening and delayed definitive therapy. This review was conducted to analyze the impact of the coronavirus disease 2019 (COVID-19) pandemic on management of CRC and to identify the changes made in order to adapt to the pandemic. We performed a literature search in PubMed, Medline, Index Medicus, EMBASE, SCOPUS, Reference Citation Analysis (https://www.referencecitationanalysis.com/) and Google Scholar using the following keywords in various combinations: Colorectal cancer, elective surgery, emergency surgery, stage upgrading, screening, surveillance and the COVID-19 pandemic. Only studies published in English were included. To curtail the spread of COVID-19 infection, there were modifications made in the management of CRC. Screening was limited to high risk individuals, and the screening tests of choice during the pandemic were fecal occult blood test, fecal immunochemical test and stool DNA testing. The use of capsule colonoscopy and open access colonoscopy was also encouraged. Blood-based tests like serum methylated septin 9 were also encouraged for screening of CRC during the pandemic. The presentation of CRC was also affected by the pandemic with more patients presenting with emergencies like obstruction and perforation. Stage migration was also observed during the pandemic with more patients presenting with more advanced tumors. The operative therapy of CRC was altered by the pandemic as more emergencies surgeries were done, which may require exteriorization by stoma. This was to reduce the morbidity associated with anastomosis and encourage early discharge from the hospital. There was also an initial reduction in laparoscopic surgical procedures due to the fear of aerosols and COVID-19 infection. As we gradually come out of the pandemic, we should remember the lessons learned and continue to apply them even after the pandemic passes.

[The comparison of logistic regression model selection methods for the prediction of coronary artery disease]

OBJECTIVE

In this study, logistic regression model selection methods were compared for the prediction of coronary artery disease (CAD).

METHODS

Coronary artery disease data were taken from 237 consecutive people who had been applied to Inönü University Faculty of Medicine, Department of Cardiology. Logistic regression model selection methods were applied to CAD data containing continuous and discrete independent variables. Goodness of fit test was performed by Hosmer-Lemeshow statistic. Likelihood-ratio statistic was used to compare the estimated models.

RESULTS

Each of the logistic regression model selection methods had sensitivity, specificity and accuracy rates greater than 91.9%. Hosmer-Lemeshow statistic showed that the model selection methods were successful in the description of CAD data. Related factors with CAD were identified and the results were evaluated.

CONCLUSION

Logistic regression model selection methods were very successful in the prediction of CAD. Stepwise model selection methods were better than Enter method based on Likelihood-ratio statistic for the prediction of CAD. Age, diabetes mellitus, hypertension, family history, smoking, low-density lipoprotein, triglyceride, stress and obesity variables may be used for the prediction of CAD.

Assessment of clinical and pathological features of patients who underwent thyroid surgery: A retrospective clinical study

AIM

To evaluate whether there was any correlation between the clinical parameters and final pathological results among patients who underwent thyroid surgery.

METHODS

We retrospectively analyzed parameters, including age, sex, complete blood cell count parameters, nodule diameter, nodule localization, thyroid function testing, and pathology reports, in patients who underwent thyroid surgery. The patients were divided into malignant (n = 92) and benign (n = 413) groups depending on the final pathological results. Both groups were compared for demographic and clinical parameters. The Kolmogorov-Smirnov normality test was used to determine if the quantitative variables had a normal distribution. The nonparametric Mann-Whitney U test was used to compare quantitative data that were not normally distributed, and Pearson's chi-squared test was used to compare the qualitative data. The correlation between the final pathological results and fine-needle aspiration biopsy findings was calculated using the cross-tabulation method.

RESULTS

This study included 406 women and 99 men aged between 15 and 85 years. No significant differences were found between the groups with respect to age, sex, white blood cell count, neutrophil count, lymphocyte count, thrombocyte count, red cell distribution width, platelet distribution width, mean platelet volume, platecrit, nodule localization, and thyroid function testing. On the other hand, there were significant differences between the groups with respect to nodule size (P = 0.001), cervical lymphadenopathy (P = 0.0001) and nodular calcification (P = 0.0001). Compared with the malignant group, the benign group had a significantly greater nodule size (35.4 mm vs 27.6 mm). The best cut-off point (≤ 28 mm) for nodule size, as determined by the receiver operating characteristic curve, had a sensitivity and specificity of 67.7% and 64.4%, respectively. The correlation between fine-needle aspiration biopsy and the final pathological results was assessed using the cross-table method. The sensitivity and specificity of fine-needle aspiration biopsy were 60% and 98%, respectively.

CONCLUSION

This study showed that significant differences existed between the malignant and benign groups with regard to nodule size, cervical lymphadenopathy, and nodular calcification.

Predicting coronary artery disease using different artificial neural network models

OBJECTIVE

Eight different learning algorithms used for creating artificial neural network (ANN) models and the different ANN models in the prediction of coronary artery disease (CAD) are introduced.

METHODS

This work was carried out as a retrospective case-control study. Overall, 124 consecutive patients who had been diagnosed with CAD by coronary angiography (at least 1 coronary stenosis > 50% in major epicardial arteries) were enrolled in the work. Angiographically, the 113 people (group 2) with normal coronary arteries were taken as control subjects. Multi-layered perceptrons ANN architecture were applied. The ANN models trained with different learning algorithms were performed in 237 records, divided into training (n=171) and testing (n=66) data sets. The performance of prediction was evaluated by sensitivity, specificity and accuracy values based on standard definitions.

RESULTS

The results have demonstrated that ANN models trained with eight different learning algorithms are promising because of high (greater than 71%) sensitivity, specificity and accuracy values in the prediction of CAD. Accuracy, sensitivity and specificity values varied between 83.63%-100%, 86.46%-100% and 74.67%-100% for training, respectively. For testing, the values were more than 71% for sensitivity, 76% for specificity and 81% for accuracy.

CONCLUSIONS

It may be proposed that the use of different learning algorithms other than backpropagation and larger sample sizes can improve the performance of prediction. The proposed ANN models trained with these learning algorithms could be used a promising approach for predicting CAD without the need for invasive diagnostic methods and could help in the prognostic clinical decision.

Investigating the protective effect of melatonin on liver injury related to myocardial ischemia-reperfusion

BACKGROUND

An animal model of myocardial ischemia-reperfusion (MI/R) was used to test the hypothesis that free radicals released with MI/R have hazardous effects on liver through remote organ injury.

MATERIAL/METHODS

Twenty-one rats were divided into three groups: sham-treated, MI/R, and MI/R+melatonin. To produce MI/R, a branch of the left coronary artery was occluded for 30 min followed by two hours of reperfusion. Melatonin or vehicle was given 10 min before ischemia. At the end of the study, liver tissue was obtained for biochemical determination. The false discovery rate (FDR) is explained and was used for multiple comparisons of the groups' means.

RESULTS

Compared with the sham group, MI/R significantly decreased glutathione (GSH) content and increased levels of nitric oxide (NO) and malondialdehyde (MDA). Melatonin administration significantly increased GSH levels and decreased the levels of NO and MDA compared with the MI/R group.

CONCLUSIONS

Melatonin could prevent liver damage due to its strong antioxidant and free radical scavenger effects. Therefore, melatonin may have beneficial effects on remote organ injury such as MI/R-induced liver disorders.