PCA-MLP SVM distinction of salivary Raman spectra of dengue fever infection

The application of feature engineering in establishing a rapid and robust model for identifying patients with glioma

The aim of the study is to evaluate the efficacy of the combination of Raman spectroscopy with feature engineering and machine learning algorithms for detecting glioma patients. In this study, we used Raman spectroscopy technology to collect serum spectra of glioma patients and healthy people and used feature engineering-based classification models for prediction. First, to reduce the dimensionality of the data, we used two feature extraction algorithms which are partial least squares (PLS) and principal component analysis (PCA). Then, the principal components were selected using the feature selection methods of four correlation indexes, namely, Relief-F (RF), the Pearson correlation coefficient (PCC), the F-score (FS) and term variance (TV). Finally, back-propagation neural network (BP), linear discriminant analysis (LDA) and support vector machine (SVM) classification models were established. To improve the reliability of the model, we used a fivefold cross validation to measure the prediction performance between different models. In this experiment, 33 classification models were established. Integrating 4 classification criteria, PLS-Relief-F-BP, PLS-F-Score-BP, PLS-LDA and PLS-Relief-F-SVM had better effects, and their accuracy rates reached 97.58%, 96.33%, 97.87% and 96.19%, respectively. The experimental results show that feature engineering can select more representative features, reduce computational time complexity and simplify the model. The classification model established in this experiment can not only increase the robustness of the model and shorten the discrimination time but also realize the rapid, stable and accurate diagnosis of glioma patients, which has high clinical application value.

Reduced Featured k-NN Classifier Model Optimal for Classification of Dengue Fever from Salivary Raman Spectra

Current diagnostic methods based on nonstructural protein 1 (NS1) for dengue infection use blood as the medium and hence are invasive. Worry for blood infected diseases, pain from pricking, overcrowded public hospitals and ignorance are just a few of the causes for delayed diagnosis that contributes to mortality from dengue fever (DF). NS1 has also been reported in saliva, but sensitivity of detection is much lower than that of blood. If saliva is to be a medium, detection of NS1 requires a more specific and sensitive technique. In this study, we are exploiting the advantages of saliva and Surface Enhanced Raman Spectroscopy (SERS) to develop a non-invasive early detection method for DF. Significant features from Raman spectra of saliva samples of dengue suspected patients and healthy volunteers were extracted with Principal Component Analysis (PCA) and served as input to k-Nearest Neighbour (k-NN) for classification. Cumulative Percentage Variance (CPV) is the criterion for feature extraction. Two k-NN distance rules (Cosine and Manhattan) combined with k-values ranging from 3 to 17 were varied to obtain an optimal k-NN classifier. Then, performance of the different k-NN classifier models is benchmarked against Panbio Dengue Early ELISA and SD BIOLINE Dengue Duo technique from the clinical laboratory. The finding is encouraging with the best performance achieved, 82.14% for accuracy, 85.71% for sensitivity and 78.57% for specificity.

Severe Dengue Prognosis Using Human Genome Data and Machine Learning

Dengue has become one of the most important worldwide arthropod-borne diseases. Dengue phenotypes are based on laboratorial and clinical exams, which are known to be inaccurate.

OBJECTIVE

We present a machine learning approach for the prediction of dengue fever severity based solely on human genome data.

METHODS

One hundred and two Brazilian dengue patients and controls were genotyped for 322 innate immunity single nucleotide polymorphisms (SNPs). Our model uses a support vector machine algorithm to find the optimal loci classification subset and then an artificial neural network (ANN) is used to classify patients into dengue fever or severe dengue.

RESULTS

The ANN trained on 13 key immune SNPs selected under dominant or recessive models produced median values of accuracy greater than 86%, and sensitivity and specificity over 98% and 51%, respectively.

CONCLUSION

The proposed classification method, using only genome markers, can be used to identify individuals at high risk for developing the severe dengue phenotype even in uninfected conditions.

SIGNIFICANCE

Our results suggest that the genetic context is a key element in phenotype definition in dengue. The methodology proposed here is extendable to other Mendelian based and genetically influenced diseases.