Dataset Information

Septicemic Melioidosis Detection Using Support Vector Machine with Five Immune Cell Types.

ABSTRACT: Melioidosis, caused by Burkholderia pseudomallei (B. pseudomallei), predominantly occurs in the tropical regions. Of various types of melioidosis, septicemic melioidosis is the most lethal one with a mortality rate of 40%. Early detection of the disease is paramount for the better chances of cure. In this study, we developed a novel approach for septicemic melioidosis detection, using a machine learning technique-support vector machine (SVM). Several SVM models were built, and 19 features characterized by the corresponding immune cell types were generated by Cell type Identification Estimating Relative Subsets Of RNA Transcripts (CIBERSORT). Using these features, we trained a binomial SVM model on the training set and evaluated it on the independent testing set. Our findings indicated that this model performed well with means of sensitivity and specificity up to 0.962 and 0.979, respectively. Meanwhile, the receiver operating characteristic (ROC) curve analysis gave area under curves (AUCs) ranging from 0.952 to 1.000. Furthermore, we found that a concise SVM model, built upon a combination of CD8+ T cells, resting CD4+ memory T cells, monocytes, M2 macrophages, and activated mast cells, worked perfectly on the detection of septicemic melioidosis. Our data showed that its mean of sensitivity was up to 0.976 while that of specificity up to 0.993. In addition, the ROC curve analysis gave AUC close to 1.000. Taken together, this SVM model is a robust classification tool and may serve as a complementary diagnostic technique to septicemic melioidosis.

SUBMITTER: Xu K

PROVIDER: S-EPMC8668356 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Melioidosis, caused by Gram negative bacteria Burkholderia pseudomallei, is a major type of community-acquired septicemia in Southeast Asia and Northern Australia with high mortality and morbidity rate. More accurate and rapid diagnosis is needed for improving the management of septicemic melioidosis. We previously identified 37-gene candidate signature to distinguish septicemic melioidosis from sepsis due to other pathogens. The aims of this current study were to independently validate our previous biomarker and consolidate gene selection from each of our microarray data set for establishing a targeted assay for the differential diagnosis of melioidosis. Blood samples were collected from patients who presented with severe inflammatory response syndromes from 3 provincial hospitals in Northeast of Thailand during September 2009 and November 2011. Only culture-confirmed sepsis were included in the study (n=166). We generated a new microarray dataset comprising of 29 patients with septicemic melioidosis and 54 patients with sepsis due to other pathogens. Validation of the 37-gene signature using this new dataset demonstrated the prediction accuracy of approximately 80% for detecting type of sepsis. In order to develop a nanoliter-scale high throughput PCR technology, we further identified additional gene signature from this new microarray dataset and by revisiting our published data. Altogether 85 genes including 6 housekeeping genes were selected. Using multi-steps iteration approach we could reduce the number of biomarkers to 12 genes while the performance is comparable to that of the full panel. The high performance (accuracy >70%) of this 12-gene signature could be validated in a second independent set of samples. The 12-gene panel identified by our study provides high performance for the differential diagnosis of septicemic melioidosis. This finding will be useful for improving the management of septicemic melioidosis in term of diagnosis, treatment and follow up.

Dataset Information

Septicemic Melioidosis Detection Using Support Vector Machine with Five Immune Cell Types.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets