Dataset Information

Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections.

ABSTRACT: Sepsis is a high-mortality disease that is infected by bacteria, but pathogens in individual patients are difficult to diagnosis. Metabolomic changes triggered by microbial activity provide us with the possibility of accurately identifying infection. We adopted machine learning methods for training different classifiers with a clinical-metabolomic database from sepsis cases to identify the pathogen of sepsis. Records of clinical indicators and concentration of metabolites were obtained for each patient upon their arrival at the hospital. Machine learning algorithms were used in 100 patients with clear infection and corresponding 29 controls to select specific biosignatures to discriminate microorganism in septic patients. The sensitivity, specificity, and AUC value of clinical and metabolomic characteristics in predicting diagnostic outcomes were determined at admission. Our analyses demonstrate that the biosignatures selected by machine learning algorithms could have diagnostic value on the identification of infected patients and Gram-positive from Gram-negative; related AUC values were 0.94 ± 0.054 and 0.80 ± 0.085, respectively. Pathway and blood disease enrichment analyses of clinical and metabolomic biomarkers among infected patients showed that sepsis disease was accompanied by abnormal nitrogen metabolism, cell respiratory disorder, and renal or intestinal failure. The panel of selected clinical and metabolomic characteristics might be powerful biomarkers to discriminate patients with sepsis.

SUBMITTER: Zheng L

PROVIDER: S-EPMC7403934 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections.

Zheng Lingling L Lin Fangqin F Zhu Changxi C Liu Guangjian G Wu Xiaohui X Wu Zhiyuan Z Zheng Jianbin J Xia Huimin H Cai Yi Y Liang Huiying H

BioMed research international 20200727

Sepsis is a high-mortality disease that is infected by bacteria, but pathogens in individual patients are difficult to diagnosis. Metabolomic changes triggered by microbial activity provide us with the possibility of accurately identifying infection. We adopted machine learning methods for training different classifiers with a clinical-metabolomic database from sepsis cases to identify the pathogen of sepsis. Records of clinical indicators and concentration of metabolites were obtained for each ...[more]

PMID: 32802867

Similar Datasets

Project description:Cystinosis is a rare, devastating hereditary disease secondary to recessive CTNS gene mutations. The most commonly used diagnostic method is confirmation of an elevated leukocyte cystine level; however, this method is expensive and difficult to perform. This study aimed to identify candidate biomarkers for the diagnosis and follow-up of cystinosis based on multiomics studies. The study included three groups: newly-diagnosed cystinosis patients (patient group, n = 14); cystinosis patients under treatment (treatment group, n = 19); and healthy controls (control group, n = 30). Plasma metabolomics analysis identified 10 metabolites as candidate biomarkers that differed between the patient and control groups [L-serine, taurine, lyxose, 4-trimethylammoniobutanoic acid, orotic acid, glutathione, PE(O-18:1(9Z)/0:0), 2-hydroxyphenyl acetic acid, acetyl-N-formil-5-metoxikinuramine, 3-indoxyl sulphate]. As compared to the healthy control group, in the treatment group, hypotaurine, phosphatidylethanolamine, N-acetyl-d-mannosamine, 3-indolacetic acid, p-cresol, phenylethylamine, 5-aminovaleric acid, glycine, creatinine, and saccharic acid levels were significantly higher, and the metabolites quinic acid, capric acid, lenticin, xanthotoxin, glucose-6-phosphate, taurine, uric acid, glyceric acid, alpha-D-glucosamine phosphate, and serine levels were significantly lower. Urinary metabolomic analysis clearly differentiated the patient group from the control group by means of higher allo-inositol, talose, glucose, 2-hydroxybutiric acid, cystine, pyruvic acid, valine, and phenylalanine levels, and lower metabolite (N-acetyl-L-glutamic acid, 3-aminopropionitrile, ribitol, hydroquinone, glucuronic acid, 3-phosphoglycerate, xanthine, creatinine, and 5-aminovaleric acid) levels in the patient group. Urine metabolites were also found to be significantly different in the treatment group than in the control group. Thus, this study identified candidate biomarkers that could be used for the diagnosis and follow-up of cystinosis.

Project description:BackgroundCluster randomized trials (CRTs) are becoming an increasingly important design. However, authors of CRTs do not always adhere to requirements to explicitly identify the design as cluster randomized in titles and abstracts, making retrieval from bibliographic databases difficult. Machine learning algorithms may improve their identification and retrieval. Therefore, we aimed to develop machine learning algorithms that accurately determine whether a bibliographic citation is a CRT report.MethodsWe trained, internally validated, and externally validated two convolutional neural networks and one support vector machine (SVM) algorithm to predict whether a citation is a CRT report or not. We exclusively used the information in an article citation, including the title, abstract, keywords, and subject headings. The algorithms' output was a probability from 0 to 1. We assessed algorithm performance using the area under the receiver operating characteristic (AUC) curves. Each algorithm's performance was evaluated individually and together as an ensemble. We randomly selected 5000 from 87,633 citations to train and internally validate our algorithms. Of the 5000 selected citations, 589 (12%) were confirmed CRT reports. We then externally validated our algorithms on an independent set of 1916 randomized trial citations, with 665 (35%) confirmed CRT reports.ResultsIn internal validation, the ensemble algorithm discriminated best for identifying CRT reports with an AUC of 98.6% (95% confidence interval: 97.8%, 99.4%), sensitivity of 97.7% (94.3%, 100%), and specificity of 85.0% (81.8%, 88.1%). In external validation, the ensemble algorithm had an AUC of 97.8% (97.0%, 98.5%), sensitivity of 97.6% (96.4%, 98.6%), and specificity of 78.2% (75.9%, 80.4%)). All three individual algorithms performed well, but less so than the ensemble.ConclusionsWe successfully developed high-performance algorithms that identified whether a citation was a CRT report with high sensitivity and moderately high specificity. We provide open-source software to facilitate the use of our algorithms in practice.

Dataset Information

Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections.

Publications

Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets