Machine learning approaches to the human metabolome in sepsis identify metabolic links with survival

Abstract

Background Metabolic predictors and potential mediators of survival in sepsis have been incompletely characterized. We examined whether machine learning (ML) tools applied to the human plasma metabolome could consistently identify and prioritize metabolites implicated in sepsis survivorship, and whether these methods improved upon conventional statistical approaches. Methods Plasma gas chromatography–liquid chromatography mass spectrometry quantified 411 metabolites measured ≤ 72 h of ICU admission in 60 patients with sepsis at a single center (Brigham and Women’s Hospital, Boston, USA). Seven ML approaches were trained to differentiate survivors from non-survivors. Model performance predicting 28 day mortality was assessed through internal cross-validation, and innate top-feature (metabolite) selection and rankings were compared across the 7 ML approaches and with conventional statistical methods (logistic regression). Metabolites were consensus ranked by a summary, ensemble ML ranking procedure weighing their contribution to mortality risk prediction across multiple ML models. Results Median (IQR) patient age was 58 (47, 62) years, 45% were women, and median (IQR) SOFA score was 9 (6, 12). Mortality at 28 days was 42%. The models’ specificity ranged from 0.619 to 0.821. Partial least squares regression-discriminant analysis and nearest shrunken centroids prioritized the greatest number of metabolites identified by at least one other method. Penalized logistic regression demonstrated top-feature results that were consistent with many ML methods. Across the plasma metabolome, the 13 metabolites with the strongest linkage to mortality defined through an ensemble ML importance score included lactate, bilirubin, kynurenine, glycochenodeoxycholate, phenylalanine, and others. Four of these top 13 metabolites (3-hydroxyisobutyrate, indoleacetate, fucose, and glycolithocholate sulfate) have not been previously associated with sepsis survival. Many of the prioritized metabolites are constituents of the tryptophan, pyruvate, phenylalanine, pentose phosphate, and bile acid pathways. Conclusions We identified metabolites linked with sepsis survival, some confirming prior observations, and others representing new associations. The application of ensemble ML feature-ranking tools to metabolomic data may represent a promising statistical platform to support biologic target discovery.

Advances in Mass Spectrometry-Based Blood Metabolomics Profiling for Non-Cancer Diseases: A Comprehensive Review

“…Differentiation between survival and non-survival in septic patients is a popular field of metabolomics applications, as metabolites associated with survival in septic patients are poorly characterized. A study by Kosyakovsky et al [ 177 ] suggests some novel metabolites associated with sepsis survival: hydroxyisobutyrate, indoleacetate, fucose, and glycolithocholate sulfate. In another study, several upregulated and downregulated metabolites in survivors and non-survivors were identified [ 178 ].…”

Bile Acids, Intestinal Barrier Dysfunction, and Related Diseases

“…Thus, bile acids may be a potential marker for early sepsis [52,53]. Of interest is the analysis of plasma from septic individuals found to be glycochenodeoxycholate-and phenylalanine-associated with survival of sepsis [91].…”

Biomarkers for surgical sepsis. A review of foreign scientific and medical publications

“…Kosyakovsky с колл. [27] измерили уровни 411 метаболитов плазмы у пациентов с сепсисом и с помощью метода машинного обучения по шкале значимости выделили 13 молекул, ассоциированных с 28-дневной летальностью: лактат, билирубин, фенилаланин, гли колитохолатсульфат, гликохенодезоксихолат, 3-гид ро ксиизобутират, кинуренин, индолацетат, β-гид ро ксиизовалерат, таурохоленат сульфат, 3-мето кситирозин, фукоза и гидроксиизовалероилкарнитин. Эти метаболиты связаны с метаболическими путями триптофана, пирувата, фенилаланина, пентозофосфата и желчных кислот [27].…”