Multi-Omic Admission-Based Prognostic Biomarkers Identified by Machine Learning Algorithms Predict Patient Recovery and 30-Day Survival in Trauma Patients.

Autor: Abdelhamid SS; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Scioscia J; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Vodovotz Y; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Wu J; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Eight-Year Program of Medicine, Xiangya School of Medicine, Central South University, Changsha 410013, China., Rosengart A; Center for Systems Immunology, Departments of Immunology and Computational & Systems Biology, University of Pittsburgh, Pittsburgh, PA 15213, USA., Sung E; Center for Systems Immunology, Departments of Immunology and Computational & Systems Biology, University of Pittsburgh, Pittsburgh, PA 15213, USA., Rahman S; Center for Systems Immunology, Departments of Immunology and Computational & Systems Biology, University of Pittsburgh, Pittsburgh, PA 15213, USA., Voinchet R; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Bonaroti J; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Li S; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Darby JL; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Kar UK; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Neal MD; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Sperry J; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA., Das J; Center for Systems Immunology, Departments of Immunology and Computational & Systems Biology, University of Pittsburgh, Pittsburgh, PA 15213, USA., Billiar TR; Department of Surgery, University of Pittsburgh, Pittsburgh, PA 15213, USA.; Pittsburgh Trauma and Transfusion Medicine Research Center, University of Pittsburgh, Pittsburgh, PA 15213, USA.
Jazyk: angličtina
Zdroj: Metabolites [Metabolites] 2022 Aug 23; Vol. 12 (9). Date of Electronic Publication: 2022 Aug 23.
DOI: 10.3390/metabo12090774
Abstrakt: Admission-based circulating biomarkers for the prediction of outcomes in trauma patients could be useful for clinical decision support. It is unknown which molecular classes of biomolecules can contribute biomarkers to predictive modeling. Here, we analyzed a large multi-omic database of over 8500 markers (proteomics, metabolomics, and lipidomics) to identify prognostic biomarkers in the circulating compartment for adverse outcomes, including mortality and slow recovery, in severely injured trauma patients. Admission plasma samples from patients ( n = 129) enrolled in the Prehospital Air Medical Plasma (PAMPer) trial were analyzed using mass spectrometry (metabolomics and lipidomics) and aptamer-based (proteomics) assays. Biomarkers were selected via Least Absolute Shrinkage and Selection Operator (LASSO) regression modeling and machine learning analysis. A combination of five proteins from the proteomic layer was best at discriminating resolvers from non-resolvers from critical illness with an Area Under the Receiver Operating Characteristic curve (AUC) of 0.74, while 26 multi-omic features predicted 30-day survival with an AUC of 0.77. Patients with traumatic brain injury as part of their injury complex had a unique subset of features that predicted 30-day survival. Our findings indicate that multi-omic analyses can identify novel admission-based prognostic biomarkers for outcomes in trauma patients. Unique biomarker discovery also has the potential to provide biologic insights.
Databáze: MEDLINE