Metabolomics Analysis in Acute Paraquat Poisoning Patients Based on UPLC-Q-TOF-MS and Machine Learning Approach

Abstract

Most paraquat (PQ) poisoned patients died from acute multiple organ failure (MOF) such as lung, kidney, and heart. However, the exact mechanism of intoxication is still unclear. In order to find out the initial toxic mechanism of PQ poisoning, a blood metabolomics study based on ultraperformance liquid chromatography coupled to quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF-MS) and efficient machine learning approach was performed on 23 PQ poisoned patients and 29 healthy subjects. The initial PQ plasma concentrations of PQ poisoned patients were >1000 ng/mL, and the blood samples were collected at before first hemoperfusion (HP), after first HP, and after last HP. The results showed that PQ poisoned patients all differed from healthy subjects, whatever they were before or after first HP or after last HP. The efficient machine learning approaches selected key metabolites from three UPLC/Q-TOF-MS data sets which had the highest classification performance in terms of classification accuracy, Matthews Correlation Coefficients, sensitivity, and specificity, respectively. The mass identification revealed that the most important metabolite was adenosine, which sustained in low level, regardless of whether PQ poisoned patients received HP treatment. In conclusion, decreased adenosine was the most important metabolite in PQ poisoned patients. The metabolic disturbance caused by PQ poisoning cannot be improved by HP treatment even the PQ was cleared from the blood.

A Novel Deep-Learning Model for Automatic Detection and Classification of Breast Cancer Using the Transfer-Learning Technique

“…In future work, the proposed method can be further used to diagnosis or prognosis of paraquat-poisoned patients [104]- [109], identification of poisoning status [110]- [112], diagnosis of tuberculous pleural effusion [113], differentiation of malignant and benign thyroid nodules [114], early diagnosis of Parkinson's disease [115]- [119], RNA secondary structure prediction [120], detection of erythemato-squamous diseases [121], online recognition of foreign fibers in cotton [122].…”

Classification of acute poisoning exposures with machine learning models derived from the National Poison Data System

“…15 Dong et al investigated ML to predict opioid overdose, and found high recall using a random forest model and high accuracy with deep learning models. 22 Other studies have leveraged ML to predict paraquat poisoning prognosis, 23,24 seizures from tramadol poisoning, 25 adverse drug events in elderly patients, 26 smoking cessation treatment outcome, 27 lead poisoning in children, 28 pesticide ototoxicity 29 and inadequate medication responses in the emergency department. 30 In recent years, ML in medicine has garnered considerable interest, from anticipated cost-effectiveness, speed, and accuracy.…”

Paraquat and Diquat: Recent Updates on Their Pretreatment and Analysis Methods since 2010 in Biological Samples

“…It has significant advantages such as a high sensitivity, fast analysis speed, and high-resolution separation. There are a few papers that applied UHPLC–MS for the detection of PQ and DQ in biological samples [ 13 , 32 , 42 , 69 , 70 ]. Lu et al obtained LODs of 0.1 and 0.3 ng/mL and LOQs of 0.3 and 0.8 ng/mL for urine and plasma by UPLC–ESI–HRMS/MS, respectively [ 13 ].…”

“…Commonly used HRMS detectors include orbitrap MS, ion trap, time-of-flight mass spectrometry (TOF MS), and FTICR. FTICR/MS has an extremely high resolution, but its high data acquisition speed limits its on-line coupling with UPLC [ 68 , 69 , 70 , 71 ]. Time-of-flight mass spectrometry has innate performance advantages over quadrupole mass spectrometers.…”

“…HRMS has the advantages of a high mass spectrum resolution, a fast scanning speed, accurate isotopic abundance information, and a wide m / z dynamic scanning range that can supply accurate qualitative information. Moreover, HRMS has a unique advantage for screening unknown compounds, and its use in the field of metabolomics has become popular [ 51 , 69 , 70 , 74 ].…”