DNA Methylation Signature on Phosphatidylethanol, not Self-Reported Alcohol Consumption, Predicts Hazardous Alcohol Consumption in Two Distinct Populations

Abstract

The process of diagnosing hazardous alcohol drinking (HAD) is based on self-reported data and is thereby vulnerable to bias. There has been an interest in developing epigenetic biomarkers for HAD that might complement clinical assessment. Because alcohol consumption has been previously linked to DNA methylation (DNAm), here, we aimed to select DNAm signatures in blood to predict HAD from two demographically and clinically distinct populations (N total =1,549). We first separately conducted an epigenome-wide association study (EWAS) for phosphatidylethanol (PEth), an objective measure of alcohol consumption, and for self-reported alcohol consumption in Cohort 1.We identified 102 PEth-associated CpGs, including 32 CpGs previously associated with alcohol consumption or alcohol use disorders. In contrast, no CpG reached epigenomewide significance on self-reported alcohol consumption. Using a machine learning approach, two subsets of CpGs from EWAS on PEth and on self-reported alcohol consumption from Cohort 1 were separately tested for the prediction of HAD in Cohort 2. We found that a subset of 130 CpGs selected from the EWAS on PEth showed an excellent prediction of HAD with area under the ROC curve (AUC) of 91.31% in training set and 70.65% in validation set of Cohort 2. However, CpGs preselected from the EWAS on self-reported alcohol consumption showed a poor prediction of HAD with AUC 75.18% in the training set and 57.60% in the validation set. Our results demonstrate that an objective measure for alcohol consumption is a more informative phenotype than self-reported data for revealing epigenetic mechanism. The PEthassociated DNAm signature in blood is a robust biomarker for alcohol consumption.is approximately 4-7 days 6 . Thus, other more stable biomarkers for alcohol consumption are needed to inform clinical practice.Epigenetic signatures have emerged as attractive biomarkers for complex diseases such as cancers and neurodegenerative diseases 7 . Epigenetic markers may reflect environmental exposures, including alcohol consumption. Among these epigenetic markers, DNA methylation (DNAm) biomarkers are particularly attractive because they are relatively stable and capture an early stage of pathophysiological changes 8,9 . A recent longitudinal study on DNAm showed that most DNA methylome changes occurred 80-90 days before clinically detectable glucose elevation 10 , suggesting that DNAm is involved in an early stage of diabetes. Finally, epigenetic modifications can be reliably detected in noninvasive fluids and biospecimens 11 . Thus, the utility of epigenetic alterations has motivated the biomarker research field to develop epigenetic signatures derived from easily accessible cells for clinical use [12][13][14] .DNAm markers are emerging as diagnostic biomarkers in many areas of medicine and are applied to predict complex diseases 15 . For example, DNAm markers on the promoters of several genes, including BMP3, NDRG4, and SPEPT9, in blood or stool samples have been approved by the Food and Drug Administration...

AI in patient flow: applications of artificial intelligence to improve patient flow in NHS acute mental health inpatient units

“…Some studies focused on developing triage and screening tools [ 44 , 45 , 46 ]. AI has also been applied to enhance our understanding of diseases [ 47 ], improve diagnostic accuracy [ 48 ], and even enable new diagnostic methods including novel biomarkers, such as DNA methylation [ 49 ]. In the field of prognosis, AI was used to improve accuracy and personalisation of predicting long-term outcomes such as severity [ 50 ] relapse, progression [ 51 ], and quality of life.…”

Applications of artificial intelligence to improve patient flow on mental health inpatient units - Narrative literature review

“…Liang et al. [ 19 ] used ML to develop an objective blood biomarker for hazardous alcohol consumption based on DNA methylation which had higher accuracy of diagnosis than traditional self-reporting (73.9% vs 57.5%). Additionally, research has been done to successfully screen and diagnose patients based on ‘natural language processing’ (NLP) analysis of self-reports [ 20 ] and clinical notes [ 21 ].…”

A New Monocyte Epigenetic Clock Reveals Effects of Alcohol Consumption on Epigenetic Aging in Three Independent Cohorts

“…A majority of HIV+ participants were on antiretroviral therapy and were virally suppressed (63.66%). Alcohol consumption was assessed by using PEth, a biomarker for alcohol use [22] that is positively correlated with AUDIT scores [41,42]. HAD was defined as PEth≥20 (N=299) according to a previous study [43].…”