Prediction of Lung Function in Adolescence Using Epigenetic Aging: A Machine Learning Approach

Arefeen, Md Adnan; Nimi, Sumaiya Tabassum; Rahman, M. Sohel; Arshad, Syed Hasan; Holloway, John W.; Rezwan, Faisal I.

doi:10.3390/mps3040077

Cited by 4 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…b. Machine learning: Machine learning (ML) was reported in 46 studies to analyse, classify, diagnose, manage, monitor, and predict different health conditions or diseases (e.g., frailty, back pain, ischemic stroke, cancer, COVID-19, tuberculosis, diabetes, mortality, hypertension, mental health conditions, bacterial vaginosis, and heart disease) ( 21 , 22 , 25 – 27 , 30 , 33 , 37 , 39 , 41 , 43 , 46 , 47 , 50 , 52 , 54 , 56 , 58 , 60 , 63 , 65 , 67 , 70 , 71 , 73 , 76 , 77 , 81 , 82 , 84 , 87 , 92 , 96 , 101 , 103 , 105 , 108 , 110 ). This approach was also used to create patient re-admission files, pre-authorization in health insurance, and for finding missed cases of disease; these all form a significant part in delivering medical care services ( 30 , 76 , 111 ).…”

Section: Resultsmentioning

confidence: 99%

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

Okeibunor

Jaca

Iwu

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

BackgroundArtificial intelligence (AI) is a broad outlet of computer science aimed at constructing machines capable of simulating and performing tasks usually done by human beings. The aim of this scoping review is to map existing evidence on the use of AI in the delivery of medical care.MethodsWe searched PubMed and Scopus in March 2022, screened identified records for eligibility, assessed full texts of potentially eligible publications, and extracted data from included studies in duplicate, resolving differences through discussion, arbitration, and consensus. We then conducted a narrative synthesis of extracted data.ResultsSeveral AI methods have been used to detect, diagnose, classify, manage, treat, and monitor the prognosis of various health issues. These AI models have been used in various health conditions, including communicable diseases, non-communicable diseases, and mental health.ConclusionsPresently available evidence shows that AI models, predominantly deep learning, and machine learning, can significantly advance medical care delivery regarding the detection, diagnosis, management, and monitoring the prognosis of different illnesses.

show abstract

Section: Resultsmentioning

confidence: 99%

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

Okeibunor

Jaca

Iwu

et al. 2023

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Both FEV 1 and the ratio of FEV 1 to forced vital capacity (FVC) were significantly negatively associated with epigenetic age acceleration. Epigenetic age has also been used to predict lung capacity in adults [ 112 ]. More investigations are needed into the relationship between FEV and epigenetic age, particularly in pediatric cohorts.…”

Section: Applications Of the First-generation Epigenetic Clocks To As...mentioning

confidence: 99%

A Review of the Epigenetic Clock: Emerging Biomarkers for Asthma and Allergic Disease

Vasileva,

Greenwood,

Daley

2023

Genes

View full text Add to dashboard Cite

DNA methylation (DNAm) is a dynamic, age-dependent epigenetic modification that can be used to study interactions between genetic and environmental factors. Environmental exposures during critical periods of growth and development may alter DNAm patterns, leading to increased susceptibility to diseases such as asthma and allergies. One method to study the role of DNAm is the epigenetic clock—an algorithm that uses DNAm levels at select age-informative Cytosine-phosphate-Guanine (CpG) dinucleotides to predict epigenetic age (EA). The difference between EA and calendar age (CA) is termed epigenetic age acceleration (EAA) and reveals information about the biological capacity of an individual. Associations between EAA and disease susceptibility have been demonstrated for a variety of age-related conditions and, more recently, phenotypes such as asthma and allergic diseases, which often begin in childhood and progress throughout the lifespan. In this review, we explore different epigenetic clocks and how they have been applied, particularly as related to childhood asthma. We delve into how in utero and early life exposures (e.g., smoking, air pollution, maternal BMI) result in methylation changes. Furthermore, we explore the potential for EAA to be used as a biomarker for asthma and allergic diseases and identify areas for further study.

show abstract

“…Previous work found machine learning methods can predict smoking cessation and forced expiratory volume in one second (FEV 1 ), a spirometric measure used to determine COPD severity [ 2 – 4 ]. In particular, radial basis neural network predicted FEV 1 using spirometry data [ 5 ], and spirometry and demographic data [ 6 ], and the predicted and actual FEV 1 values were highly correlated.…”

Section: Introductionmentioning

confidence: 99%

Covariate adjustment of spirometric and smoking phenotypes: The potential of neural network models

et al. 2022

View full text Add to dashboard Cite

To increase power and minimize bias in statistical analyses, quantitative outcomes are often adjusted for precision and confounding variables using standard regression approaches. The outcome is modeled as a linear function of the precision variables and confounders; however, for many complex phenotypes, the assumptions of the linear regression models are not always met. As an alternative, we used neural networks for the modeling of complex phenotypes and covariate adjustments. We compared the prediction accuracy of the neural network models to that of classical approaches based on linear regression. Using data from the UK Biobank, COPDGene study, and Childhood Asthma Management Program (CAMP), we examined the features of neural networks in this context and compared them with traditional regression approaches for prediction of three outcomes: forced expiratory volume in one second (FEV1), age at smoking cessation, and log transformation of age at smoking cessation (due to age at smoking cessation being right-skewed). We used mean squared error to compare neural network and regression models, and found the models performed similarly unless the observed distribution of the phenotype was skewed, in which case the neural network had smaller mean squared error. Our results suggest neural network models have an advantage over standard regression approaches when the phenotypic distribution is skewed. However, when the distribution is not skewed, the approaches performed similarly. Our findings are relevant to studies that analyze phenotypes that are skewed by nature or where the phenotype of interest is skewed as a result of the ascertainment condition.

show abstract

Prediction of Lung Function in Adolescence Using Epigenetic Aging: A Machine Learning Approach

Cited by 4 publications

References 41 publications

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

A Review of the Epigenetic Clock: Emerging Biomarkers for Asthma and Allergic Disease

Covariate adjustment of spirometric and smoking phenotypes: The potential of neural network models

Contact Info

Product

Resources

About