Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk
Objective: Obesity is a significant risk factor for adverse outcomes following coronavirus infection (COVID-19). However, BMI fails to capture differences in the body fat distribution, the critical driver of metabolic health. Conventional statistical methodologies lack functionality to investigate t...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Bioinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbinf.2023.1163430/full |
| _version_ | 1797821506877652992 |
|---|---|
| author | T. Waddell T. Waddell A. I. L. Namburete P. Duckworth N. Eichert H. Thomaides-Brears D. J. Cuthbertson D. J. Cuthbertson J. P. Despres M. Brady |
| author_facet | T. Waddell T. Waddell A. I. L. Namburete P. Duckworth N. Eichert H. Thomaides-Brears D. J. Cuthbertson D. J. Cuthbertson J. P. Despres M. Brady |
| author_sort | T. Waddell |
| collection | DOAJ |
| description | Objective: Obesity is a significant risk factor for adverse outcomes following coronavirus infection (COVID-19). However, BMI fails to capture differences in the body fat distribution, the critical driver of metabolic health. Conventional statistical methodologies lack functionality to investigate the causality between fat distribution and disease outcomes.Methods: We applied Bayesian network (BN) modelling to explore the mechanistic link between body fat deposition and hospitalisation risk in 459 participants with COVID-19 (395 non-hospitalised and 64 hospitalised). MRI-derived measures of visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), and liver fat were included. Conditional probability queries were performed to estimate the probability of hospitalisation after fixing the value of specific network variables.Results: The probability of hospitalisation was 18% higher in people living with obesity than those with normal weight, with elevated VAT being the primary determinant of obesity-related risk. Across all BMI categories, elevated VAT and liver fat (>10%) were associated with a 39% mean increase in the probability of hospitalisation. Among those with normal weight, reducing liver fat content from >10% to <5% reduced hospitalisation risk by 29%.Conclusion: Body fat distribution is a critical determinant of COVID-19 hospitalisation risk. BN modelling and probabilistic inferences assist our understanding of the mechanistic associations between imaging-derived phenotypes and COVID-19 hospitalisation risk. |
| first_indexed | 2024-03-13T09:53:41Z |
| format | Article |
| id | doaj.art-8b13b20ac7284ddb85cbc74952226f5c |
| institution | Directory Open Access Journal |
| issn | 2673-7647 |
| language | English |
| last_indexed | 2024-03-13T09:53:41Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioinformatics |
| spelling | doaj.art-8b13b20ac7284ddb85cbc74952226f5c2023-05-24T05:30:33ZengFrontiers Media S.A.Frontiers in Bioinformatics2673-76472023-05-01310.3389/fbinf.2023.11634301163430Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation riskT. Waddell0T. Waddell1A. I. L. Namburete2P. Duckworth3N. Eichert4H. Thomaides-Brears5D. J. Cuthbertson6D. J. Cuthbertson7J. P. Despres8M. Brady9Department of Engineering Science, The University of Oxford, Oxford, United KingdomPerspectum Ltd., Oxford, United KingdomDepartment of Computer Science, University of Oxford, Oxford, United KingdomOxford Robotics Institute, The University of Oxford, Oxford, United KingdomPerspectum Ltd., Oxford, United KingdomPerspectum Ltd., Oxford, United KingdomDepartment of Cardiovascular and Metabolic Medicine, Institute of Life Course and Medical Sciences, University of Liverpool, Liverpool, United KingdomLiverpool University Hospitals NHS Foundation Trust, Liverpool, United KingdomScientific director of VITAM – Research Center for Sustainable Health, Laval University, Quebec, QC, CanadaPerspectum Ltd., Oxford, United KingdomObjective: Obesity is a significant risk factor for adverse outcomes following coronavirus infection (COVID-19). However, BMI fails to capture differences in the body fat distribution, the critical driver of metabolic health. Conventional statistical methodologies lack functionality to investigate the causality between fat distribution and disease outcomes.Methods: We applied Bayesian network (BN) modelling to explore the mechanistic link between body fat deposition and hospitalisation risk in 459 participants with COVID-19 (395 non-hospitalised and 64 hospitalised). MRI-derived measures of visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), and liver fat were included. Conditional probability queries were performed to estimate the probability of hospitalisation after fixing the value of specific network variables.Results: The probability of hospitalisation was 18% higher in people living with obesity than those with normal weight, with elevated VAT being the primary determinant of obesity-related risk. Across all BMI categories, elevated VAT and liver fat (>10%) were associated with a 39% mean increase in the probability of hospitalisation. Among those with normal weight, reducing liver fat content from >10% to <5% reduced hospitalisation risk by 29%.Conclusion: Body fat distribution is a critical determinant of COVID-19 hospitalisation risk. BN modelling and probabilistic inferences assist our understanding of the mechanistic associations between imaging-derived phenotypes and COVID-19 hospitalisation risk.https://www.frontiersin.org/articles/10.3389/fbinf.2023.1163430/fullBayesian networksprobabilistic reasoningectopic fatCOVID-19hospitalisation |
| spellingShingle | T. Waddell T. Waddell A. I. L. Namburete P. Duckworth N. Eichert H. Thomaides-Brears D. J. Cuthbertson D. J. Cuthbertson J. P. Despres M. Brady Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk Frontiers in Bioinformatics Bayesian networks probabilistic reasoning ectopic fat COVID-19 hospitalisation |
| title | Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk |
| title_full | Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk |
| title_fullStr | Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk |
| title_full_unstemmed | Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk |
| title_short | Bayesian networks and imaging-derived phenotypes highlight the role of fat deposition in COVID-19 hospitalisation risk |
| title_sort | bayesian networks and imaging derived phenotypes highlight the role of fat deposition in covid 19 hospitalisation risk |
| topic | Bayesian networks probabilistic reasoning ectopic fat COVID-19 hospitalisation |
| url | https://www.frontiersin.org/articles/10.3389/fbinf.2023.1163430/full |
| work_keys_str_mv | AT twaddell bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT twaddell bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT ailnamburete bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT pduckworth bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT neichert bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT hthomaidesbrears bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT djcuthbertson bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT djcuthbertson bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT jpdespres bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk AT mbrady bayesiannetworksandimagingderivedphenotypeshighlighttheroleoffatdepositionincovid19hospitalisationrisk |