Publications

BibTex format

@article{Atabaki-Pasdar:2020:10.1371/journal.pmed.1003149,
author = {Atabaki-Pasdar, N and Ohlsson, M and Vinuela, A and Frau, F and Pomares-Millan, H and Haid, M and Jones, AG and Thomas, EL and Koivula, RW and Kurbasic, A and Mutie, PM and Fitipaldi, H and Fernandez, J and Dawed, AY and Giordano, GN and Forgie, IM and McDonald, TJ and Rutters, F and Cederberg, H and Chabanova, E and Dale, M and Masi, FD and Thomas, CE and Allin, KH and Hansen, TH and Heggie, A and Hong, M-G and Elders, PJM and Kennedy, G and Kokkola, T and Pedersen, HK and Mahajan, A and McEvoy, D and Pattou, F and Raverdy, V and Haussler, RS and Sharma, S and Thomsen, HS and Vangipurapu, J and Vestergaard, H and 't, Hart LM and Adamski, J and Musholt, PB and Brage, S and Brunak, S and Dermitzakis, E and Frost, G and Hansen, T and Laakso, M and Pedersen, O and Ridderstrale, M and Ruetten, H and Hattersley, AT and Walker, M and Beulens, JWJ and Mari, A and Schwenk, JM and Gupta, R and McCarthy, MI and Pearson, ER and Bell, JD and Pavo, I and Franks, PW},
doi = {10.1371/journal.pmed.1003149},
journal = {PLoS Medicine},
pages = {1--27},
title = {Predicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts},
url = {http://dx.doi.org/10.1371/journal.pmed.1003149},
volume = {17},
year = {2020}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - BackgroundNon-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in individuals with and without type 2 diabetes (T2D). Early diagnosis of NAFLD is important, as this can help prevent irreversible damage to the liver and, ultimately, hepatocellular carcinomas. We sought to expand etiological understanding and develop a diagnostic tool for NAFLD using machine learning.Methods and findingsWe utilized the baseline data from IMI DIRECT, a multicenter prospective cohort study of 3,029 European-ancestry adults recently diagnosed with T2D (n = 795) or at high risk of developing the disease (n = 2,234). Multi-omics (genetic, transcriptomic, proteomic, and metabolomic) and clinical (liver enzymes and other serological biomarkers, anthropometry, measures of beta-cell function, insulin sensitivity, and lifestyle) data comprised the key input variables. The models were trained on MRI-image-derived liver fat content (<5% or ≥5%) available for 1,514 participants. We applied LASSO (least absolute shrinkage and selection operator) to select features from the different layers of omics data and random forest analysis to develop the models. The prediction models included clinical and omics variables separately or in combination. A model including all omics and clinical variables yielded a cross-validated receiver operating characteristic area under the curve (ROCAUC) of 0.84 (95% CI 0.82, 0.86; p < 0.001), which compared with a ROCAUC of 0.82 (95% CI 0.81, 0.83; p < 0.001) for a model including 9 clinically accessible variables. The IMI DIRECT prediction models outperformed existing noninvasive NAFLD prediction tools. One limitation is that these analyses were performed in adults of European ancestry residing in northern Europe, and it is unknown how well these findings will translate to people of other ancestries and exposed to environmental risk factors that differ from those of the present cohort. Another key limitation of
AU  - Atabaki-Pasdar,N
AU  - Ohlsson,M
AU  - Vinuela,A
AU  - Frau,F
AU  - Pomares-Millan,H
AU  - Haid,M
AU  - Jones,AG
AU  - Thomas,EL
AU  - Koivula,RW
AU  - Kurbasic,A
AU  - Mutie,PM
AU  - Fitipaldi,H
AU  - Fernandez,J
AU  - Dawed,AY
AU  - Giordano,GN
AU  - Forgie,IM
AU  - McDonald,TJ
AU  - Rutters,F
AU  - Cederberg,H
AU  - Chabanova,E
AU  - Dale,M
AU  - Masi,FD
AU  - Thomas,CE
AU  - Allin,KH
AU  - Hansen,TH
AU  - Heggie,A
AU  - Hong,M-G
AU  - Elders,PJM
AU  - Kennedy,G
AU  - Kokkola,T
AU  - Pedersen,HK
AU  - Mahajan,A
AU  - McEvoy,D
AU  - Pattou,F
AU  - Raverdy,V
AU  - Haussler,RS
AU  - Sharma,S
AU  - Thomsen,HS
AU  - Vangipurapu,J
AU  - Vestergaard,H
AU  - 't,Hart LM
AU  - Adamski,J
AU  - Musholt,PB
AU  - Brage,S
AU  - Brunak,S
AU  - Dermitzakis,E
AU  - Frost,G
AU  - Hansen,T
AU  - Laakso,M
AU  - Pedersen,O
AU  - Ridderstrale,M
AU  - Ruetten,H
AU  - Hattersley,AT
AU  - Walker,M
AU  - Beulens,JWJ
AU  - Mari,A
AU  - Schwenk,JM
AU  - Gupta,R
AU  - McCarthy,MI
AU  - Pearson,ER
AU  - Bell,JD
AU  - Pavo,I
AU  - Franks,PW
DO  - 10.1371/journal.pmed.1003149
EP  - 27
PY  - 2020///
SN  - 1549-1277
SP  - 1
TI  - Predicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts
T2  - PLoS Medicine
UR  - http://dx.doi.org/10.1371/journal.pmed.1003149
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000544084400001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1003149
UR  - http://hdl.handle.net/10044/1/82912
VL  - 17
ER  -

Download

ProfessorJimmyBell

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)