Predicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Predicting and elucidating the etiology of fatty liver disease : A machine learning modeling and validation study in the IMI DIRECT cohorts. / Atabaki-Pasdar, Naeimeh; Ohlsson, Mattias; Viñuela, Ana; Frau, Francesca; Pomares-Millan, Hugo; Haid, Mark; Jones, Angus G; Thomas, E Louise; Koivula, Robert W; Kurbasic, Azra; Mutie, Pascal M; Fitipaldi, Hugo; Fernandez, Juan; Dawed, Adem Y; Giordano, Giuseppe N; Forgie, Ian M; McDonald, Timothy J; Rutters, Femke; Cederberg, Henna; Chabanova, Elizaveta; Dale, Matilda; Masi, Federico De; Thomas, Cecilia Engel; Allin, Kristine H.; Hansen, Tue H; Heggie, Alison; Hong, Mun-Gwan; Elders, Petra J M; Kennedy, Gwen; Kokkola, Tarja; Pedersen, Helle Krogh; Mahajan, Anubha; McEvoy, Donna; Pattou, Francois; Raverdy, Violeta; Häussler, Ragna S; Sharma, Sapna; Thomsen, Henrik S; Vangipurapu, Jagadish; Vestergaard, Henrik; Adamski, Jerzy; Musholt, Petra B; Brage, Søren; Brunak, Søren; Dermitzakis, Emmanouil; Frost, Gary; Hansen, Torben; Laakso, Markku; Pedersen, Oluf; IMI-DIRECT consortium.
I: PLoS Medicine, Bind 17, Nr. 6, e1003149, 2020.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Predicting and elucidating the etiology of fatty liver disease
T2 - A machine learning modeling and validation study in the IMI DIRECT cohorts
AU - Atabaki-Pasdar, Naeimeh
AU - Ohlsson, Mattias
AU - Viñuela, Ana
AU - Frau, Francesca
AU - Pomares-Millan, Hugo
AU - Haid, Mark
AU - Jones, Angus G
AU - Thomas, E Louise
AU - Koivula, Robert W
AU - Kurbasic, Azra
AU - Mutie, Pascal M
AU - Fitipaldi, Hugo
AU - Fernandez, Juan
AU - Dawed, Adem Y
AU - Giordano, Giuseppe N
AU - Forgie, Ian M
AU - McDonald, Timothy J
AU - Rutters, Femke
AU - Cederberg, Henna
AU - Chabanova, Elizaveta
AU - Dale, Matilda
AU - Masi, Federico De
AU - Thomas, Cecilia Engel
AU - Allin, Kristine H.
AU - Hansen, Tue H
AU - Heggie, Alison
AU - Hong, Mun-Gwan
AU - Elders, Petra J M
AU - Kennedy, Gwen
AU - Kokkola, Tarja
AU - Pedersen, Helle Krogh
AU - Mahajan, Anubha
AU - McEvoy, Donna
AU - Pattou, Francois
AU - Raverdy, Violeta
AU - Häussler, Ragna S
AU - Sharma, Sapna
AU - Thomsen, Henrik S
AU - Vangipurapu, Jagadish
AU - Vestergaard, Henrik
AU - Adamski, Jerzy
AU - Musholt, Petra B
AU - Brage, Søren
AU - Brunak, Søren
AU - Dermitzakis, Emmanouil
AU - Frost, Gary
AU - Hansen, Torben
AU - Laakso, Markku
AU - Pedersen, Oluf
AU - IMI-DIRECT consortium
PY - 2020
Y1 - 2020
N2 - BACKGROUND: Non-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 FINDINGS: We 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 this study is that the prediction was done on a binary outcome of liver fat quantity (<5% or ≥5%) rather than a continuous one.CONCLUSIONS: In this study, we developed several models with different combinations of clinical and omics data and identified biological features that appear to be associated with liver fat accumulation. In general, the clinical variables showed better prediction ability than the complex omics variables. However, the combination of omics and clinical variables yielded the highest accuracy. We have incorporated the developed clinical models into a web interface (see: https://www.predictliverfat.org/) and made it available to the community.TRIAL REGISTRATION: ClinicalTrials.gov NCT03814915.
AB - BACKGROUND: Non-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 FINDINGS: We 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 this study is that the prediction was done on a binary outcome of liver fat quantity (<5% or ≥5%) rather than a continuous one.CONCLUSIONS: In this study, we developed several models with different combinations of clinical and omics data and identified biological features that appear to be associated with liver fat accumulation. In general, the clinical variables showed better prediction ability than the complex omics variables. However, the combination of omics and clinical variables yielded the highest accuracy. We have incorporated the developed clinical models into a web interface (see: https://www.predictliverfat.org/) and made it available to the community.TRIAL REGISTRATION: ClinicalTrials.gov NCT03814915.
U2 - 10.1371/journal.pmed.1003149
DO - 10.1371/journal.pmed.1003149
M3 - Journal article
C2 - 32559194
VL - 17
JO - P L o S Medicine (Online)
JF - P L o S Medicine (Online)
SN - 1549-1277
IS - 6
M1 - e1003149
ER -
ID: 244996187