Predicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts
Open accessPublished version of a preprint
The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
![Fig 1 Pearson pairwise correlation matrix of clinical variables (data are inverse normal transformed) in the cohort combining participants with and without diabetes in IMI DIRECT (n = 1,049). The magnitude and direction of the correlation are reflected by the size (larger is stronger) and color (red is positive and blue is negative) of the circles, respectively. ActGLP1min0, concentration of fasting active GLP-1 in plasma; ALT, alanine transaminase; AST, aspartate transaminase; AST_ALT, AST to ALT ratio; BasalISR, insulin secretion at the beginning of the oral glucose tolerance test/mixed-meal tolerance test; BMI, body mass index; CHOI, total daily intake of dietary carbohydrates; Chol, total cholesterol; Clins, mean insulin clearance during the oral glucose tolerance test/mixed-meal tolerance test, calculated as (mean insulin secretion)/(mean insulin concentration); Clinsb, insulin clearance calculated from basal values as (insulin secretion)/(insulin concentration); DBP, mean diastolic blood pressure; FatI, total daily intake of dietary fats; FLI, fatty liver index; FibreI, total daily intake of dietary Association of Official Analytical Chemists (AOAC) fiber; GGTP, gamma-glutamyl transpeptidase; Glucagonmin0, fasting glucagon concentration; Glucose, fasting glucose from venous plasma samples; GlucoseSens, glucose sensitivity, slope of the dose–response relating insulin secretion to glucose concentration; HbA1c, hemoglobin A1C; HDL, fasting high-density lipoprotein cholesterol; IncGLP1min60, 1-hour GLP-1 increment; IncGlucagonmin60, 1-hour glucagon increment; Insulin, fasting insulin from venous plasma samples; LDL, fasting low-density lipoprotein cholesterol; Matsuda, insulin sensitivity index according to the method of Matsuda et al. [23]; MeanGlucose, mean glucose during the oral glucose tolerance test/mixed-meal tolerance test; MeanInsulin, mean insulin during the oral glucose tolerance test/mixed-meal tolerance test; MUFatI, daily intake of dietary monounsaturated fats; OGIS, oral glucose insulin sensitivity index according to the method of Mari et al. [24]; PA_intensity_0_48f, number of values in high-pass-filtered vector magnitude physical activity at ≥0 and ≤48; PA_intensity_154_389f, number of values in high-pass-filtered vector magnitude physical activity at ≥154 and ≤389; PA_intensity_389_9999f, number of values in high-pass-filtered vector magnitude physical activity at ≥389 and ≤9,999; PA_intensity_48_154f, number of values in high-pass-filtered vector magnitude physical activity at ≥48 and ≤154; PA_intensity_mean, mean high-pass-filtered vector magnitude physical activity intensity; PFR, potentiation factor ratio; ProteinI, total daily intake of dietary proteins; PUFatI, daily intake of dietary polyunsaturated fats; RateSens, rate sensitivity (parameter characterizing early insulin secretion); SatFatI, daily intake of dietary saturated fats; SBP, mean systolic blood pressure; Stumvoll, insulin sensitivity index according to the method of Stumvoll et al. [25]; SugarI, total daily intake of dietary; TEI, total daily energy intake based on validated multi-pass food habit questionnaire; TG, fasting triglycerides; TotalISR, integral of insulin secretion during the whole oral glucose tolerance test/mixed-meal tolerance test; TotGLP1min0, concentration of fasting total GLP-1 in plasma; TwoGlucose, 2-hour glucose after oral glucose tolerance test/mixed-meal tolerance test; TwoInsulin, 2-hour insulin; Waist_Hip, waist to hip ratio.](https://figures.cochat.ai/paper-figures/c6afde009f044f439bdf277ccb72f2cd/predicting-and-elucidating-the-etiology-of-fatty-liver-disease-a-machine-figure-1.jpg)




![Fig 6 Variable importance for the advanced model 14 with 185 omics and clinical input variables (clinical = 22, genetic = 23, transcriptomic = 93, exploratory proteomic = 22, and targeted metabolomic = 25). The y-axis shows the top 20 predictors in the model. The x-axis shows the variable importance calculated, via a permutation accuracy importance measure using random forest analysis, as the difference in prediction accuracy before and after the permutation for each variable scaled by the standard error. ALT, alanine transaminase; AST, aspartate transaminase; BasalISR, insulin secretion at the beginning of the oral glucose tolerance test/mixed-meal tolerance test; BMI, body mass index; Clins, mean insulin clearance during the oral glucose tolerance test/mixed-meal tolerance test calculated as (mean insulin secretion)/(mean insulin concentration); FLT3, fetal liver tyrosine kinase-3; Insulin, fasting insulin from venous plasma samples; MYLIP, myosin regulatory light chain interacting protein; OGIS, oral glucose insulin sensitivity index according to the method of Mari et al. [24]; TG, fasting triglycerides; TotGLP1min0, concentration of fasting total GLP-1 in plasma; TwoInsulin, 2-hour insulin after oral glucose tolerance test/mixed meal tolerance test.](https://figures.cochat.ai/paper-figures/137180b4880f4b5480756e69a65eead9/predicting-and-elucidating-the-etiology-of-fatty-liver-disease-a-machine-figure-6.jpg)
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In the IMI-DIRECT study, Atabaki-Pasdar et al.93 identified several variables with high discriminative power for MASLD; those with the best performance were associated with lipids, i.e. PCs and glycerophospholipids, in particular ceramides, and included lipoprotein lipase proteins and the PNPLA3-148M gene variant.”
From Lipid metabolism in MASLD and MASH: From mechanism to the clinic (2024) · cites this paper as [93]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2025) · doi:10.32614/r.manuals · Cited by 352,181
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“The penalty applied by λ can be any value from 0 to positive infinity and is determined through a cross-validation step [26].”
Regularization Paths for Generalized Linear Models via Coordinate Descent
Friedman, J., Hastie, T., & Tibshirani, R. (2010) · Journal of Statistical Software · doi:10.18637/jss.v033.i01 · Cited by 19,927 · cited 1×
“LASSO was conducted with package glmnet in R [28] with a 10-fold cross-validation step for defining the λ parameter that resulted in the minimum value for the mean square error of the regression model.”
MethodTissue-based map of the human proteome
Uhlén, M., Fagerberg, L., Hallström, B. M., Lindskog, C., Oksvold, P., Mardinoglu, A., Sivertsson, Å., Kampf, C., Sjöstedt, E., Asplund, A., et al. (2015) · Science · doi:10.1126/science.1260419 · Cited by 15,286
Self-citationSudlow, C., Gallacher, J., Allen, N., Beral, V., Burton, P., Danesh, J., Downey, P., Elliott, P., Green, J., Landray, M., et al. (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001779 · Cited by 12,728 · cited 1×
“The UK Biobank cohort [38] was used to validate the clinical prediction models (models 1 and 2) derived using IMI DIRECT data (UK Biobank application ID: 18274).”
MethodYounossi, Z. M., Koenig, A. B., Abdelatif, D., Fazel, Y., Henry, L., & Wymer, M. (2016) · Hepatology · doi:10.1002/hep.28431 · Cited by 10,781
The metabolic syndrome—a new worldwide definition
Alberti, K. G. M., Zimmet, P., & Shaw, J. (2005) · The Lancet · doi:10.1016/s0140-6736(05)67402-8 · Cited by 9,352
An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression
Altman, N. S. (1992) · The American Statistician · doi:10.1080/00031305.1992.10475879 · Cited by 5,708 · cited 1×
“We used k-nearest neighbor [22] imputation with k equal to 10 as a means to reduce the loss of sample size, but found that this did not materially improve predictive power in subsequent analyses, so we decided not to include these imputed data.”
MethodMatsuda, M., & DeFronzo, R. A. (1999) · Diabetes Care · doi:10.2337/diacare.22.9.1462 · Cited by 5,621 · cited 1×
“[23]; MeanGlucose, mean glucose during the oral glucose tolerance test/mixed-meal tolerance test; MeanInsulin, mean insulin during the oral glucose tolerance test/mixed-meal tolerance test; MUFatI, daily intake of dietary monounsaturated fats; OGIS, oral glucose insulin sensitivity index according to the method of Mar…”
MethodBias in random forest variable importance measures: Illustrations, sources and a solution
Strobl, C., Boulesteix, A.-L., Zeileis, A., & Hothorn, T. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-25 · Cited by 3,688
Cited by
Asnicar, F., Berry, S. E., Valdes, A. M., Nguyen, L. H., Piccinno, G., Drew, D. A., Leeming, E., Gibson, R., Le Roy, C., Khatib, H. A., et al. (2021) · Nature Medicine · doi:10.1038/s41591-020-01183-8 · Cited by 995
Self-citationNoninvasive proteomic biomarkers for alcohol-related liver disease
Niu, L., Thiele, M., Geyer, P. E., Rasmussen, D. N., Webel, H. E., Santos, A., Gupta, R., Meier, F., Strauss, M., Kjaergaard, M., et al. (2022) · Nature Medicine · doi:10.1038/s41591-022-01850-y · Cited by 309
Self-citationInter-organ crosstalk during development and progression of type 2 diabetes mellitus
Xourafa, G., Korbmacher, M., & Roden, M. (2024) · Nature Reviews Endocrinology · doi:10.1038/s41574-023-00898-1 · Cited by 274
“The IMI-DIRECT analysis highlighted circulating IGFBP1, IGFBP2, CXCL1 and the TNF super-family member CD30 (TNFRSF8) as predictors of (pre)T2DM-related NAFLD 237 .”
BackgroundMethodLipid metabolism in MASLD and MASH: From mechanism to the clinic
Carli, F., Della Pepa, G., Sabatini, S., Vidal Puig, A., & Gastaldelli, A. (2024) · JHEP Reports · doi:10.1016/j.jhepr.2024.101185 · Cited by 147
Ghosh, S., Zhao, X., Alim, M., Brudno, M., & Bhat, M. (2024) · Gut · doi:10.1136/gutjnl-2023-331740 · Cited by 129
“34 In their multiomics study, Atabaki-Pasdar et al 43 found that integrating genetic, transcriptomic, proteomic and metabolomic with clinical variables yielded better performance (AUROC 0.84) compared with using clinical variables alone (AUROC 0.82) in predicting liver fat quantity.”
InfluentialDecharatanachart, P., Chaiteerakij, R., Tiyarattanachai, T., & Treeprasertsuk, S. (2021) · Therapeutic Advances in Gastroenterology · doi:10.1177/17562848211062807 · Cited by 74
Liu, Y.-X., Liu, X., Cen, C., Li, X., Liu, J., Ming, Z., Yu, S., Tang, X., Zhou, L., Yu, J., et al. (2021) · Hepatobiliary & pancreatic diseases international · doi:10.1016/j.hbpd.2021.08.004 · Cited by 68
Huber, H., Schieren, A., Holst, J. J., & Simon, M.-C. (2024) · The American Journal of Clinical Nutrition · doi:10.1016/j.ajcnut.2024.01.007 · Cited by 62
“Population-based studies have reported that elevated fasting total GLP-1 concentrations are predictive of increased liver fat [84] and cardiometabolic risks [85], whereas higher physical activity is associated with lower fasting GLP-1 concentrations.”
BackgroundArtificial Intelligence Applications in Hepatology
Schattenberg, J. M., Chalasani, N., & Alkhouri, N. (2023) · Clinical Gastroenterology and Hepatology · doi:10.1016/j.cgh.2023.04.007 · Cited by 76
Stinson, S. E., Jonsson, A. E., Lund, M. A. V., Frithioff‐Bøjsøe, C., Holm, L. A., Pedersen, O. B., Ängquist, L. H., Sørensen, T. I. A., Holst, J. J., Christiansen, M., et al. (2021) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/clinem/dgab098 · Cited by 66
“In fact, a recent study found fasting total GLP-1 to be among the top 20 predictors of magnetic resonance imaging–derived liver fat content in a machine learning and validation model composed of 185 different omics and clinical input variables in the IMI DIRECT prospective cohort study (57).”
BackgroundSelf-citationOpportunities and barriers in omics-based biomarker discovery for steatotic liver diseases
Thiele, M. S., Villesen, I. F., Niu, L., Johansen, S., Sulek, K., Nishijima, S., Espen, L. V., Keller, M. I., Israelsen, M. E., Suvitaival, T., et al. (2024) · Journal of Hepatology · doi:10.1016/j.jhep.2024.03.035 · Cited by 75
Self-citationDevelopment of a novel machine learning model to predict presence of nonalcoholic steatohepatitis
Docherty, M., Régnier, S. A., Capkun, G., Balp, M., Ye, Q., Janssens, N., Tietz, A., Löffler, J., Cai, J. X., Pedrosa, M. C., et al. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocab003 · Cited by 58
“NASH and healthy patients may be more differentiated than NASH and non-NASH NAFLD.”
MethodInfluentialPrecision medicine for cardiometabolic disease: a framework for clinical translation
Franks, P. W., Cefalu, W. T., Dennis, J., Florez, J. C., Mathieu, C., Morton, R. W., Ridderstråle, M., Sillesen, H. H., & Stehouwer, C. D. A. (2023) · The Lancet Diabetes & Endocrinology · doi:10.1016/s2213-8587(23)00165-1 · Cited by 66
Self-citationWu, L., Zhao, Y., Lin, P., Qin, H., Liu, Y., Wan, D., Li, X., He, Y., & Yang, H. (2021) · BMC Medical Imaging · doi:10.1186/s12880-021-00610-7 · Cited by 51
“Abbreviations DCIS: Ductal carcinoma in situ; ER: Estrogen receptor; PR: Progesterone receptor; HER2: Human epidermal growth factor receptor-2; AUC : Area under the curve; CI: Confidence interval; IHC: Immunohistochemistry; US: Ultrasound; MRI: Magnetic resonance imaging; BI-RADS: Breast imaging reporting and data sys…”
MethodDinani, A. M., Kowdley, K. V., & Noureddin, M. (2021) · Hepatology · doi:10.1002/hep.31869 · Cited by 43
“Further studies to differentiate NAFLD stages are included in Table 1.(5,6)”
BackgroundMachine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record
Sun, Q., Zou, X., Yan, Y., Zhang, H., Wang, S., Gao, Y., Liu, H., Liu, S., Lu, J., Yang, Y., et al. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/9635526 · Cited by 70
“In a recent study, the RF algorithm had also achieved a good predictive effect in fatty liver disease [31], suggesting that the RF algorithm had advantages in the processing of clinical electronic medical records.”
BackgroundMachine Learning in liver disease diagnosis: Current progress and future opportunities
Tanwar, N., & Rahman, K. F. (2021) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1022/1/012029 · Cited by 39
McTeer, M., Applegate, D., Mesenbrink, P. G., Ratziu, V., Schattenberg, J. M., Bugianesi, E., Geier, A., Romero‐Gómez, M., Dufour, J., Ekstedt, M., et al. (2024) · PLoS ONE · doi:10.1371/journal.pone.0299487 · Cited by 45
Ultrasound‐Based Machine Learning Approach for Detection of Nonalcoholic Fatty Liver Disease
Tahmasebi, A., Wang, S., Wessner, C. E., Vu, T. T. T., Liu, J., Forsberg, F., Civan, J. M., Guglielmo, F. F., & Eisenbrey, J. R. (2023) · Journal of Ultrasound in Medicine · doi:10.1002/jum.16194 · Cited by 37
“48 – 50 Biswas et al developed a deep learning-based paradigm for detection and risk strati fi cation of biopsy proven fatty liver disease using ultrasound.”
BackgroundYanavich, C., Pacheco, A. G., Cardoso, S., Nunes, E., Chaves, U. S. B., de Freitas, G. R. P., dos Santos, R. R., Morata, M. M. S., Veloso, V. G., Grinsztejn, B. G. J., et al. (2021) · HIV Medicine · doi:10.1111/hiv.13060 · Cited by 38
Longitudinal plasma protein profiling of newly diagnosed type 2 diabetes
Gummesson, A., Björnson, E., Fagerberg, L., Zhong, W., Tebani, A., Edfors, F., Schmidt, C., Lundqvist, A., Adiels, M., Bäckhed, F., et al. (2020) · EBioMedicine · doi:10.1016/j.ebiom.2020.103147 · Cited by 37
Self-citationZhang, P., Wang, Z., Qiu, H., Zhou, W., Wang, M., & Cheng, G. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.05.024 · Cited by 39
“Lasso has been successfully applied to metabolomics data analysis, and novel metabolite markers related to liver disease and neurological diseases have been found [19–21].”
MethodLiu, F., Tang, X., Mao, B., Zhang, Q., Zhao, J., Cui, S., & Chen, W. (2022) · Nutrients · doi:10.3390/nu14194180 · Cited by 34
“Visceral obesity and insulin resistance play a role in the development and maintenance of hepatic inflammation, and NAFLD is defined by hepatocellular fat accumulation and inflammation, both of which are factors that may significantly worsen health [4,5].”
BackgroundMethodThe application of artificial intelligence in hepatology: A systematic review
Balsano, C., Alisi, A., Brunetto, M. R., Invernizzi, P., Burra, P., Piscaglia, F., Alvaro, D., Bonino, F., Carbone, M., Faita, F., et al. (2021) · Digestive and Liver Disease · doi:10.1016/j.dld.2021.06.011 · Cited by 34
Kamada, Y., Nakamura, T., Isobe, S., Hosono, K., Suama, Y., Ohtakaki, Y., Nauchi, A., Yasuda, N., Mitsuta, S., Miura, K., et al. (2022) · Journal of Gastroenterology · doi:10.1007/s00535-022-01932-1 · Cited by 39
Yang, B., Lu, H., & Ran, Y. (2024) · Frontiers in Endocrinology · doi:10.3389/fendo.2024.1450317 · Cited by 36
Adiposity, metabolomic biomarkers, and risk of nonalcoholic fatty liver disease: a case-cohort study
Pang, Y., Kartsonaki, C., Lv, J., Millwood, I. Y., Fairhurst-Hunter, Z., Turnbull, I. J., Bragg, F., Hill, M., Yu, C., Guo, Y., et al. (2021) · American Journal of Clinical Nutrition · doi:10.1093/ajcn/nqab392 · Cited by 32
Mehta, S., Huey, S. L., Fahim, S. M., Sinha, S., Rajagopalan, K., Ahmed, T., Knight, R. D., & Finkelstein, J. L. (2025) · Nature Communications · doi:10.1038/s41467-025-62985-3 · Cited by 47
“Training ML models on MRI-derived images of liver fat content along with other ‘ omics and clinical data have also been used to diagnose NAFLD and outperformed existing prediction tools 77 .”
Artificial intelligence applied to omics data in liver diseases: Enhancing clinical predictions
Baciu, C., Xu, C., Alim, M., Prayitno, K., & Bhat, M. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.1050439 · Cited by 27
“Using multi-omics, two studies used random forest (RF) models for early diagnosis of NAFLD and prediction of the progression from NAFLD to NASH (Atabaki-Pasdar et al., 2020; Oh et al., 2020).”
BackgroundMethodInfluentialDisease classification, diagnostic challenges, and evolving clinical trial design in MASLD
Lauridsen, M. M., Ravnskjær, K., Gluud, L. L., & Sanyal, A. J. (2025) · Journal of Clinical Investigation · doi:10.1172/jci189953 · Cited by 34
Defining NASH from a Multi-Omics Systems Biology Perspective
Niu, L., Sulek, K., Vasilopoulou, C. G., Santos, A., Albrechtsen, N. J. W., Rasmussen, S., Meier, F., & Mann, M. (2021) · Journal of Clinical Medicine · doi:10.3390/jcm10204673 · Cited by 24
“Only a few of these studies took a step further to demonstrate the predictive or discriminative power of proposed biomarkers by building machine learning-based classification models, often predicting only one type of pathological condition: fatty liver [89,90], and recently fibrosis [91].”
BackgroundMethodInfluentialLi, H., Hou, Y., Xin, W., Ding, L., Yang, Y., Zhang, Y., Wu, W., Wang, Z., & Ding, W. (2025) · Pharmacological Research · doi:10.1016/j.phrs.2025.107647 · Cited by 28
Yu, Y., Yang, Y., Li, Q., Yuan, J., & Zha, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-96478-6 · Cited by 29
Predicting Non-Alcoholic Steatohepatitis: A Lipidomics-Driven Machine Learning Approach
Mouskeftara, T., Kalopitas, G., Liapikos, T., Arvanitakis, K., Germanidis, G. S., & Gika, H. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25115965 · Cited by 20
“Additionally, a number of published studies have explored the effectiveness of Machine Learning (ML) approaches in predicting the different phenotypes of NAFLD [22–25].”
BackgroundMethodInfluentialZhong, J., Cai, Z., Zhu, G., & Zhang, J. (2025) · Diabetes Obesity and Metabolism · doi:10.1111/dom.16348 · Cited by 18
Stinson, S. E., Jonsson, A. E., Alzola, I. F. D. R., Lund, M. A. V., Frithioff‐Bøjsøe, C., Holm, L. A., Fonvig, C. E., Pedersen, O. B., Ängquist, L. H., Sørensen, T. I. A., et al. (2022) · The Journal of Clinical Endocrinology & Metabolism · doi:10.1210/clinem/dgac108 · Cited by 19
“A similar finding 302 has been reported in adults with and without T2D (n = 1049) from the IMI DIRECT Study (9,41).”
ResultSelf-citationYasar, O., Long, P., Harder, B., Marshall, H., Bhasin, S., Lee, S., DeLegge, M. H., Roy, S., Doyle, O., Leavitt, N., et al. (2022) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2021-100510 · Cited by 17
Bermingham, K. M., Smith, H., Duncan, E. L., Gonzalez, J. T., Valdes, A. M., Franks, P. W., Delahanty, L. M., Dashti, H. S., Davies, R., Hadjigeorgiou, G. M., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-70308-3 · Cited by 21
“TIR 3.9 – 5.6 (%), TITR 3.9 – 7.8 (%), glycaemic variability (CV %), and mean daily glucose (mmol/L) for Liver Fat Probability (cut-off 0.4) 40 .”
InfluentialSelf-citationIntegrative Characterization of Immune-relevant Genes in Hepatocellular Carcinoma
Hong, W.-F., Gu, Y., Wang, N., Xia, J. L., Zhou, H., Zhan, K., Cheng, M.-X., & Cai, Y. (2021) · Journal of Clinical and Translational Hepatology · doi:10.14218/jcth.2020.00132 · Cited by 18
Ullal, T., Lakin, S. M., Gallagher, B., Sbardellati, N., Abdo, Z., & Twedt, D. C. (2022) · Journal of Veterinary Internal Medicine · doi:10.1111/jvim.16580 · Cited by 14
“logic datasets to develop and validate artificial neural network algorithms similar to those developed for humans.(100,101,103) Such algorithms could dramatically improve our ability to screen, predict,”
MethodLan, L., Feng, K., Wu, Y., Zhang, W., Wei, L., Che, H., Xue, L., Gao, Y., Tao, J., Qian, S., et al. (2023) · Phenomics · doi:10.1007/s43657-023-00128-8 · Cited by 14
“Machine learning has been utilized to non-alcoholic fatty liver disease (NAFLD) and identify biological players in liver fat accumulation (Atabaki-Pasdar et al. 2020).”
BackgroundIntelligent Identification of Liver Diseases Based on Incremental Hidden Layer Neurons ANN Model
Terlapu, P. V., Sadi, R. P. R., Pondreti, R., & Tippana, C. R. (2022) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/110183 · Cited by 13
Liang, C., Li, J., Tian, B., Tian, L., Liu, Y., Li, J., Xin, L., Wang, J., Fu, C., Shi, Z., et al. (2021) · Biomedicine & Pharmacotherapy · doi:10.1016/j.biopha.2021.112298 · Cited by 14
Nivethitha, V., Daniel, R. A., Debnath, A., Dwarakanathan, V., Jeer, G., & Kavipriya, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-17386-3 · Cited by 14
Johansen, M. J., Lund, M. A. V., Ängquist, L. H., Fonvig, C. E., Holm, L. A., Chabanova, E., Thomsen, H. S., Hansen, T. F., & Holm, J. (2022) · Pediatric Obesity · doi:10.1111/ijpo.12947 · Cited by 12
“A recent study by Atabaki-Pasdar et al.(49) has shown the feasibility of using surrogate markers in a model to predict NAFLD in adults.”
BackgroundSelf-citationArtificial intelligence in nonalcoholic fatty liver disease
Mahzari, A. (2022) · Egyptian Liver Journal · doi:10.1186/s43066-022-00224-w · Cited by 10
“…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 [4].”
InfluentialZhu, Z., Chen, Y., Qin, X., Liu, S., Wang, J., & Ren, H. (2023) · Smart Medicine · doi:10.1002/smmd.20220029 · Cited by 10
Ramesh, D., Manickavel, P., Ghosh, S., & Bhat, M. (2025) · Journal of Clinical and Experimental Hepatology · doi:10.1016/j.jceh.2025.102611 · Cited by 11
Zhu, X., Ventura, E. F., Bansal, S., Wijeyesekera, A., & Vimaleswaran, K. S. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109661 · Cited by 7
Atabaki, N. N., Coral, D., Pomares‐Millan, H., Smith, K., Behjat, H., Koivula, R. W., Tura, A., Miller, H., Pinnick, K. E., Agudelo, L. Z., et al. (2026) · Metabolism · doi:10.1016/j.metabol.2026.156552 · Cited by 8
Self-citationSubramanian, R., Tang, R. H., Zhang, Z., Joshi, V., Miner, J. N., & Lo, Y. (2022) · Scientific Reports · doi:10.1038/s41598-022-15364-7 · Cited by 9
Feng, A., Zhao, H., Qiu, C., Luo, D., Wu, H., Meng, X., Li, L., & Zou, H. (2025) · Infectious Diseases of Poverty · doi:10.1186/s40249-025-01291-y · Cited by 7
“LASSO has been applied in various metabolomics data analyses to perform necessary data reduction prior to building the model [35, 36].”
Raj, H., Niharika, G., Kodipalli, A., & Rao, T. (2024) · IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS) · doi:10.1109/iciteics61368.2024.10625550 · Cited by 5
“The authors [25] Naeimeh Atabaki-Pasdar they used data from the IMI DIRECT study to develop prediction models for liver fat content.”
MethodDagher, J., Nassar, M., & Faour, W. H. (2025) · European Journal of Pharmacology · doi:10.1016/j.ejphar.2025.178183 · Cited by 5
Lei, P., Hu, N., Wu, Y., Tang, M., Chong, L., Kong, L., Zhang, L., Luo, P., & Chan, L. (2023) · iRadiology · doi:10.1002/ird3.24 · Cited by 6
Mao, L., Yu, Z. T., Lin, L., Sharma, M., Song, H., Zhao, H., & Xu, X. (2024) · JMIR Aging · doi:10.2196/59810 · Cited by 7
“Furthermore, to mitigate overfitting and enhance model generalization [36], external 5-fold cross-validation was implemented.”
MethodMatboli, M., Hamady, S., Saad, M., Khaled, R., Khaled, A., Barakat, E., Sayed, S. A., Agwa, S. H. A., & Youssef, I. (2024) · Non-coding RNA Research · doi:10.1016/j.ncrna.2024.10.002 · Cited by 5
“Atabaki-Pasdar et al. (2020), used a selection operator (LASSO) model and a least absolute shrinkage for selecting features and developed several random forest models to predict whether liver fat was less than 5 % or equal to or greater than 5 %, indicating non-MASLD or MASLD [105], respectively.”
Jiang, C., Liang, J., Hu, K., Ye, Y., Yang, J., Zhang, X., Ye, G., Zhang, J., Zhang, D., Zhong, B., et al. (2025) · Endocrine Connections · doi:10.1530/ec-24-0470 · Cited by 3
“LASSO is a regularized linear logistic regression analysis method that minimizes the over fi tting that may occur with high-dimensional data (32, 33).”
Bromfield, B. B., CHIMENE-WEISS, J. I., Gheewalla, G., Feldman, T., Mitten, E. K., Portincasa, P., & Baffy, G. (2026) · EClinicalMedicine · doi:10.1016/j.eclinm.2026.103921 · Cited by 5
A descriptive study of fatty liver disease detection using machine learning
Singh, J., Thakral, P., & Kaur, R. (2023) · AIP conference proceedings · doi:10.1063/5.0133327 · Cited by 3
Prediction of nonalcoholic fatty liver disease using machine learning
Makka, S., Naveen, S., Puranam, S. S. K., & Srikesh, S. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-21870-5.00032-7 · Cited by 3
Qin, Y., Chhetri, P. D., Theusch, E., Lim, G., Teker, S. S., Kuang, Y.-L., Raftar, S. K. A., Mehraban, M. H., Munoz-Howell, A., Saxena, V., et al. (2025) · Stem Cells Translational Medicine · doi:10.1093/stcltm/szaf066 · Cited by 2
Sadeghi, B., Zarrinbal, M., Poustchi, H., Sadeghi, A., & Taheri, E. (2026) · Scientific Reports · doi:10.1038/s41598-026-36834-2 · Cited by 3
Artificial Intelligence in Identifying Patients With Undiagnosed Nonalcoholic Steatohepatitis
Başer, O., Samayoa, G., Yapar, N., & Baser, E. (2024) · Journal of health economics and outcomes research · doi:10.36469/jheor.2024.123645 · Cited by 3
Decoding MASLD Progression: A Molecular Trajectory-Based Framework for Modelling Disease DynamicsPreprint
Kamzolas, I., Koutsandreas, T., Barker, C. G., Pournara, A. V., Weston, H., Fujiwara, N., Hoshida, Y., Anstee, Q. M., Vacca, M., Papatheodorou, I., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.14.632908 · Cited by 2
Atabaki, N. N., Coral, D., Pomares‐Millan, H., Smith, K., Behjat, H., Koivula, R. W., Tura, A., Miller, H., Pinnick, K. E., Agudelo, L. Z., et al. (2025) · medRxiv · doi:10.1101/2025.06.02.25328773 · Cited by 2
Self-citationCoFIM: A Computational Framework for Proteomic and Metabolomic Integrated Data Analysis
Zhong, A., Liu, A., & Wu, A. Y. (2021) · International Conference on Digital Medicine and Image Processing (DMIP) · doi:10.1145/3506651.3506658 · Cited by 1
“…models in diagnosing diseases such as using ExtraTrees classification models to analyze multi-omics data to predict COVID-19 severity [23] or using a total of 18 prediction models to develop accurate noninvasive methods to aid in the clinical prediction of Non-alcoholic fatty liver disease [24].”
MethodJauniaux, B., Burke, L., Snook, N. J., Καρακάντζα, Μ., Kerr, M., Wilson, M., Zougman, A., Bellamy, M. C., Banks, R. E., & Moore, J. K. (2024) · Transfusion and Apheresis Science · doi:10.1016/j.transci.2024.104028 · Cited by 2
Global trends in artificial intelligence applications in liver disease over seventeen years
Zhou, X., Huang, S., Shi, X.-M., Liu, S., Zhang, W., Shi, L., Lv, M., & Tang, X. (2025) · World Journal of Hepatology · doi:10.4254/wjh.v17.i3.101721 · Cited by 5
Yang, F., Sun, X., Jiang, K., Zhang, M., & Sun, C. (2026) · Diabetes/Metabolism Research and Reviews · doi:10.1002/dmrr.70129 · Cited by 2
“Moreover, Atabaki‐Pasdar et al. [56] utilised baseline data from the Innovative Medicines Initiative Diabetes Research on Patient Stratification cohort, applied LASSO and RF analysis, and integrated clinical and multi‐omics resources to develop a highly accurate MASLD prediction model.”
Zeng, J., Cai, K., Zheng, J., Hu, P., Dong, Y., Ren, X., Guo, Y., Guo, X., Zheng, Y., Liu, F., et al. (2026) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2026.03.006 · Cited by 1
Wang, R., Liu, C., Xue, M., Qian, J., & Hu, Y. (2026) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2026.111619 · Cited by 3
Fatty Chain Acids Risk Factors in Sudden Infant Death Syndrome: A Genetic Algorithm Approach
Villagrana-Bañuelos, K. E., Zanella-Calzada, L. A., Gonzalez-Curiel, I. E., Galván-Tejada, J. I., & Galvan-Tejada, C. E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60884-2_18 · Cited by 1
Application of artificial intelligence in non-alcoholic fatty liver disease and viral hepatitis
Gunasekharan, A., Jiang, J. H., Nickerson, A. M., Jalil, S., & Mumtaz, K. (2022) · Artificial Intelligence in Gastroenterology · doi:10.35712/aig.v3.i2.46 · Cited by 1
A commentary on “Causal relationship between gut microbiota and obstructive sleep apnea”
Li, S., & Jiang, J. (2024) · Archives of Gerontology and Geriatrics · doi:10.1016/j.archger.2024.105497 · Cited by 1
Gao, Y., Wu, F., Guo, W., Zheng, H., Zhang, L., Chen, X., & Li, M. (2022) · European Journal of Gastroenterology & Hepatology · doi:10.1097/meg.0000000000002451 · Cited by 1
Leveraging AutoML to provide NAFLD screening diagnosis: Proposed machine learning models
Bangash, A. H. (2023) · Journal of Heart and Vasculature · doi:10.31579/2834-8788/014 · Cited by 1
Fu, Y., Li, F., Fustel, P. B., Zhao, L., Jia, L., Zheng, H., Sun, Q., Rong, S. S., Tang, H., Xue, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.08807 · Cited by 1
Silva, K. D., Demmer, R. T., Jönsson, D., Mousa, A., Forbes, A. B., & Enticott, J. (2022) · medRxiv · doi:10.1101/2022.02.07.22270652 · Cited by 1
“geared to optimizing prediction, although it is increasingly used to derive etiologic insights of diseases [52, 53].”
BackgroundAtabaki‐Pasdar, N., Pomares‐Millan, H., Koivula, R. W., Tura, A., Brown, A. A., Viñuela, A., Agudelo, L. Z., Coral, D., van Oort, S., Allin, K. H., et al. (2021) · medRxiv · doi:10.1101/2021.08.31.21262709
Self-citationFu, Y., Li, F., Fustel, P. B., Zhao, L., Jia, L., Zheng, H., Sun, Q., Rong, S. S., Tang, H., Xue, X., et al. (2021) · medRxiv · doi:10.1101/2021.09.24.21263766
Fu, Y., Li, F., Fustel, P. B., Zhao, L., Jia, L., Zheng, H., Sun, Q., Rong, S. S., Tang, H., Xue, X., et al. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3925473
Artificial Intelligence in Identifying Patients with Undiagnosed Nonalcoholic SteatohepatitisPreprint
Başer, O., Samayoa, G., Yapar, N., & Baser, E. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4481966
Deshmukh, A. A., Krishna, R. V. V., Salman, R., Sandhiya, S., Balajee, J. M., & Pilli, D. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150273 · Cited by 1
Wu, L., Zhao, Y., Lin, P., Qin, H., Liu, Y., Wan, D., Li, X., He, Y., & Yang, H. (2021) · Figshare · doi:10.6084/m9.figshare.14609062
Wu, L., Zhao, Y., Lin, P., Qin, H., Liu, Y., Wan, D., Li, X., He, Y., & Yang, H. (2021) · Figshare · doi:10.6084/m9.figshare.14609065
Mao, L., Yu, Z. T., Lin, L., Sharma, M., Song, H., Zhao, H., & Xu, X. (2024) · doi:10.2196/preprints.59810
Park, H., Lee, Y.-R., Che, X., & Kim, J.-M. (2024) · doi:10.2196/preprints.63621
Detecting Non-Alcoholic Fatty Liver Disease (NAFLD) using Clinical Reports
Warrier, L., Devika, M., Raghavendra, P., & R, R. S. (2024) · Kalpa publications in computing · doi:10.29007/6x7w
“Studies by Wu et al. [17], Atabaki et al. [18], and Chen et al. [19] have explored the development and comparison of ML models for early prediction of liver disease, demonstrating promising results with high AU-ROC values.”
Xia, P., Li, X., Peng, J., Hu, K., Ling, J., Wu, Y., Liang, J., Liu, Y., Xiong, Y., Liu, J., et al. (2025) · Journal of Bioenergetics and Biomembranes · doi:10.1007/s10863-025-10078-7
“Additionally, we constructed an interaction network between differentially expressed RBPs and differential seen a significant rise in its incidence and prevalence globally, imposing a substantial health and economic burden on society (Noureddin et al. 2022 ; Atabaki-Pasdar et al. 2020 ).”
Multiomics biomarkers of health and disease
Titz, B., & Ivanov, N. V. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-19116-9.00043-9
Targeting the Gut-Liver Mitochondria Axis in MASLD: Mechanisms and Therapeutic Perspectives
Wang, Y., He, X., Lin, L., Ning, L.-L., Zhao, Y., Zhang, M.-X., Chen, L., & Chen, M. (2026) · Current Medical Science · doi:10.1007/s11596-026-00190-z · Cited by 1
Yu, H., Huang, Y., Wang, J., Zhang, J., Yang, L., Geng, T., Liu, G., Pan, A., & Liao, Y. (2026) · Diabetes Obesity and Metabolism · doi:10.1111/dom.70824
“…despite advances in large-scale proteomic technologies [9], only a limited number of plasma proteins have been identified for predicting MALOs in individuals with MASLD [10, 11], primarily constrained by small sample sizes, cross-sectional designs and a narrow scope of protein measurements [12–14].”
Sharma, A. N., Bhagavatula, H., Mapundu, M. T., & Chimusa, E. R. (2026) · Frontiers in Oncology · doi:10.3389/fonc.2026.1803957 · Cited by 1
Liu, Z. H., Song, M., Heng, Y., Nie, T., Xu, J., Wu, X., Shen, L., Cao, Y. X., Wu, F., & Qin, L. (2026) · BMC Medical Imaging · doi:10.1186/s12880-026-02563-1
“This approach is advantageous as it can comprehensively and efficiently identify those indicators that are highly correlated with patient prognosis from a large dataset, compared to traditional methods [34].”
Hira, S., K, S. G., Swarnalatha, S., Prema, R., George, A. S. H., & Chinnusamy, S. (2026) · International Conference on Natural Language Processing and Computer Vision (ICNPCV) · doi:10.1109/icnpcv69434.2026.11708912
Qin, Z., Juramt, D., Chen, Y., Li, Y., Wei, J., Yang, H., Chen, L., & Qiu, W. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1946657
“Although the full model only modestly improved discrimination over clinically accessible variables alone, the study showed how ML can prioritize molecular features associated with fatty liver disease (114).”
Metadata
- Authors
- Atabaki-Pasdar, N., Ohlsson, M., Viñuela, A., Frau, F., Pomares-Millan, H., Haid, M., Jones, A. G., Thomas, E. L., Koivula, R. W., Kurbasic, A., Mutie, P. M., Fitipaldi, H., Fernandez, J., Dawed, A. Y., Giordano, G. N., Forgie, I. M., McDonald, T. J., Rutters, F., Cederberg, H., Chabanova, E., Dale, M., Masi, F. D., Thomas, C. E., Allin, K. H., Hansen, T. H., Heggie, A., Hong, M.-G., Elders, P. J. M., Kennedy, G., Kokkola, T., Pedersen, H. K., Mahajan, A., McEvoy, D., Pattou, F., Raverdy, V., Häussler, R. S., Sharma, S., Thomsen, H. S., Vangipurapu, J., Vestergaard, H., ‘t Hart, L. M., Adamski, J., Musholt, P. B., Brage, S., Brunak, S., Dermitzakis, E., Frost, G., Hansen, T., Laakso, M., Pedersen, O., Ridderstråle, M., Ruetten, H., Hattersley, A. T., Walker, M., Beulens, J. W. J., Mari, A., Schwenk, J. M., Gupta, R., McCarthy, M. I., Pearson, E. R., Bell, J. D., Pavo, I., & Franks, P. W.
- Affiliations
- Lund University (SE)
- University of Geneva (CH)
- Sanofi (Germany) (DE)
- Helmholtz Munich (DE)
- University of Exeter (GB)
- University of Westminster (GB)
- University of Dundee (GB)
- Amsterdam Public Health (NL)
- Helsinki University Hospital (FI)
- Herlev Hospital (DK)
- Science for Life Laboratory (SE)
- Technical University of Denmark (DK)
- University of Copenhagen (DK)
- Newcastle University (GB)
- University of Eastern Finland (FI)
- Centre for Human Genetics (GB)
- Inserm (FR)
- National University of Singapore (SG)
- Sanofi (France) (FR)
- Imperial College London (GB)
- Novo Nordisk (Denmark) (DK)
- University Medical Center Utrecht (NL)
- National Academies of Sciences, Engineering, and Medicine (US)
- Eli Lilly (United States) (US)
- Harvard University (US)
- Corresponding author
- Ohlsson, Mattias
- Viñuela, Ana
- Frau, Francesca
- 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
- Raverdy, Violeta
- Häussler, Ragna S.
- Sharma, Sapna
- Thomsen, Henrik S.
- Vangipurapu, Jagadish
- Vestergaard, Henrik
- Adamski, Jerzy
- Musholt, Petra B.
- Brunak, Søren
- Dermitzakis, Emmanouil
- Frost, Gary
- Hansen, Torben
- Laakso, Markku
- Pedersen, Oluf
- Ridderstråle, Martin
- Ruetten, Hartmut
- Hattersley, Andrew T.
- Walker, Mark
- Beulens, Joline W. J.
- Mari, Andrea
- Schwenk, Jochen M.
- Gupta, Ramneek
- McCarthy, Mark I.
- Pearson, Ewan R.
- Bell, Jimmy D.
- Pavo, Imre
- Franks, Paul W.
- ORCID
- 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
- Raverdy, Violeta
- Häussler, Ragna S.
- Sharma, Sapna
- Thomsen, Henrik S.
- Vangipurapu, Jagadish
- Vestergaard, Henrik
- ‘t Hart, Leen M.
- Adamski, Jerzy
- Musholt, Petra B.
- Brage, Soren
- Brunak, Søren
- Dermitzakis, Emmanouil
- Frost, Gary
- Hansen, Torben
- Laakso, Markku
- Pedersen, Oluf
- Ridderstråle, Martin
- Hattersley, Andrew T.
- Walker, Mark
- Beulens, Joline W. J.
- Mari, Andrea
- Schwenk, Jochen M.
- Gupta, Ramneek
- McCarthy, Mark I.
- Pearson, Ewan R.
- Bell, Jimmy D.
- Pavo, Imre
- Franks, Paul W.
- Venue
- PLOS Medicine
- Publisher
- Public Library of Science (PLoS)
- Published
- 2020-06-19
- Volume
- 17
- Issue
- 6
- Pages
- e1003149
- ISSN
- 1549-1277 (ISSN-L)
- 1549-1676
- PMC
- PMC7304567
- OpenAlex
- W3035784389
- Cited by
- 97
- References
- 60
- Citations by year
- 2026: 13 · 2025: 17 · 2024: 19 · 2023: 10 · 2022: 16 · 2021: 20 · 2020: 2
- FWCI
- 8.95
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- public-domain
- creativecommons.org/publicdomain/zero/1.0/ (vor)
- Locations
- PLoS Medicine (publishedVersion, public-domain)
- medRxiv (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, public-domain)
- PubMed (publishedVersion)
- Discovery Research Portal (University of Dundee) (publishedVersion, public-domain)
- Pure Amsterdam UMC (publishedVersion, cc-by)
- Research at the University of Copenhagen (University of Copenhagen) (publishedVersion, cc-by)
- WestminsterResearch (University of Westminster) (acceptedVersion, public-domain)
- HAL (submittedVersion, public-domain)
- Leiden Repository (Leiden University) (submittedVersion, other-oa)
- Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU) (submittedVersion, other-oa)
- Apollo (University of Cambridge) (submittedVersion, public-domain)
- National University of Singapore (submittedVersion, public-domain)
- Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Työväentutkimus Vuosikirja (submittedVersion)
- CNR ExploRA (submittedVersion, other-oa)
- LillOA (Université de Lille (University Of Lille)) (submittedVersion, public-domain)
- Lund University Publications (Lund University) (submittedVersion)
- Amsterdam UMC (VU Amsterdam) - Institutional Repository (submittedVersion, other-oa)
- PuSH - Publication Server of Helmholtz Zentrum München (submittedVersion, cc-by)
- Royal Devon and Exeter Research Repository (Royal Devon and Exeter) (submittedVersion, public-domain)
- Leiden Repository (Leiden University) (submittedVersion, public-domain)
- University of Southern Denmark Research Portal (University of Southern Denmark) (submittedVersion, public-domain)
- Spiral (Imperial College London) (submittedVersion, other-oa)
- Apollo (University of Cambridge) (submittedVersion)
- Apollo
- Apollo (public-domain)
- Funders
- Innovative Medicines Initiative (115317 (DIRECT))
- Henning och Johan Throne-Holsts
- Hans Werthén
- Swedish Foundation for Strategic Research
- European Research Council (ERC-2015-CoG - 681742_NASCENT)
- Novo Nordisk Foundation (NNF18OC0031650, NNF17OC0027594, NNF14CC0001)
- NIHR clinical senior lecturer fellowship
- Wellcome Trust Senior Investigator
- NIHR Exeter Clinical Research Facility
- Science for Life Laboratory
- Knut and Alice Wallenberg Foundation
- Erling-Persson Foundation
- Wellcome (090532, 098381, 106130, 203141, 212259)
- NIH (U01-DK105535)
- Topics
- Health Sciences › Medicine › Hepatology › Liver Disease Diagnosis and Treatment
- Health Sciences › Medicine › Pathology and Forensic Medicine › Alcohol Consumption and Health Effects
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- non-alcoholic fatty liver disease, type 2 diabetes, liver fat, multi-omics, genetic biomarkers, transcriptomics, proteomics, metabolomics, LASSO feature selection, random forest, non-invasive diagnosis, beta-cell function, insulin sensitivity
- MeSH terms
- Machine Learning, Fatty Liver, Female, Humans, Male, Middle Aged, Prospective Studies, Reproducibility of Results, Models, Statistical, Risk Assessment, Diabetes Complications
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.