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; Fernández, Juan Carlos Delgado; Dawed, Adem Y; Giordano, G; Forgie, Ian; McDonald, Timothy J.; Rutters, Femke; Cederberg, Henna; Chabanova, Elizaveta; Dale, Matilda; Masi, Federico De; Thomas, Cecilia Engel; Allin, Kristine H.; Hansen, Torben; Heggie, Alison; Hong, Mun Gwan; Elders, Petra; Kennedy, Gwen; Kokkola, Tarja; Pedersen, Helle; Mahajan, Anubha; McEvoy, Donna; Pattou, François; Raverdy, Violeta; Häussler, Ragna S.; Sharma, Sapna; Thomsen, Henrik S.; Vangipurapu, Jagadish; Vestergaard, Henrik; Hart, Leen M. ‘t; Adamski, Jerzy; Musholt, Petra B.; Brage, Sören; Brunak, Søren; Dermitzakis, Emmanouil T.; Frost, Gary; 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; Pearson, Ewan R.; Bell, Jimmy D.; Pávó, Imre; Franks, Paul W.

doi:10.1371/journal.pmed.1003149

Cited by 52 publications

(49 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NAFLD is an important risk factor for liver disease as well as CVD [36] , yet often goes undetected in the clinical routine due to the limited sensitivity of current liver function tests [37] , and therefore improved biomarkers are needed. Our observation that NAFLD is a strong driver of plasma protein patterns is in line with two recent studies suggesting that protein profiling could potentially serve as a biomarker for NAFLD-screening [ 7 , 38 ].…”

Section: Discussionsupporting

confidence: 91%

Longitudinal plasma protein profiling of newly diagnosed type 2 diabetes

et al. 2021

View full text Add to dashboard Cite

Background Comprehensive proteomics profiling may offer new insights into the dysregulated metabolic milieu of type 2 diabetes, and in the future, serve as a useful tool for personalized medicine. This calls for a better understanding of circulating protein patterns at the early stage of type 2 diabetes as well as the dynamics of protein patterns during changes in metabolic status. Methods To elucidate the systemic alterations in early-stage diabetes and to investigate the effects on the proteome during metabolic improvement, we measured 974 circulating proteins in 52 newly diagnosed, treatment-naïve type 2 diabetes subjects at baseline and after 1 and 3 months of guideline-based diabetes treatment, while comparing their protein profiles to that of 94 subjects without diabetes. Findings Early stage type 2 diabetes was associated with distinct protein patterns, reflecting key metabolic syndrome features including insulin resistance, adiposity, hyperglycemia and liver steatosis. The protein profiles at baseline were attenuated during guideline-based diabetes treatment and several plasma proteins associated with metformin medication independently of metabolic variables, such as circulating EPCAM. Interpretation The results advance our knowledge about the biochemical manifestations of type 2 diabetes and suggest that comprehensive protein profiling may serve as a useful tool for metabolic phenotyping and for elucidating the biological effects of diabetes treatments. Funding This work was supported by the Swedish Heart and Lung Foundation, the Swedish Research Council, the Erling Persson Foundation, the Knut and Alice Wallenberg Foundation, and the Swedish state under the agreement between the Swedish government and the county councils (ALF-agreement).

show abstract

Section: Discussionsupporting

confidence: 91%

Longitudinal plasma protein profiling of newly diagnosed type 2 diabetes

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Using liver biopsy as the reference, FLI, HSI and NAFLD-LFS yielded AUROCs of 0.83 (0.72-0.91), 0.81 (0.71-0.88) and 0.80 (0.69-0.88), respectively, for steatosis detection (> 5% hepatocytes) [30]. More recently, machine learning models with different combinations of clinical and multi-omics (genetic, transcriptomic, proteomic and metabolomic) data have been proposed to identify individuals at high risk of NAFLD [31]. However, the use of these algorithms in clinical practice might not be feasible and need further validation.…”

Section: Discussionmentioning

confidence: 99%

Diagnostic value of serological biomarkers for detection of non‐alcoholic fatty liver disease (NAFLD) and/or advanced liver fibrosis in people living with HIV

et al. 2021

View full text Add to dashboard Cite

We aimed to evaluate the accuracy of serological biomarkers for non-alcoholic fatty liver disease (NAFLD) and advanced fibrosis (METAVIR-F3F4) in HIV mono-infected individuals. MethodsIn all, 674 participants from the PROSPEC-HIV study (NCT02542020), who had blood sample tests and transient elastography (TE) performed on the same day, were eligible. Exclusion criteria were viral hepatitis co-infection (n = 90), abusive alcohol intake (n = 61), missing data (n = 47) or unreliable TE (n = 39). NAFLD was defined by controlled attenuation parameter ≥ 248 dB/m and advanced fibrosis by liver stiffness measurement ≥ 8.7 kPa with M probe or ≥ 7.2 kPa with XL probe. Biomarkers for NAFLD [Steato-ELSA, Fatty Liver Index (FLI), Hepatic Steatosis Index (HSI), NAFLD-Liver Fat Score (NAFLD-LFS)] and fibrosis [Fibrosis-4 score (FIB-4), Aspartate-to-Platelet Ratio Index (APRI) and NAFLD Fibrosis Score (NFS)] were calculated. ResultsA total of 437 patients [57% female, age = 44 (interquartile range: 35-52) years, body mass index (BMI) = 26.1 (23.4-29.3) kg/m 2 , CD4 = 660 (427-901) cells/μL] were included. The prevalence [95% confidence interval (CI)] of NAFLD and advanced fibrosis were 38.2% (33.8-42.9) and 10.5% (8.0-13.8), respectively. The areas (95% CI) under the receiver operator curve (AUROCs) for diagnosis of NAFLD were 0.854 (0.818-0.889), 0.840 (0.804-0.877), 0.805 (0.762-0.847) and 0.793 (0.750-0.836) for Steato-ELSA, FLI, HSI and NAFLD-LFS (P < 0.001), respectively. All tests yielded satisfactory sensitivities, specificities and negative predictive values (NPVs). The AUROCs (95% CI) for diagnosis of advanced fibrosis were 0.736 (0.659-0.814), 0.700 (0.614-0.7851) and 0.795 (0.726-0.864) for FIB-4, APRI and NFS (P = 0.077), respectively. These tests yielded high specificities and negative predictive values (NPVs) > 90%. ConclusionBiomarkers for NAFLD had a good accuracy and those for fibrosis had high specificities and NPVs. These tests should be integrated to HIV care to detect NAFLD and to exclude advanced liver fibrosis.

show abstract

“…Many studies have been done to utilize machine learning for the prediction of fatty liver disease. Atabaki-Pasdar N et al (11) in a major modelling & validation study concluded that the highest AUC (of 0.84 for the respective study) is obtained by the combination of “-omics” data & clinical variables. Using MRI-derived proton density fat fraction for referencing, Han A et al (12) developed deep learning one-dimensional convolutional neural networks for NAFLD diagnosis by taking in ultrasound data.…”

Section: Discussionmentioning

confidence: 99%

Leveraging AutoML to provide NAFLD screening diagnosis: Proposed machine learning models

Bangash

2020

Preprint

View full text Add to dashboard Cite

NAFLD is reported to be the only hepatic ailment increasing in its prevalence concurrently with both; obesity & T2DM. In the wake of a massive strain on global health resources due to COVID 19 pandemic, NAFLD is bound to be neglected & shelved. Abdominal ultrasonography is done for NAFLD screening diagnosis which has a high monetary cost associated with it. We utilize MLjar, an autoML web platform, to propose machine learning models that require no cod-ing whatsoever & take in only easy-to-measure anthropometric measures for coming up with a screening diagnosis for NAFLD with considerably high AUC. Further studies are suggested to validate the generalization of the presented models.

show abstract

Predicting and elucidating the etiology of fatty liver disease: A machine learning modeling and validation study in the IMI DIRECT cohorts

Abstract: Peer Review History: PLOS recognizes the benefits of transparency in the peer review process; therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. The editorial history of this article is available here:

Cited by 52 publications

References 59 publications

Longitudinal plasma protein profiling of newly diagnosed type 2 diabetes

Longitudinal plasma protein profiling of newly diagnosed type 2 diabetes

Diagnostic value of serological biomarkers for detection of non‐alcoholic fatty liver disease (NAFLD) and/or advanced liver fibrosis in people living with HIV

Leveraging AutoML to provide NAFLD screening diagnosis: Proposed machine learning models

Contact Info

Product

Resources

About