Liver Fat Fraction and Machine Learning Improve Steatohepatitis Diagnosis in Liver Transplant Patients

. 2025 Jul ; 38 (7) : e70077.

Jazyk angličtina Země Velká Británie, Anglie Médium print

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/pmid40491220

Grantová podpora
00023001 Ministry of Health, Czech Republic
LX22NPO5104 Ministry of Education, Youth and Sports, Czech Republic, Next Generation EU, programme EXCELES

This study investigates the diagnostic accuracy of liver fat fraction (FF) and other biomarkers in differentiating metabolic dysfunction‐associated steatohepatitis (MASH) from non‐MASH conditions in a cohort of 127 liver transplant patients using 1H MRS and machine learning techniques. Receiver operating characteristic analysis identified FF as the most significant predictor, achieving an area under the curve (AUC) > 0.96 for distinguishing MASH from non‐steatosis and non‐MASH metabolic dysfunction‐associated steatotic liver disease (MASLD). Secondary biomarkers, including insulinemia and elastography, showed moderate discriminatory power (AUC = 0.7–0.8) and contributed to refining classification decisions within a decision tree model. The decision tree analysis, validated with 10‐fold cross‐validation and independent testing, demonstrated robust sensitivity and specificity, with FF contributing 60%–70% to decision‐making. Secondary splits, such as insulinemia (~16.21 μIU/mL) and elastography (~8 kPa), provided additional discriminatory power, particularly in cases with borderline FF values. Non‐significant biomarkers, such as waist circumference and signals of diallylic protons resonating at 2.8 ppm, were excluded due to low discriminatory performance (AUC < 0.7). Compared to the general population (~5.8% prevalence), MASH was significantly more common in liver transplant recipients (~30%–50%). In patients with FF > 5.3%, the positive predictive value (PPV) for MASH ranged from 88% to 97%, more than twice the PPV observed in the general population (approximately 60%). These findings align with existing literature validating MRI‐derived proton density fat fraction as a reliable biomarker for hepatic steatosis. However, liver fat percentage alone is insufficient for MASH diagnosis. Secondary biomarkers, particularly insulinemia and elastography, enhanced classification accuracy near the FF threshold of 5.3%. This multiparametric approach significantly improves diagnostic accuracy and addresses the elevated risk and unique clinical needs of liver transplant recipients. Overall, these results underscore the clinical utility and precision of MR spectroscopy as a noninvasive biomarker for MASH diagnosis in liver transplant patients.

Machine learning identifies liver fat fraction (FF) measured by 1H MR spectroscopy, insulinemia, and elastography as robust, non-invasive biomarkers for diagnosing steatohepatitis in liver transplant patients, validated through decision tree analysis. Compared to the general population (~5.8% prevalence), MASH is significantly more common in liver transplant recipients (~30%-50%). In patients with FF > 5.3%, the positive predictive value for MASH ranged up to 97%, more than twice the value observed in the general population.

Zobrazit více v PubMed

Tacke F., Horn P., Wai‐Sun Wong V., et al., “EASL‐EASD‐EASO Clinical Practice Guidelines on the Management of Metabolic Dysfunction‐Associated Steatotic Liver Disease (MASLD),” Journal of Hepatology 81, no. 3 (2024): 492–542, 10.1016/j.jhep.2024.04.031. PubMed DOI

Le P., Tatar M., Dasarathy S., et al., “Estimated Burden of Metabolic Dysfunction‐Associated Steatotic Liver Disease in US Adults, 2020 to 2050,” JAMA Network Open 8, no. 1 (2025): e2454707, 10.1001/jamanetworkopen.2024.54707. PubMed DOI PMC

Saeed N., Glass L., Sharma P., Shannon C., Sonnenday C. J., and Tincopa M. A., “Incidence and Risks for Nonalcoholic Fatty Liver Disease and Steatohepatitis Post‐Liver Transplant: Systematic Review and Meta‐Analysis,” Transplantation 103, no. 11 (2019): e345–e354, 10.1097/TP.0000000000002916. PubMed DOI

Kleiner D. E., Brunt E. M., Van Natta M., et al., “Nonalcoholic Steatohepatitis Clinical Research Network. Design and Validation of a Histological Scoring System for Nonalcoholic Fatty Liver Disease,” Hepatology 41, no. 6 (2005): 1313–1321, 10.1002/hep. PubMed DOI

Gu J., Liu S., Du S., et al., “Diagnostic Value of MRI‐PDFF for Hepatic Steatosis in Patients With Non‐Alcoholic Fatty Liver Disease: A Meta‐Analysis,” European Radiology 29, no. 7 (2019): 3564–3573, 10.1007/s00330-019-06072-4. PubMed DOI

Stine J. G., Munaganuru N., Barnard A., et al., “Change in MRI‐PDFF and Histologic Response in Patients With Nonalcoholic Steatohepatitis: A Systematic Review and Meta‐Analysis,” Clinical Gastroenterology and Hepatology 19, no. 11 (2021): 2274–2283.e5, 10.1016/j.cgh.2020.08.061. PubMed DOI PMC

Tang A., Tan J., Sun M., et al., “Nonalcoholic Fatty Liver Disease: MR Imaging of Liver Proton Density Fat Fraction to Assess Hepatic Steatosis,” Radiology 267, no. 2 (2013): 422–431, 10.1148/radiol.12120896. PubMed DOI PMC

Ferraioli G., Berzigotti A., Barr R. G., et al., “Quantification of Liver Fat Content With Ultrasound: A WFUMB Position Paper,” Ultrasound in Medicine & Biology 47, no. 10 (2021): 2803–2820, 10.1016/j.ultrasmedbio.2021.06.002. PubMed DOI

Szczepaniak L. S., Nurenberg P., Leonard D., et al., “Magnetic Resonance Spectroscopy to Measure Hepatic Triglyceride Content: Prevalence of Hepatic Steatosis in the General Population,” American Journal of Physiology. Endocrinology and Metabolism 288, no. 2 (2005): E462–E468, 10.1152/ajpendo.00064.2004. PubMed DOI

Longo R., Pollesello P., Ricci C., et al., “Proton MR Spectroscopy in Quantitative In Vivo Determination of Fat Content in Human Liver Steatosis,” Journal of Magnetic Resonance Imaging 5, no. 3 (1995): 281–285, 10.1002/jmri.1880050311. PubMed DOI

Hamilton G., Yokoo T., Bydder M., et al., “In Vivo Characterization of the Liver Fat (1)H MR Spectrum,” NMR in Biomedicine 24, no. 7 (2011): 784–790, 10.1002/nbm.1622. PubMed DOI PMC

Hajek M., Dezortova M., Wagnerova D., et al., “MR Spectroscopy as a Tool for In Vivo Determination of Steatosis in Liver Transplant Recipients,” Magnetic Resonance Materials in Physics 24, no. 5 (2011): 297–304, 10.1007/s10334-011-0264-9. PubMed DOI

Liu C.‐Y., McKenzie C. A., Yu H., Brittain J. H., and Reeder S. B., “Fat Quantification With IDEAL Gradient Echo Imaging: Correction of Bias From T(1) and Noise,” Magnetic Resonance in Medicine 58, no. 2 (2007): 354–364, 10.1002/mrm.21301. PubMed DOI

Azizi N., Naghibi H., Shakiba M., et al., “Evaluation of MRI Proton Density Fat Fraction in Hepatic Steatosis: A Systematic Review and Meta‐Analysis,” European Radiology 35, no. 4 (2024): 1794–1807, 10.1007/s00330-024-11001-1. PubMed DOI

Middleton M. S., Heba E. R., Hooker C. A., et al., “Agreement Between Magnetic Resonance Imaging Proton Density Fat Fraction Measurements and Pathologist‐Assigned Steatosis Grades of Liver Biopsies From Adults With Nonalcoholic Steatohepatitis,” Gastroenterology 153, no. 3 (2017): 753–761, 10.1053/j.gastro.2017.06.005. PubMed DOI PMC

Bawden S. J., Hoad C., Kaye P., et al., “Comparing Magnetic Resonance Liver Fat Fraction Measurements With Histology in Fibrosis: The Difference Between Proton Density Fat Fraction and Tissue Mass Fat Fraction,” Magnetic Resonance Materials in Physics, Biology and Medicine 36, no. 4 (2023): 553–563, 10.1007/s10334-022-01052-0. PubMed DOI PMC

Vilar‐Gomez E. and Chalasani N., “Non‐Invasive Assessment of Non‐Alcoholic Fatty Liver Disease: Clinical Prediction Rules and Blood‐Based Biomarkers,” Journal of Hepatology 68 (2018): 305–315, 10.1016/j.jhep.2017.11.013. PubMed DOI

Banerjee R., Pavlides M., Tunnicliffe E. M., et al., “Multiparametric Magnetic Resonance for the Non‐Invasive Diagnosis of Liver Disease,” Journal of Hepatology 60, no. 1 (2014): 69–77, 10.1016/j.jhep.2013.09.002. PubMed DOI PMC

Okanoue T., Shima T., Mitsumoto Y., et al., “Artificial Intelligence/Neural Network System for the Screening of Nonalcoholic Fatty Liver Disease and Nonalcoholic Steatohepatitis,” Hepatology Research 51, no. 5 (2021): 554–569, 10.1111/hepr.13628. PubMed DOI

Erickson M. L., Haus J. M., Malin S. K., Flask C. A., McCullough A. J., and Kirwan J. P., “Non‐Invasive Assessment of Hepatic Lipid Subspecies Matched With Non‐Alcoholic Fatty Liver Disease Phenotype,” Nutrition, Metabolism, and Cardiovascular Diseases 29, no. 11 (2019): 1197–1204, 10.1016/j.numecd.2019.06.012. PubMed DOI PMC

Chang D., Truong E., Mena E. A., et al., “Machine Learning Models Are Superior to Noninvasive Tests in Identifying Clinically Significant Stages of NAFLD and NAFLD‐Related Cirrhosis,” Hepatology 77, no. 2 (2023): 546–557, 10.1002/hep.32655. PubMed DOI

McTeer M., Applegate D., Mesenbrink P., et al., “Machine Learning Approaches to Enhance Diagnosis and Staging of Patients With MASLD Using Routinely Available Clinical Information,” PLoS ONE 19, no. 2 (2024): e0299487, 10.1371/journal.pone.0299487. PubMed DOI PMC

Dinani A. M., Kowdley K. V., and Noureddin M., “Application of Artificial Intelligence for Diagnosis and Risk Stratification in NAFLD and NASH: The State of the Art,” Hepatology 74, no. 4 (2021): 2233–2240, 10.1002/hep.31869. PubMed DOI

Burian M., Hajek M., Sedivy P., Mikova I., Trunecka P., and Dezortova M., “Lipid Profile and Hepatic Fat Content Measured by 1H MR Spectroscopy in Patients Before and After Liver Transplantation,” Metabolites 11, no. 9 (2021): 625, 10.3390/metabo11090625. PubMed DOI PMC

“LCModel Home Web Site,” accessed February 2, 2025, http://s‐provencher.com/lcmodel.shtml.

Šedivý P., Dezortová M., Burian M., Dusilová T., Kovář J., and Hájek M., “Comparison of Accuracy of Magnetic Resonance Spectroscopic and Imaging Techniques for the Liver Steatosis Assessment,” Chemicke Listy 115 (2021): 46–53.

Panagiotopoulos N., Batakis D., Wolfson T., et al., “PDFF Predicts NASH in Obese Patients Without Known Liver Disease,” Proceedings of the International Society for Magnetic Resonance in Medicine 30 (2022): 2396, 10.58530/2022/2396. DOI

Patel J., Bettencourt R., Cui J., et al., “Association of Noninvasive Quantitative Decline in Liver Fat Content on MRI With Histologic Response in Nonalcoholic Steatohepatitis,” Therapeutic Advances in Gastroenterology 9, no. 5 (2016): 692–701, 10.1177/1756283X16656735. PubMed DOI PMC

Le T. A., Chen J., Changchien C., et al., “Effect of Colesevelam on Liver Fat Quantified by Magnetic Resonance in Nonalcoholic Steatohepatitis: A Randomized Controlled Trial,” Hepatology 56, no. 3 (2012): 922–932, 10.1002/hep.25731. PubMed DOI PMC

Caussy C., Reeder S. B., Sirlin C. B., and Loomba R., “Noninvasive, Quantitative Assessment of Liver Fat by MRI‐PDFF as an Endpoint in NASH Trials,” Hepatology 68, no. 2 (2018): 763–772, 10.1002/hep.29797. PubMed DOI PMC

Chalasani N., Younossi Z., Lavine J. E., et al., “The Diagnosis and Management of Nonalcoholic Fatty Liver Disease: Practice Guidance From the American Association for the Study of Liver Diseases,” Hepatology 67, no. 1 (2018): 328–357, 10.1002/hep.29367. PubMed DOI

Yin Z., Murphy M. C., Li J., et al., “Prediction of Nonalcoholic Fatty Liver Disease (NAFLD) Activity Score (NAS) With Multiparametric Hepatic Magnetic Resonance Imaging and Elastography,” European Radiology 29, no. 11 (2019): 5823–5831, 10.1007/s00330-019-06076-0. PubMed DOI PMC

Noureddin M., Truong E., Gornbein J. A., et al., “MRI‐Based (MAST) Score Accurately Identifies Patients With NASH and Significant Fibrosis,” Journal of Hepatology 76, no. 4 (2022): 781–787, 10.1016/j.jhep.2021.11.012. PubMed DOI

Troelstra M. A., Witjes J. J., van Dijk A. M., et al., “Assessment of Imaging Modalities Against Liver Biopsy in Nonalcoholic Fatty Liver Disease: The Amsterdam NAFLD‐NASH Cohort,” Journal of Magnetic Resonance Imaging 54, no. 6 (2021): 1937–1949, 10.1002/jmri.27703. PubMed DOI PMC

McHenry S., Park Y., Browning J. D., Sayuk G., and Davidson N. O., “Dallas Steatosis Index Identifies Patients With Nonalcoholic Fatty Liver Disease,” Clinical Gastroenterology and Hepatology 18, no. 9 (2020): 2073–2080.e7, 10.1016/j.cgh.2020.01.020. PubMed DOI PMC

Fialoke S., Malarstig A., Miller M. R., and Dumitriu A., “Application of Machine Learning Methods to Predict Non‐Alcoholic Steatohepatitis (NASH) in Non‐Alcoholic Fatty Liver (NAFL) Patients,” American Medical Informatics Association Annual Symposium Proceedings 2018 (2018): 430–439. PubMed PMC

Najít záznam

Citační ukazatele

Nahrávání dat ...

Možnosti archivace

Nahrávání dat ...