본문 바로가기
KERD
논문KCI 등재

Liver Fibrosis Biomarker Validation Using Machine Learning Algorithms

권현주|박창훈|권민정|박효순|우희연|신강수|김민경
대한진단검사의학회 (Korean Society For Laboratory Medicine)|2023.07|Laboratory Medicine Online|제13권 제3호|pp. 189-198|DOI 10.47429/lmo.2023.13.3.189

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

Machine learningRandom forestSupport vector machineLiver fibrosisM2BPGiStiffness measurements

초록

Background: Liver fibrosis which causes several liver diseases, requires early screening and management. The gold standard for fibrosis assessment, liver biopsy, has recently been replaced by noninvasive scores. In this study, we validated liver fibrosis-associated biomarkers using machine learning techniques applied in medical research and evaluated their prediction models. Methods: Noninvasive scores were assayed in 144 patients who underwent transient elastography (TE). The patients were divided into three groups (<7 kPa, 7–10 kPa, ≥10 kPa) according to their TE results. Feature selection and modeling for predicting liver fibrosis were performed using random forest (RF) and support vector machine (SVM). Results: Considering the mean decrease in impurity, permutation importance, and multicollinear analysis, the important features for differentiating between the three groups were Mac-2 binding protein glycosylation isomer (M2BPGi), platelet count, and aspartate aminotransferase (AST). Using these features, the RF and SVM models showed equivalent or better performance than noninvasive scores. The sensitivities of RF and SVM models for predicting ≥7 kPa TE results were higher than noninvasive scores (83.3% and 90.0% vs. <80%, respectively). The sensitivity and specificity of RF and SVM models for ≥10 kPa TE result was 100%. Conclusions: We used machine learning techniques to verify the usefulness of established serological biomarkers (M2BPGi, PLT, and AST) that predict liver fibrosis. Conclusively, machine learning models showed better performance than noninvasive scores.

Abstract

Background: Liver fibrosis which causes several liver diseases, requires early screening and management. The gold standard for fibrosis assessment, liver biopsy, has recently been replaced by noninvasive scores. In this study, we validated liver fibrosis-associated biomarkers using machine learning techniques applied in medical research and evaluated their prediction models. Methods: Noninvasive scores were assayed in 144 patients who underwent transient elastography (TE). The patients were divided into three groups (<7 kPa, 7–10 kPa, ≥10 kPa) according to their TE results. Feature selection and modeling for predicting liver fibrosis were performed using random forest (RF) and support vector machine (SVM). Results: Considering the mean decrease in impurity, permutation importance, and multicollinear analysis, the important features for differentiating between the three groups were Mac-2 binding protein glycosylation isomer (M2BPGi), platelet count, and aspartate aminotransferase (AST). Using these features, the RF and SVM models showed equivalent or better performance than noninvasive scores. The sensitivities of RF and SVM models for predicting ≥7 kPa TE results were higher than noninvasive scores (83.3% and 90.0% vs. <80%, respectively). The sensitivity and specificity of RF and SVM models for ≥10 kPa TE result was 100%. Conclusions: We used machine learning techniques to verify the usefulness of established serological biomarkers (M2BPGi, PLT, and AST) that predict liver fibrosis. Conclusively, machine learning models showed better performance than noninvasive scores.

참고문헌 (47)

  1. Campana L, "Liver regeneration and infiammation : from fundamental science to clinical applications", Nat Rev Mol Cell Biol, 22, pp.608~624 (2021)
  2. Rockey DC, "Fibrosis — a common pathway to organ injury and failure", N Engl J Med, 372, pp.1138~1149 (2015)
  3. Pellicoro A, "Liver fibrosis and repair : immune regulation of wound healing in a solid organ", Nat Rev Immunol, 14, pp.181~194 (2014)
  4. Kim BK, "Clinical application of liver stiffness measurement using transient elastography in chronic liver disease from longitudinal perspectives", World J Gastroenterol, 19, pp.1890~1900 (2013)
  5. Khalifa A, "The utility of liver biopsy in 2020", Curr Opin Gastroenterol, 36, pp.184~191 (2020)
  6. Fallatah HI, "Fibroscan compared to FIB-4, APRI, and AST", ALT ratio for assessment of liver fibrosis in Saudi patients with nonalcoholic fatty liver disease, 2016, pp.16, e38346~
  7. Amernia B, "FIB-4, APRI, and AST", ALT ratio compared to FibroScan for the assessment of hepatic fibrosis in patients with non-alcoholic fatty liver disease in Bandar Abbas, Iran, 2021, pp.21, 453~
  8. 문희원, "Usefulness of Enhanced Liver Fibrosis, Glycosylation Isomer of Mac-2 Binding Protein, Galectin-3, and Soluble Suppression of Tumorigenicity 2 for Assessing Liver Fibrosis in Chronic Liver Diseases", Annals of Laboratory Medicine, 38(4), pp.331~337 (2018), 대한진단검사의학회
  9. Shirabe K, "Mac-2 binding protein glycan isomer(M2BPGi)is a new serum biomarker for assessing liver fibrosis : more than a biomarker of liver fibrosis", J Gastroenterol, 53, pp.819~826 (2018)
  10. Saleh SA, "M2BPGi for assessing liver fibrosis in patients with hepatitis C treated with direct-acting antivirals", World J Gastroenterol, 26, pp.2864~2876 (2020)
  11. Mak LY, "Role of serum M2BPGi levels in predicting persistence of advanced fibrosis in chronic hepatitis B virus infection", Dig Dis Sci, 67, pp.5127~5136 (2022)
  12. Choi R, "Evaluation of the serum Mac-2 binding protein glycosylation isomer test used for diagnosis and monitoring of liver fibrosis and the correlation of Mac-2 binding protein glycosylation isomer with hemoglobin A1c", Clin Lab, 65, pp.197~201 (2019)
  13. Tsochatzis EA, "Elastography for the diagnosis of severity of fibrosis in chronic liver disease : a meta-analysis of diagnostic accuracy", J Hepatol, 54, pp.650~659 (2011)
  14. Mikolasevic I, "Transient elastography(FibroScan®)with controlled attenuation parameter in the assessment of liver steatosis and fibrosis in patients with nonalcoholic fatty liver disease-Where do we stand?", World J Gastroenterol, 22, pp.7236~7251 (2016)
  15. Festi D, "Review article : the diagnosis of non-alcoholic fatty liver disease – availability and accuracy of non-invasive methods", Aliment Pharmacol Ther, 37, pp.392~400 (2013)
  16. Oeda S, "Diagnostic accuracy of FibroScan and factors affecting measurements", Diagnostics(Basel), 10, pp.940~ (2020)
  17. Haq AU, "Detection of breast cancer through clinical data using supervised and unsupervised feature selection techniques", IEEE Access, 9, pp.22090~22105 (2021)
  18. Ahmad S, "Deep learning enabled disease diagnosis for secure internet of medical things", Computers, Materials & Continua, 73, pp.965~979 (2022)
  19. Poonguzhali R, "Automated brain tumor diagnosis using deep residual U-Net segmentation model", Computers, Materials & Continua, 74, pp.2179~2194 (2023)
  20. Decharatanachart P, "Application of artificial intelligence in chronic liver diseases : a systematic review and meta-analysis", BMC Gastroenterol, 21, pp.10~ (2021)
  21. Spann A, "Applying machine learning in liver disease and transplantation : a comprehensive review", Hepatology, 71, pp.1093~1105 (2020)
  22. Deo RC, "Machine learning in medicine", Circulation, 132, pp.1920~1930 (2015)
  23. Feng G, "Novel urinary protein panels for the non-invasive diagnosis of non-alcoholic fatty liver disease and fibrosis stages", Liver Int, 43, pp.1234~1236 (2023)
  24. Alkhouri N, "Putting it all together : noninvasive diagnosis of fibrosis in nonalcoholic fatty liver disease in adults and children", Clin Liver Dis(Hoboken), 9, pp.134~137 (2017)
  25. Wei B, "M2BPGi as a potential diagnostic tool of cirrhosis in Chinese patients with hepatitis B virus infection", J Clin Lab Anal, 32, pp.e22261~ (2018)
  26. Dong Wook Jekarl, "Diagnosis of Liver Fibrosis With Wisteria floribunda Agglutinin-Positive Mac-2 Binding Protein (WFAM2BP) Among Chronic Hepatitis B Patients", Annals of Laboratory Medicine, 38(4), pp.348~354 (2018), 대한진단검사의학회
  27. Cross TJ, "Prospective comparison of Fibroscan, King’s score and liver biopsy for the assessment of cirrhosis in chronic hepatitis C infection", J Viral Hepat, 17, pp.546~554 (2010)
  28. Wong VW, "Diagnosis of fibrosis and cirrhosis using liver stiffness measurement in nonalcoholic fatty liver disease", Hepatology, 51, pp.454~462 (2010)
  29. Breiman L, (2017), Routledge
  30. Altmann A, "Permutation importance : a corrected feature importance measure", Bioinformatics, 26, pp.1340~1347 (2010)
  31. Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)
  32. Burger CJ, "A tutorial on support vector machines for pattern recognition", Data mining and knowledge discovery, 2, pp.121~167 (1998)
  33. Hunter JD, "Matplotlib : a 2D graphics environment", Computing in science & engineering, 9, pp.90~95 (2007)
  34. Pedregosa F, "Scikit-learn : Machine learning in Python", J Mach Learn Res, 12, pp.2825~2830 (2011)
  35. Nishikawa H, "Impact of serum Wisteria floribunda agglutinin positive Mac-2-binding protein and serum interferon-gamma-inducible protein-10 in primary biliary cirrhosis", Hepatol Res, 46, pp.575~583 (2016)
  36. Umemura T, "Serum Wisteria floribunda agglutinin-positive Mac-2-binding protein level predicts liver fibrosis and prognosis in primary biliary cirrhosis", Am J Gastroenterol, 110, pp.857~864 (2015)
  37. Yamada N, "Serum Mac-2 binding protein glycosylation isomer predicts grade F4 liver fibrosis in patients with biliary atresia", J Gastroenterol, 52, pp.245~252 (2017)
  38. Nishikawa H, "Clinical significance of serum Wisteria floribunda agglutinin positive Mac-2-binding protein level and high-sensitivity C-reactive protein concentration in autoimmune hepatitis", Hepatol Res, 46, pp.613~621 (2016)
  39. Abe M, "Association between Wisteria fioribunda agglutinin-positive Mac-2 binding protein and the fibrosis stage of non-alcoholic fatty liver disease", J Gastroenterol, 50, pp.776~784 (2015)
  40. Mizuno M, "Classification of patients with non-alcoholic fatty liver disease using rapid immunoassay of serum type IV collagen compared with liver histology and other fibrosis markers", Hepatol Res, 47, pp.216~225 (2017)
  41. Nishikawa H, "Clinical significance of serum Wisteria fioribunda agglutinin positive Mac-2-binding protein level in non-alcoholic steatohepatitis", Hepatol Res, 46, pp.1194~1202 (2016)
  42. Shigefuku R, "Correlations of hepatic hemodynamics, liver function, and fibrosis markers in nonalcoholic fatty liver disease : Comparison with chronic hepatitis related to hepatitis C virus", Int J Mol Sci, 17, pp.1545~ (2016)
  43. Fujiyoshi M, "Clinicopathological characteristics and diagnostic performance of Wisteria fioribunda agglutinin positive Mac-2-binding protein as a preoperative serum marker of liver fibrosis in hepatocellular carcinoma", J Gastroenterol, 50, pp.1134~1144 (2015)
  44. Toshima T, "A novel serum marker, glycosylated Wisteria fioribunda agglutinin-positive Mac-2 binding protein(WFA(+)-M2BP), for assessing liver fibrosis", J Gastroenterol, 50, pp.76~84 (2015)
  45. Vapnik VN, "An overview of statistical learning theory", IEEE Trans Neural Netw, 10, pp.988~999 (1999)
  46. LeCun Y, "Deep learning", Nature, 521, pp.436~444 (2015)
  47. Singh S, "Liver stiffness is associated with risk of decompensation, liver cancer, and death in patients with chronic liver diseases : a systematic review and meta-analysis", Clin Gastroenterol Hepatol, 11, pp.1573~1584 (2013)

이 간행물의 다른 논문 (13건)

내분비교란물질이 사람의 건강에 미치는 영향조성은, 이준형, 대한임상화학회 임상질량분석연구위원회pp. 129-140선천성 이상의 염색체마이크로어레이 검사 지침(I): 일반 및 산전검사 지침원동주, 김인숙, 설창안, 하정숙pp. 141-153선천성 이상의 염색체마이크로어레이 검사 지침(II): 보고 및 해석 지침하정숙, 김인숙, 원동주, 설창안pp. 154-164카우덴 증후군정예령, 정소연, 장윤정, 이시연, 전지영, 이동옥, 공선영, 유금혜pp. 165-171Concordance of Current Tests Used for the Diagnosis of Bone Marrow Involvement in B-Lineage Lymphoma with Respect to Various Lymphoma Grade박상혁, 문슬기, 김혜림, 김인숙pp. 172-181
원문 보기