본문 바로가기
KERD
논문KCI 등재

Nonalcoholic fatty liver disease and early prediction of gestational diabetes mellitus using machine learning methods

김경민|김원|Sue Shin|Seung Mi Lee|Suhyun Hwangbo|Errol R. Norwitz|Ja Nam Koo|Ig Hwan Oh|Eun Saem Choi|Young Mi Jung|Sun Min Kim|Byoung Jae Kim|Sang Youn Kim|Sae Kyung Joo|Chan-Wook Park|Taesung Park|Joong Shin Park
대한간학회 (The korean Association for the Study of the Liver)|2022.01|Clinical and Molecular Hepatology|제28권 제1호|pp. 105-116|DOI 10.3350/cmh.2021.0174

1

조회

0

다운로드

2

인용

0

참고문헌

키워드

Machine learningPregnancyDiabetesPredictionHigh-riskGestationalNonalcoholic fatty liver disease

초록

Background/Aims: To develop an early prediction model for gestational diabetes mellitus (GDM) using machine learning and to evaluate whether the inclusion of nonalcoholic fatty liver disease (NAFLD)-associated variables increases the performance of model. Methods: This prospective cohort study evaluated pregnant women for NAFLD using ultrasound at 10–14 weeks and screened them for GDM at 24–28 weeks of gestation. The clinical variables before 14 weeks were used to develop prediction models for GDM (setting 1, conventional risk factors; setting 2, addition of new risk factors in recent guidelines; setting 3, addition of routine clinical variables; setting 4, addition of NALFD-associated variables, including the presence of NAFLD and laboratory results; and setting 5, top 11 variables identified from a stepwise variable selection method). The predictive models were constructed using machine learning methods, including logistic regression, random forest, support vector machine, and deep neural networks. Results: Among 1,443 women, 86 (6.0%) were diagnosed with GDM. The highest performing prediction model among settings 1–4 was setting 4, which included both clinical and NAFLD-associated variables (area under the receiver operating characteristic curve [AUC] 0.563–0.697 in settings 1–3 vs. 0.740–0.781 in setting 4). Setting 5, with top 11 variables (which included NAFLD and hepatic steatosis index), showed similar predictive power to setting 4 (AUC 0.719– 0.819 in setting 5, P=not significant between settings 4 and 5). Conclusions: We developed an early prediction model for GDM using machine learning. The inclusion of NAFLDassociated variables significantly improved the performance of GDM prediction. (ClinicalTrials.gov Identifier: NCT02276144)

Abstract

Background/Aims: To develop an early prediction model for gestational diabetes mellitus (GDM) using machine learning and to evaluate whether the inclusion of nonalcoholic fatty liver disease (NAFLD)-associated variables increases the performance of model. Methods: This prospective cohort study evaluated pregnant women for NAFLD using ultrasound at 10–14 weeks and screened them for GDM at 24–28 weeks of gestation. The clinical variables before 14 weeks were used to develop prediction models for GDM (setting 1, conventional risk factors; setting 2, addition of new risk factors in recent guidelines; setting 3, addition of routine clinical variables; setting 4, addition of NALFD-associated variables, including the presence of NAFLD and laboratory results; and setting 5, top 11 variables identified from a stepwise variable selection method). The predictive models were constructed using machine learning methods, including logistic regression, random forest, support vector machine, and deep neural networks. Results: Among 1,443 women, 86 (6.0%) were diagnosed with GDM. The highest performing prediction model among settings 1–4 was setting 4, which included both clinical and NAFLD-associated variables (area under the receiver operating characteristic curve [AUC] 0.563–0.697 in settings 1–3 vs. 0.740–0.781 in setting 4). Setting 5, with top 11 variables (which included NAFLD and hepatic steatosis index), showed similar predictive power to setting 4 (AUC 0.719– 0.819 in setting 5, P=not significant between settings 4 and 5). Conclusions: We developed an early prediction model for GDM using machine learning. The inclusion of NAFLDassociated variables significantly improved the performance of GDM prediction. (ClinicalTrials.gov Identifier: NCT02276144)

참고문헌 (50)

  1. Hunt KJ, "The increasing prevalence of diabetes in pregnancy", Obstet Gynecol Clin North Am, 34, pp.173~199 (2007)[DOI]
  2. Metzger BE, "Summary and recommendations of the Fourth International Workshop-Conference on gestational diabetes mellitus. The Organizing Committee", Diabetes care, 21(2), pp.161~167 (1998)
  3. American Diabetes Association, "Standards of medical care in diabetes--2012", Diabetes Care, 35(1), pp.11~63 (2012)
  4. "ACOG Practice Bulletin No. 190: Gestational Diabetes Mellitus", Obstetrics & Gynecology, 131(2), pp.e49~e64 (2018), Ovid Technologies (Wolters Kluwer Health)[DOI]
  5. 홍수빈, "A Comparison of Predictive Performances between Old versus New Criteria in a Risk-Based Screening Strategy for Gestational Diabetes Mellitus", Diabetes and Metabolism Journal, 44(5), pp.726~736 (2020), 대한당뇨병학회[DOI]
  6. Hyun Chin Cho, "Prevalence and Factors Associated with Nonalcoholic Fatty Liver Disease in a Nonobese Korean Population", Gut and Liver, 10(1), pp.117~125 (2016), 거트앤리버 소화기연관학회협의회
  7. Choi SY, "The relation between non-alcoholic fatty liver disease and the risk of coronary heart disease in Koreans", Am J Gastroenterol, 104, pp.1953~1960 (2009)
  8. Vernon G, "Systematic review : the epidemiology and natural history of non-alcoholic fatty liver disease and non-alcoholic steatohepatitis in adults", Aliment Pharmacol Ther, 34, pp.274~285 (2011)
  9. Loomba R, "The global NAFLD epidemic", Nat Rev Gastroenterol Hepatol, 10, pp.686~690 (2013)
  10. Williams CD, "Prevalence of nonalcoholic fatty liver disease and nonalcoholic steatohepatitis among a largely middle-aged population utilizing ultrasound and liver biopsy : a prospective study", Gastroenterology, 140, pp.124~131 (2011)
  11. Younossi ZM, "Global epidemiology of nonalcoholic fatty liver disease-meta-analytic assessment of prevalence, incidence, and outcomes", Hepatology, 64, pp.73~84 (2016)
  12. Ramesh S, "Evaluation and management of non-alcoholic steatohepatitis", J Hepatol (2005)
  13. Targher G, "Prevalence of nonalcoholic fatty liver disease and its association with cardiovascular disease among type 2 diabetic patients", Diabetes Care, 30, pp.1212~1218 (2007)
  14. Marchesini G, "Nonalcoholic fatty liver disease : a feature of the metabolic syndrome", Diabetes, 50, pp.1844~1850 (2001)
  15. Hagström H, "Adverse outcomes of pregnancy in women with non-alcoholic fatty liver disease", Liver Int, 36, pp.268~274 (2016)
  16. Lee SM, "Non-alcoholic fatty liver disease in the first trimester and subsequent development of gestational diabetes mellitus", Diabetologia, 62, pp.238~248 (2019)
  17. Lee SM, "Nonalcoholic fatty liver disease is a risk factor for large-for-gestational-age birthweight", PLoS One, 14, pp.e0221400~ (2019)
  18. Sarkar M, "Non-alcoholic fatty liver disease in pregnancy is associated with adverse maternal and perinatal outcomes", J Hepatol, 73, pp.516~522 (2020)
  19. Ye Y, "Comparison of machine learning methods and conventional logistic regressions for predicting gestational diabetes using routine clinical data : a retrospective cohort study", J Diabetes Res, 2020, pp.4168340~ (2020)
  20. Yan Xiong, "Prediction of gestational diabetes mellitus in the first 19 weeks of pregnancy using machine learning techniques", The Journal of Maternal-Fetal & Neonatal Medicine, 35(13), pp.2457~2463 (2020), Informa UK Limited[DOI]
  21. Artzi NS, "Prediction of gestational diabetes based on nationwide electronic health records", Nat Med, 26, pp.71~76 (2020)
  22. Jung YM, "The risk of pregnancy-associated hypertension in women with nonalcoholic fatty liver disease", Liver Int, 40, pp.2417~2426 (2020)
  23. Ewing JA, "Detecting alcoholism. The CAGE questionnaire", JAMA, 252, pp.1905~1907 (1984)
  24. Saadeh S, "The utility of radiological imaging in nonalcoholic fatty liver disease", Gastroenterology, 123, pp.745~750 (2002)
  25. Taylor KJ, "Quantitative US attenuation in normal liver and in patients with diffuse liver disease : importance of fat", Radiology, 160, pp.65~71 (1986)
  26. Lee JH, "Hepatic steatosis index : a simple screening tool reflecting nonalcoholic fatty liver disease", Dig Liver Dis, 42, pp.503~508 (2010)
  27. Practice bulletin No, "137 : gestational diabetes mellitus", Obstet Gynecol, 122(2 Pt 1), pp.406~416 (2013)
  28. Carpenter MW, "Criteria for screening tests for gestational diabetes", Am J Obstet Gynecol, 144, pp.768~773 (1982)
  29. International Diabetes Institute, "The Asia-Pacific perspective : redefining obesity and its treatment", World Health Organization, pp.1~55 (2000)
  30. Kim Y, "BMI and metabolic disorders in South Korean adults : 1998 Korea National Health and Nutrition Survey", Obes Res, 12, pp.445~453 (2004)
  31. 김세익, "Development of Web-Based Nomograms to Predict Treatment Response and Prognosis of Epithelial Ovarian Cancer", Cancer Research and Treatment, 51(3), pp.1144~1155 (2019), 대한암학회
  32. Liaw A, "Classification and regression by randomForest", R News, 2, pp.18~22 (2002)
  33. Drucker H, "Support vector regression machines", Adv Neural Inf Process Syst, 9, pp.155~161 (1997)
  34. Armstrong MJ, "Extrahepatic complications of nonalcoholic fatty liver disease", Hepatology, 59, pp.1174~1197 (2014)
  35. De Souza LR, "Non-alcoholic fatty liver disease in early pregnancy predicts dysglycemia in mid-pregnancy : prospective study", Am J Gastroenterol, 111, pp.665~670 (2016)
  36. Mousa N, "Impact of non-alcoholic fatty liver disease on pregnancy", Br J Biomed Sci, 75, pp.197~199 (2018)
  37. Sharma DL, "Investigating molecular connections of non-alcoholic fatty liver disease with associated pathological conditions in West Virginia for biomarker analysis", J Clin Cell Immunol, 8, pp.523~ (2017)
  38. Misu H, "A liver-derived secretory protein, selenoprotein P, causes insulin resistance", Cell Metab, 12, pp.483~495 (2010)
  39. Peverill W, "Evolving concepts in the pathogenesis of NASH : beyond steatosis and inflammation", Int J Mol Sci, 15, pp.8591~8638 (2014)
  40. Hershman M, "Implications of nonalcoholic fatty liver disease on pregnancy and maternal and child outcomes", Gastroenterol Hepatol(N Y), 15, pp.221~228 (2019)
  41. Liu H, "Machine learning risk score for prediction of gestational diabetes in early pregnancy in Tianjin, China", Diabetes Metab Res Rev, 37, pp.e3397~ (2021)
  42. Zheng T, "A simple model to predict risk of gestational diabetes mellitus from 8 to 20 weeks of gestation in Chinese women", BMC Pregnancy Childbirth, 19, pp.252~ (2019)
  43. Miller DD, "Artificial intelligence in medical practice : the question to the answer?", Am J Med, 131, pp.129~133 (2018)
  44. Koivusalo SB, "Gestational diabetes mellitus can be prevented by lifestyle intervention : the finnish gestational diabetes prevention study(RADIEL) : a randomized controlled trial", Diabetes Care, 39, pp.24~30 (2016)
  45. Wang C, "A randomized clinical trial of exercise during pregnancy to prevent gestational diabetes mellitus and improve pregnancy outcome in overweight and obese pregnant women", Am J Obstet Gynecol, 216, pp.340~351 (2017)
  46. Song C, "Lifestyle intervention can reduce the risk of gestational diabetes : a meta-analysis of randomized controlled trials", Obes Rev, 17, pp.960~969 (2016)
  47. Shipe ME, "Developing prediction models for clinical use using logistic regression : an overview", J Thorac Dis (2019)
  48. Bril F, "Clinical value of liver ultrasound for the diagnosis of nonalcoholic fatty liver disease in overweight and obese patients", Liver Int, 35, pp.2139~2146 (2015)
  49. Khov N, "Bedside ultrasound in the diagnosis of nonalcoholic fatty liver disease", World J Gastroenterol, 20, pp.6821~6825 (2014)
  50. Kabarra K, "Nonalcoholic steatohepatitis : global impact and clinical consequences", Endocr Connect, 10, pp.R240~R247 (2021)

관련 논문AI추천

Systematic review with meta-analysis: Non-alcoholic fatty liver disease and the association with pregnancy outcomesGuy D Eslick, Hydar El Jamaly, Martin Weltman대한간학회 · Clinical and Molecular Hepatology2022 · 제28권 제1호Nonalcoholic fatty liver disease-based risk prediction of adverse pregnancy outcomes: Ready for prime time?김원, Seung Mi Lee대한간학회 · Clinical and Molecular Hepatology2022 · 제28권 제1호Could Machine Learning-Based Gestational Diabetes Mellitus Prediction Models Replace Traditional Screening Test?황종윤한국모자보건학회 · 한국모자보건학회지2024 · 제28권 제4호A model for predicting gestational diabetes mellitus in early pregnancy: a prospective study in ThailandKasemsak Jandee, Manaphat Suksai, Penkae Rothmanee, Sattamat Lappharat, Tippawan Liabsuetrakul대한산부인과학회 · Obstetrics & Gynecology Science2022 · 제65권 제2호Non-alcoholic fatty liver disease in pregnancy, paving the way for adverse pregnancy outcome risk assessment권자영대한간학회 · Clinical and Molecular Hepatology2022 · 제28권 제1호Role of random blood glucose and HbA1c levels in optimizing glucose tolerance screening in early pregnancy: a retrospective cohort studyAkiko Nishimura, Akitoshi Yamamura, Haruta Mogami, Masaki Mandai, Satoshi Morita, Shin-Ichi Harashima, Yoshikazu Ikeda, Yoshitsugu Chigusa대한산부인과학회 · Obstetrics & Gynecology Science2025 · 제68권 제4호

이 간행물의 다른 논문 (10건)

The management of post-transplantation recurrence of hepatocellular carcinomaMarco PAW Claasen, Hala Muaddi, Gonzalo Sapisochin, Luckshi Rajendran, Tommy Ivanicspp. 1-16Toward a complete cure for chronic hepatitis B: Novel therapeutic targets for hepatitis B virusJun Sik Yoon, 이민종, Yuri Cho, Sun Woong Kimpp. 17-30Current knowledge about biomarkers of acute kidney injury in liver cirrhosisYeon Seok Seo, Han Ah Leepp. 31-46Nonalcoholic fatty liver disease-based risk prediction of adverse pregnancy outcomes: Ready for prime time?Seung Mi Lee, 김원pp. 47-49Non-alcoholic fatty liver disease in pregnancy, paving the way for adverse pregnancy outcome risk assessment권자영pp. 50-51
원문 보기