[1] Pivovarov R, Perotte AJ, Grave E, Angiolillo J, Wiggins CH, Elhadad N. Learning
probabilistic phenotypes from heterogeneous EHR data. J Biomed Inform 2015;58:
156–65.
[2] Perotte A, Ranganath R, Hirsch JS, Blei D, Elhadad N. Risk prediction for chronic
kidney disease progression using heterogeneous electronic health record data and
time series analysis. J Am Med Inform Assoc 2015;22(4):872–80.
[3] Jin B, Che C, Liu Z, Zhang S, Yin X, Wei X. Predicting the risk of heart failure with
EHR sequential data modeling. IEEE Access 2018;6:9256–61.
[4] Canapari CA, Hoppin AG, Kinane TB, Thomas BJ, Torriani M, Katz ES. Relationship
between sleep apnea, fat distribution, and insulin resistance in obese children.
J Clin Sleep Med 2011;7(3):268–73.
[5] Nagata T, Hata J, Sakata S, Oishi E, Honda T, Furuta Y, Ohara T, Yoshida D,
Hirakawa Y, Shibata M, Ide T, Kitazono T, Tsutsui H, Ninomiya T. Serum Nterminal pro-B-type natriuretic peptide as a predictor for future development of
atrial fibrillation in a general population: the Hisayama Study. Int J Cardiol 2020;
320:90–6.
[6] Shimizu S, Hoyer PO, Hyv¨
arinen AKA. A linear non-Gaussian acyclic model for
causal discovery. J Mach Learn Res 2006;7:2003–30.
[7] Helaj¨
arvi H, R¨
osenstrom T, Pahkala K, K¨
ah¨
onen M, Lehtim¨
aki T, Heinonen OJ,
Oikonen M, Tammelin T, Viikari JS, Raitakari OT. Exploring causality between TV
viewing and weight change in young and middle-aged adults. The Cardiovascular
Risk in Young Finns study. PLoS ONE 2014;9(7):e101860.
[8] Ogawa T, Shimobayashi H, Hirayama J-I, Kawanabe M. Asymmetric directed
functional connectivity within the frontoparietal motor network during motor
imagery and execution. Neuroimage 2022;247:118794.
[9] Goldberg D, Nichols D, Oki BM, Terry D. Using collaborative filtering to weave an
information tapestry. Commun ACM 1992;35(12):61–70.
[10] Seiffert C, et al. RUSBoost: a hybrid approach to alleviating class imbalance. IEEE
Trans Syst Man Cybern A Syst Hum 2010;40(1):185–97.
[11] Resnick P, Varian HR. Recommender systems. Commun ACM 1997;40(3):56–8.
[12] Gr¨
aßer F, Beckert S, Küster D, Schmitt J, Abraham S, Malberg H, Zaunseder S.
Therapy decision support based on recommender system methods. J Healthc Eng
2017;2017:8659460.
[13] Zeng X, Ding N, Rodríguez-Pat´
on A, Zou Q. Probability-based collaborative
filtering model for predicting gene–disease associations. BMC Medical Genom.
2017;10(5):45–53. https://doi.org/10.1186/s12920-017-0313-y.
[14] Fujiwara K, Huang Y, Hori K, Nishioji K, Kobayashi M, Kamaguchi M, Kano M.
Over- and under-sampling approach for extremely imbalanced and small minority
data problem in health record analysis. Front Public Health 2020;8:178.
[15] Lonardo A, Leoni S, Alswat KA, Fouad Y. History of nonalcoholic fatty liver disease.
Int J Mol Sci 2020;21(16):5888.
[16] Stefan N, H¨
aring H-U, Cusi K. Non-alcoholic fatty liver disease: causes, diagnosis,
cardiometabolic consequences, and treatment strategies. Lancet Diabetes
Endocrinol 2019;7(4):313–24.
[17] Diehl AM, Day C. Cause, pathogenesis, and treatment of nonalcoholic
steatohepatitis. N Engl J Med 2017;377(21):2063–72.
[18] European Association for the Study of the Liver (EASL), European Association for
the Study of Diabetes (EASD), European Association for the Study of Obesity
(EASO). EASL–EASD–EASO clinical practice guidelines for the management of nonalcoholic fatty liver disease. J Hepatol 2016;64(6):1388–402.
[19] Rinella ME. Nonalcoholic fatty liver disease: a systematic review. JAMA 2015;313
(22):2263–73.
[20] Bedogni G, Tamini S, Caroli D, Cicolini S, Domenicali M, Sartorio A. Development
and internal validation of fatty liver prediction models in obese children and
adolescents. J Clin Med 2021;10(7):1470.
[21] Deprince A, Haas JT, Staels B. Dysregulated lipid metabolism links NAFLD to
cardiovascular disease. Mol Metab 2020;42:101092.
[22] Orr WC, Fass R, Sundaram SS, Scheimann AO. The effect of sleep on
gastrointestinal functioning in common digestive diseases. Lancet Gastroenterol
Hepatol 2020;5(6):616–24.
[23] Shimizu S, Inazumi T, Sogawa Y, Hyv¨
arinen A, Kawahara Y, Washio T, et al.
DirectLiNGAM: a direct method for learning a linear non-Gaussian structural
equation model. J Mach Learn Res 2011;12:1225–48.
[24] Hyv¨
arinen A, Smith SM. Pairwise likelihood ratios for estimation of non-Gaussian
structural equation models. J Mach Learn Res 2013;14(1):111–52.
[25] Desrosiers C, Karypis G. A comprehensive survey of neighborhood-based
recommendation methods. In: Recommender systems handbook. NY: Springer;
2011.
[26] Nishioji K, Sumida Y, Kamaguchi M, Mochizuki N, Kobayashi M, Nishimura T,
Yamaguchi K, Itoh Y. Prevalence of and risk factors for non-alcoholic fatty liver
disease in a non-obese Japanese population, 2011–2012. J Gastroenterol 2015;50
(1):95–108.
[27] Musso G, Cassader M, Olivetti C, Rosina F, Carbone G, Gambino R. Association of
obstructive sleep apnoea with the presence and severity of non-alcoholic fatty liver
disease.A systematic review and meta-analysis. Obes Rev 2013;14(5):417–31.
[28] Young T, Peppard PE, Gottlieb DJ. Epidemiology of obstructive sleep apnea: a
population health perspective. Am J Respir Crit Care Med 2002;165(9):1217–39.
[29] Takegami M, Hayashino Y, Chin K, Sokejima S, Kadotani H, Akashiba T, Kimura H,
Ohi M, Fukuhara S. Simple four-variable screening tool for identification of
patients with sleep-disordered breathing. Sleep 2009;32(7):939–48.
[30] Sterling RK, Lissen E, Clumeck N, Sola R, Correa MC, Montaner J, Sulkowski MS,
Torriani FJ, Dieterich DT, Thomas DL, Messinger D, Nelson M. Development of a
simple noninvasive index to predict significant fibrosis in patients with HIV/HCV
coinfection. Hepatology 2006;43(6):1317–25.
5. Conclusion
In this study, we proposed a new medical checkup data analysis
method based on LiNGAM. In the proposed LiNGAM-beta, we can
quantitatively analyze the causal directions and strengths among health
checkup items. We adopted CF for missing value imputation of the
medical checkup data. We performed a causal effect analysis to identify
NAFLD severity factors from the medical checkup data based on the
proposed LiNGAM-beta. Since the causal relationships estimated by
LiNGAM-beta were consistent with previous reports on NAFLD pro
gression, it is appropriate to use the proposed method for causal analysis
of medical checkup data. In particular, our analysis indicated that BUN
is a candidate factor of NAFLD progression, although additional exper
iments and collection of clinical data are needed to confirm our result.
In future works, we will try to analyze medical checkup data
including binary or discrete variables, such as answers to questionnaires.
Since there has been an attempt to extend LiNGAM so that it can deal
with discrete variables [69], we will adopt such a method. We will apply
the proposed method to other types of EHR in order to identify unknown
factors of various diseases. As for clinical data, we will apply the pro
posed LiNGAM-beta with appropriate feature extraction and formatting,
and compare it with other existing methods.
Funding
This work was supported in part by JST PRESTO #JPMJPR1859.
Data availability statement
The health examination data will be made available by the corre
sponding author to colleagues who propose a reasonable scientific
request after approval by the institutional review board of the Japanese
Red Cross Kyoto Daini Hospital.
CRediT authorship contribution statement
K. F is with Quadlytics Inc. as well as Nagoya University. M. K is with
Quadlytics Inc. as well as Kyoto University. H. K's laboratory is sup
ported by donations from Fukuda Lifetech Co., Ltd., Fukuda Life Tech
Keiji Co., Ltd., Tanaka Sleep Clinic, Akita Sleep Clinic, and Ai Ai Care
Co., Ltd., made to the Shiga University of Medical Science. Other authors
declare that the research was conducted in the absence of any com
mercial or financial relationship that could be construed as a potential
conflict of interest.
T. Uchida et al.
Artificial Intelligence In Medicine 128 (2022) 102310
[51] Taketani H, Sumida Y, Tanaka S, Imajo K, Yoneda M, Hyogo H, Ono M, Fujii H,
Eguchi Y, Kanemasa K, et al. The association of insomnia with gastroesophageal
reflux symptoms in biopsy-proven nonalcoholic fatty liver disease. J Gastroenterol
2014;49(7):1163–74.
[52] Kim CW, Yun KE, Jung HS, Chang Y, Choi ES, Kwon MJ, Lee EH, Woo EJ, Kim NH,
Shin H, Ryu S. Sleep duration and quality in relation to non-alcoholic fatty liver
disease in middle-aged workers and their spouses. J Hepatol 2013;59(2):351–7.
[53] Musso G, Gambino R, Tabibian JH, Ekstedt M, Kechagias S, Hamaguchi M,
Hultcrantz R, Hagstr¨
om H, Yoon SK, Charatcharoenwitthaya P, George J, Barrera F,
Haflioad´
ottir S, Bj¨
ornsson ES, Armstrong MJ, Hopkins LJ, Gao X, Francque S,
Verrijken A, Yilmaz Y, Lindor KD, Charlton M, Haring R, Lerch MM, Rettig R,
V¨
olzke H, Ryu S, Li G, Wong LL, Machado M, Cortez-Pinto H, Yasui K, Cassader M.
Association of non-alcoholic fatty liver disease with chronic kidney disease: a
systematic review and meta-analysis. PLoS Med 2014;11(7):e1001680.
[54] Balakrishnan M, Patel P, Dunn-Valadez S, Dao C, Khan V, Ali H, El-Serag L,
Hernaez R, Sisson A, Thrift AP, Liu Y, El-Serag HB, Kanwal F. Women have a lower
risk of nonalcoholic fatty liver disease but a higher risk of progression vs men: a
systematic review and meta-analysis. Clin Gastroenterol Hepatol 2021;19(1):
61–71.e15.
[55] Lonardo A, Suzuki A. Sexual dimorphism of NAFLD in adults. Focus on clinical
aspects and implications for practice and translational research. J Clin Med 2020;9
(5):1278.
[56] Lonardo A, Nascimbeni F, Ballestri S, Fairweather D, Win S, Than TA,
Abdelmalek MF, Suzuki A. Sex differences in nonalcoholic fatty liver disease: state
of the art and identification of research gaps. Hepatology 2019;70(4):1457–69.
[57] Whittle AT, Marshall I, Mortimore IL, Wraith PK, Sellar RJ, Douglas NJ. Neck soft
tissue and fat distribution: comparison between normal men and women by
magnetic resonance imaging. Thorax 1999;54(4):323–8.
[58] O’Donnell CP, Schwartz AR, Smith PL. Upper airway collapsibility: the importance
of gender and adiposity. Am J Respir Crit Care Med 2000;162(5):1606–7.
[59] Mohsenin V. Gender differences in the expression of sleep-disordered breathing:
role of upper airway dimensions. Chest 2001;120(5):1442–7.
[60] Westreich R, Gozlan-Talmor A, et al. The presence of snoring as well as its intensity
is underreported by women. J Clin Sleep Med 2019;15(3):471–6.
[61] Mejdell T, Skogestad S. Estimation of distillation compositions from multiple
temperature measurements using partial-least-squares regression. Ind Eng Chem
Res 1991;30(12):2543–55.
[62] Kresta JV, Marlin TE, MacGregor JF. Development of inferential process models
using PLS. Comput Chem Eng 1994;18(7):597–611.
[63] Nakahara T, Hyogo H, Yoneda M, Sumida Y, Eguchi Y, Fujii H, Ono M,
Kawaguchi T, Imajo K, Aikata H, Tanaka S, Kanemasa K, Fujimoto K, Anzai K,
Saibara T, Sata M, Nakajima A, Itoh Y, Chayama K, Okanoue T, Japan Study Group
of Nonalcoholic Fatty Liver Disease (JSG-NAFLD). Type 2 diabetes mellitus is
associated with the fibrosis severity in patients with nonalcoholic fatty liver disease
in a large retrospective cohort of Japanese patients. J Gastroenterol 2014;49(11):
1477–84.
[64] Sun DQ, Liu WY, Wu SJ, Zhu GQ, Braddock M, Zhang DC, Shi KQ, Song D,
Zheng MH. Increased levels of low-density lipoprotein cholesterol within the
normal range as a risk factor for nonalcoholic fatty liver disease. Oncotarget 2016;
7(5):5728–37.
[65] Min HK, Kapoor A, Fuchs M, Mirshahi F, Zhou H, Maher J, Kellum J, Warnick R,
Contos MJ, Sanyal AJ. Increased hepatic synthesis and dysregulation of cholesterol
metabolism is associated with the severity of nonalcoholic fatty liver disease. Cell
Metab 2012;15(5):665–74.
[66] Rafiq N, Bai C, Fang Y, Srishord M, McCullough A, Gramlich T, Younossi ZM. Longterm follow-up of patients with nonalcoholic fatty liver. Clin Gastroenterol Hepatol
2009;7(2):234–8.
[67] Ho TK. The random subspace method for constructing decision forests. IEEE Trans
Pattern Anal Mach Intell 1998;20(8):832–44.
[68] Breiman L. Random forests. Mach Learn 2001;45(1):5–32.
[69] Inazumi T, Washio T, Shimizu S, Suzuki J, Yamamoto A, Kawahara Y. Discovering
causal structures in binary exclusive-or skew acyclic models. 2012. arXiv:
1202.3736.
[31] Shah AG, Lydecker A, Murray K, Tetri BN, Contos MJ, Sanyal AJ. Comparison of
noninvasive markers of fibrosis in patients with nonalcoholic fatty liver disease.
Clin Gastroenterol Hepatol 2009;7(10):1104–12.
[32] Sumida Y, Yoneda M, Hyogo H, Itoh Y, Ono M, Fujii H, Eguchi Y, Suzuki Y, Aoki N,
Kanemasa K, Fujita K, Chayama K, Saibara T, Kawada N, Fujimoto K, Kohgo Y,
Yoshikawa T, Okanoue T. Validation of the FIB4 index in a Japanese nonalcoholic
fatty liver disease population. BMC Gastroenterol 2012;12:2.
[33] Kanwal F, Kramer JR, Mapakshi S, Natarajan Y, Chayanupatkul M, Richardson PA,
Li L, Desiderio R, Thrift AP, Asch SM, Chu J, El-Serag HB. Risk of hepatocellular
cancer in patients with non-alcoholic fatty liver disease. Gastroenterology 2018;
155(6):1828–37.
[34] Hassan K, Bhalla V, Regal MEEl, A-Kader HH. Nonalcoholic fatty liver disease: a
comprehensive review of a growing epidemic. World J Gastroenterol 2014;20(34):
12082–101.
[35] Florentino GS, Cotrim HP, Vilar CP, Florentino AV, Guimaraes GM, Barreto VS.
Nonalcoholic fatty liver disease in menopausal women. Arq Gastroenterol 2013;50
(3):180–5.
[36] Hug N. Surprise: a Python library for recommender systems. JOpen Source Softw
2020;5(52):2174. https://doi.org/10.21105/joss.02174. URL doi:10.21105/
joss.02174.
[38] Andridge RR, Little RJ. A review of hot deck imputation for survey non-response.
Int Stat Rev 2010;78(1):40–64.
[39] Hamaguchi M, Kojima T, Takeda N, Nakagawa T, Taniguchi H, Fujii K, Omatsu T,
Nakajima T, Sarui H, Shimazaki M, et al. The metabolic syndrome as a predictor of
nonalcoholic fatty liver disease. Ann Intern Med 2005;143(10):722–8.
[40] Eguchi Y, Eguchi T, Mizuta T, Ide Y, Yasutake T, Iwakiri R, Hisatomi A, Ozaki I,
Yamamoto K, Kitajima Y, Kawaguchi Y, Kuroki S, Ono N. Visceral fat accumulation
and insulin resistance are important factors in nonalcoholic fatty liver disease.
J Gastroenterol 2006;41(5):462–9.
[41] Eguchi Y, Hyogo H, Ono M, Mizuta T, Ono N, Fujimoto K, et al. Prevalence and
associated metabolic factors of nonalcoholic fatty liver disease in the general
population from 2009 to 2010 in Japan: a multicenter large retrospective study.
J Gastroenterol 2012;47(5):586–95.
[42] Thomsen KL, Grønbæk H, Glavind E, Hebbard L, Jessen N, Clouston A, George J,
Vilstrup H. Experimental nonalcoholic steatohepatitis compromises ureagenesis, an
essential hepatic metabolic function. Am J Physiol Gastrointest Liver Physiol 2014;
307(3):295–301.
[43] Hashemi Kani A, Alavian SM, Esmaillzadeh A, Adibi P, Azadbakht L. Dietary
quality indices and biochemical parameters among patients with non alcoholic
fatty liver disease (NAFLD). Hepat Mon 2013;13(7):e10943.
[44] Erçin CN, Do˘
gru T, Çelebi G, Gürel H, Genç H, Serto˘
glu E, Ba˘
gci S. The relationship
between blood urea nitrogen levels and metabolic, biochemical, and
histopathologic findings of nondiabetic, nonhypertensive patients with
nonalcoholic fatty liver disease. Turk J Med Sci 2016;46(4):985–91.
[45] Eriksen PL, Vilstrup H, Rigbolt K, Suppli MP, Sørensen M, Heebøll S, Veidal SS,
Knop FK, Thomsen KL. Non-alcoholic fatty liver disease alters expression of genes
governing hepatic nitrogen conversion. Liver Int 2019;39(11):2094–101.
[46] De Chiara F, Heebøll S, Marrone G, Montoliu C, Hamilton-Dutoit S, Ferrandez A,
Andreola F, Rombouts K, Grønbæk H, Felipo V, Gracia-Sancho J, Mookerjee RP,
Vilstrup H, Jalan R, Thomsen KL. Urea cycle dysregulation in non-alcoholic fatty
liver disease. J Hepatol 2018;69(4):905–15.
[47] Lonardo A, Loria P, Leonardi F, Borsatti A, Neri P, Pulvirenti M, Verrone AM,
Bagni A, Bertolotti M, Ganazzi D, Carulli N, Group PS. Fasting insulin and uric acid
levels but not indices of iron metabolism are independent predictors of nonalcoholic fatty liver disease. a case-control study. Dig Liver Dis 2002;34(1):204–11.
[48] Zhou Y, Wei F, Fan Y. High serum uric acid and risk of nonalcoholic fatty liver
disease: a systematic review and meta-analysis. Clin Biochem 2016;49(7):636–42.
[49] Jaruvongvanich V, Ahuja W, Wirunsawanya K, Wijarnpreecha K, Ungprasert P.
Hyperuricemia is associated with nonalcoholic fatty liver disease activity score in
patients with nonalcoholic fatty liver disease: a systematic review and metaanalysis. Eur J Gastroenterol Hepatol 2017;29(9):1031–5.
[50] Mosca A, Nobili V, De Vito R, Crudele A, Scorletti E, Villani A, et al. Serum uric
acid concentrations and fructose consumption are independently associated with
NASH in children and adolescents. J Hepatol 2017;66(5):1031–6.
10
...