Non-invasive assessment of NAFLD as systemic disease-A machine learning perspective.
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2019
2019
Historique:
received:
01
03
2019
accepted:
13
03
2019
entrez:
27
3
2019
pubmed:
27
3
2019
medline:
18
12
2019
Statut:
epublish
Résumé
Current non-invasive scores for the assessment of severity of non-alcoholic fatty liver disease (NAFLD) and identification of patients with non-alcoholic steatohepatitis (NASH) have insufficient performance to be included in clinical routine. In the current study, we developed a novel machine learning approach to overcome the caveats of existing approaches. Non-invasive parameters were selected by an ensemble feature selection (EFS) from a retrospectively collected training cohort of 164 obese individuals (age: 43.5±10.3y; BMI: 54.1±10.1kg/m2) to develop a model able to predict the histological assessed NAFLD activity score (NAS). The model was evaluated in an independent validation cohort (122 patients, age: 45.2±11.75y, BMI: 50.8±8.61kg/m2). EFS identified age, γGT, HbA1c, adiponectin, and M30 as being highly associated with NAFLD. The model reached a Spearman correlation coefficient with the NAS of 0.46 in the training cohort and was able to differentiate between NAFL (NAS≤4) and NASH (NAS>4) with an AUC of 0.73. In the independent validation cohort, an AUC of 0.7 was achieved for this separation. We further analyzed the potential of the new model for disease monitoring in an obese cohort of 38 patients under lifestyle intervention for one year. While all patients lost weight under intervention, increasing scores were observed in 15 patients. Increasing scores were associated with significantly lower absolute weight loss, lower reduction of waist circumference and basal metabolic rate. A newly developed model (http://CHek.heiderlab.de) can predict presence or absence of NASH with reasonable performance. The new score could be used to detect NASH and monitor disease progression or therapy response to weight loss interventions.
Sections du résumé
BACKGROUND & AIMS
Current non-invasive scores for the assessment of severity of non-alcoholic fatty liver disease (NAFLD) and identification of patients with non-alcoholic steatohepatitis (NASH) have insufficient performance to be included in clinical routine. In the current study, we developed a novel machine learning approach to overcome the caveats of existing approaches.
METHODS
Non-invasive parameters were selected by an ensemble feature selection (EFS) from a retrospectively collected training cohort of 164 obese individuals (age: 43.5±10.3y; BMI: 54.1±10.1kg/m2) to develop a model able to predict the histological assessed NAFLD activity score (NAS). The model was evaluated in an independent validation cohort (122 patients, age: 45.2±11.75y, BMI: 50.8±8.61kg/m2).
RESULTS
EFS identified age, γGT, HbA1c, adiponectin, and M30 as being highly associated with NAFLD. The model reached a Spearman correlation coefficient with the NAS of 0.46 in the training cohort and was able to differentiate between NAFL (NAS≤4) and NASH (NAS>4) with an AUC of 0.73. In the independent validation cohort, an AUC of 0.7 was achieved for this separation. We further analyzed the potential of the new model for disease monitoring in an obese cohort of 38 patients under lifestyle intervention for one year. While all patients lost weight under intervention, increasing scores were observed in 15 patients. Increasing scores were associated with significantly lower absolute weight loss, lower reduction of waist circumference and basal metabolic rate.
CONCLUSIONS
A newly developed model (http://CHek.heiderlab.de) can predict presence or absence of NASH with reasonable performance. The new score could be used to detect NASH and monitor disease progression or therapy response to weight loss interventions.
Identifiants
pubmed: 30913263
doi: 10.1371/journal.pone.0214436
pii: PONE-D-19-06023
pmc: PMC6435145
doi:
Substances chimiques
Biomarkers
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0214436Déclaration de conflit d'intérêts
JK, UN, MR, SH, HAB, CR, AG, and DH state that there are no conflicts of interest to declare. JPS and AC state that they received royalties for a scientific lecture, which was in part supported by TECOmedical group. This does not alter the authors’ adherence to PLOS ONE policies on sharing data and materials.
Références
Biochem Biophys Res Commun. 1999 Apr 2;257(1):79-83
pubmed: 10092513
Gut. 2008 Oct;57(10):1441-7
pubmed: 18390575
Gastroenterology. 2015 Aug;149(2):389-97.e10
pubmed: 25935633
J Hepatol. 2015 Apr;62(1 Suppl):S47-64
pubmed: 25920090
Sci Rep. 2015 Aug 13;5:13058
pubmed: 26269425
Obesity (Silver Spring). 2017 Oct;25(10):1776-1785
pubmed: 28834421
Metabolism. 2016 Aug;65(8):1087-95
pubmed: 26972222
J Nutr Metab. 2011;2011:369168
pubmed: 21773018
Obes Surg. 2011 Apr;21(4):431-9
pubmed: 20532833
N Engl J Med. 2017 Aug 24;377(8):756-768
pubmed: 28834467
Z Gastroenterol. 2016 Dec;54(12):1312-1319
pubmed: 27936481
Hepatology. 2003 Aug;38(2):518-26
pubmed: 12883497
Metabolism. 2014 Dec;63(12):1542-52
pubmed: 25267016
Gastrointest Endosc. 2014 Oct;80(4):626-633.e1
pubmed: 24796959
J Gastroenterol. 2011 Feb;46(2):257-68
pubmed: 20842510
Hepatology. 2016 Jul;64(1):73-84
pubmed: 26707365
Hepatology. 2005 Jun;41(6):1313-21
pubmed: 15915461
Hepatology. 2009 Mar;49(3):1017-44
pubmed: 19243014
Hepatology. 2018 Jul;68(1):349-360
pubmed: 29222917
Hepatology. 2012 Feb;55(2):455-64
pubmed: 21993925
Clin Gastroenterol Hepatol. 2009 Oct;7(10):1104-12
pubmed: 19523535
Hepatology. 2017 Aug;66(2):555-563
pubmed: 28120471
Am J Gastroenterol. 2007 Feb;102(2):399-408
pubmed: 17311652
Am J Physiol Gastrointest Liver Physiol. 2018 Sep 1;315(3):G329-G338
pubmed: 29878845
BioData Min. 2016 Nov 18;9:36
pubmed: 27891179
J Hepatol. 2013 May;58(5):1007-19
pubmed: 23183525
Cleve Clin J Med. 2008 Oct;75(10):721-8
pubmed: 18939388
PLoS One. 2012;7(3):e30325
pubmed: 22431959
Hepatology. 2008 Feb;47(2):455-60
pubmed: 18038452
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Nat Rev Gastroenterol Hepatol. 2013 Jun;10(6):330-44
pubmed: 23507799
Nat Med. 2001 Aug;7(8):947-53
pubmed: 11479628
Diabetes Metab. 2014 Apr;40(2):95-107
pubmed: 24486145
Clin Liver Dis. 2016 May;20(2):293-312
pubmed: 27063270
BioData Min. 2017 Jun 27;10:21
pubmed: 28674556
BMJ Open Diabetes Res Care. 2017 Jul 19;5(1):e000415
pubmed: 28878939
Gastroenterology. 2005 Jun;128(7):1898-906
pubmed: 15940625
Gastroenterology. 2002 Sep;123(3):745-50
pubmed: 12198701
PLoS One. 2017 Jul 26;12(7):e0180947
pubmed: 28746378
Hepatology. 2007 Apr;45(4):846-54
pubmed: 17393509
Hepatology. 2010 May;51(5):1820-32
pubmed: 20432259
Clin Liver Dis. 2016 May;20(2):313-24
pubmed: 27063271
Gastroenterology. 2013 Dec;145(6):1271-9.e1-3
pubmed: 23973920
Gastroenterology. 2017 Feb;152(3):479-481
pubmed: 28038929
Hepatology. 2012 Nov;56(5):1751-9
pubmed: 22707395
Liver Int. 2006 Mar;26(2):151-6
pubmed: 16448452
PLoS One. 2016 Feb 23;11(2):e0147237
pubmed: 26905872