Intrahepatic cholestasis of pregnancy: machine-learning algorithm to predict elevated bile acid based on clinical and laboratory data.
Bile acid
Intrahepatic cholestasis of pregnancy
Liver enzymes
Machine learning
Journal
Archives of gynecology and obstetrics
ISSN: 1432-0711
Titre abrégé: Arch Gynecol Obstet
Pays: Germany
ID NLM: 8710213
Informations de publication
Date de publication:
09 2021
09 2021
Historique:
received:
28
11
2020
accepted:
02
02
2021
pubmed:
21
2
2021
medline:
10
11
2021
entrez:
20
2
2021
Statut:
ppublish
Résumé
Applying machine-learning models to clinical and laboratory features of women with intrahepatic cholestasis of pregnancy (ICP) and creating algorithm to identify these patients without bile acid measurements. This retrospective study included 336 pregnant women with a chief complaint of pruritis without rash during the second/third trimesters. Data extracted included: demographics, obstetric, clinical and laboratory features. The primary outcome was an elevated bile acid measurement ≥ 10 µmol/L, regardless of liver enzyme levels. We used different machine-learning models and statistical regression to predict elevated bile acid levels. Among 336 women who complained about pruritis, 167 had bile acids ≥ 10 µmol/L and 169 had normal levels. Women with elevated bile acids were older than those with normal levels (p = 0.001), higher parity (p = 0.001), and higher glutamic oxaloacetic transaminase ( GOT) (p = 0.001) and glutamic-pyruvic transaminase (GPT) levels (p = 0.001). Using machine-learning models, the XGB Classifier model was the most accurate (area under the curve (AUC), 0.9) followed by the K-neighbors model (AUC, 0.86); and then the Support Vector Classification (SVC) model (AUC, 0.82). The model with the lowest predicative ability was the logistic regression (AUC, 0.72). The maximum sensitivity of the XGB model was 86% and specificity 75%. The best predictive parameters of the XGB model were elevated GOT (Importance 0.17), elevated GPT (Importance 0.16), family history of bile disease (0.16) and previous pregnancy with ICP (0.13). Machine-learning models using clinical data may predict ICP more accurately than logistic regression does. Using detection algorithms derived from these techniques may improve identification of ICP, especially when bile acid testing is not available.
Identifiants
pubmed: 33608801
doi: 10.1007/s00404-021-05994-z
pii: 10.1007/s00404-021-05994-z
doi:
Substances chimiques
Bile Acids and Salts
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
641-647Informations de copyright
© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.
Références
Hämäläinen S-T, Turunen K, Mattila KJ, Kosunen E, Sumanen M (2019) Intrahepatic cholestasis of pregnancy and comorbidity: a 44-year follow-up study. Acta Obstet Gynecol Scand. https://doi.org/10.1111/aogs.13695
doi: 10.1111/aogs.13695
pubmed: 31355915
Ozkan S, Ceylan Y, Ozkan OV, Yildirim S (2015) Review of a challenging clinical issue: intrahepatic cholestasis of pregnancy. World J Gastroenterol 21(23):7134–7141
doi: 10.3748/wjg.v21.i23.7134
Manzotti C, Casazza G, Stimac T, Nikolova D, Gluud C (2019) Total serum bile acids or serum bile acid profile, or both, for the diagnosis of intrahepatic cholestasis of pregnancy. Cochrane database Syst Rev. https://doi.org/10.1002/14651858.CD012546.pub2
doi: 10.1002/14651858.CD012546.pub2
pubmed: 31283001
pmcid: 6613619
Al WI, Nelson-Piercy C, Williamson C (2002) Role of bile acid measurement in pregnancy. Ann Clin Biochem 39(2):105–113
doi: 10.1258/0004563021901856
Liu X, Landon MB, Chen Y, Cheng W (2016) Perinatal outcomes with intrahepatic cholestasis of pregnancy in twin pregnancies. J Matern Fetal Neonatal Med 29(13):2176–2181
doi: 10.3109/14767058.2015.1079612
Floreani A, Gervasi MT (2016) New insights on intrahepatic cholestasis of pregnancy. Clin Liver Dis 20(1):177–189
doi: 10.1016/j.cld.2015.08.010
Sheiner E, Ohel I, Levy A et al (2006) Pregnancy outcome in women with pruritus gravidarum. J Reprod Med 51:394–398
pubmed: 16779986
Batsry L, Zloto K, Kalter A, Baum M, Mazaki-Tovi S, Yinon Y (2019) Perinatal outcomes of intrahepatic cholestasis of pregnancy in twin versus singleton pregnancies: is plurality associated with adverse outcomes? Arch Gynecol Obstet. https://doi.org/10.1007/s00404-019-05247-0
doi: 10.1007/s00404-019-05247-0
pubmed: 31346701
Geenes V, Chappell LC, Seed PT, Steer PJ, Knight M, Williamson C (2014) Association of severe intrahepatic cholestasis of pregnancy with adverse pregnancy outcomes: a prospective population-based case–control study. Hepatology 59(4):1482–1491
doi: 10.1002/hep.26617
Puljic A, Kim E, Page J, Esakoff T, Shaffer B, LaCoursiere DY et al (2015) The risk of infant and fetal death by each additional week of expectant management in intrahepatic cholestasis of pregnancy by gestational age. Am J Obstet Gynecol 212(5):667.e1–5
doi: 10.1016/j.ajog.2015.02.012
Nielsen D (2016) Tree boosting with xgboost-why does xgboost win ”every” machine learning competition? Tech. rep. (Master's thesis, NTNU).
Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30:1145–1159
doi: 10.1016/S0031-3203(96)00142-2
Miller S, Abalos E, Chamillard M, Ciapponi A, Colaci D, Comandé D et al (2016) Beyond too little, too late and too much, too soon: a pathway towards evidence-based, respectful maternity care worldwide. Lancet 388(10056):2176–2192
doi: 10.1016/S0140-6736(16)31472-6
Heinonen S, Kirkinen P (1999) Pregnancy outcome with intrahepatic cholestasis. Obstet Gynecol 94(2):189–193
pubmed: 10432125
Diken Z, Usta IM, Nassar AH (2014) A clinical approach to intrahepatic cholestasis of pregnancy. Am J Perinatol 31(1):1–8
doi: 10.1055/s-0033-1333673
Dixon PH, Wadsworth CA, Chambers J, Donnelly J, Cooley S, Buckley R et al (2014) A comprehensive analysis of common genetic variation around six candidate loci for intrahepatic cholestasis of pregnancy. Am J Gastroenterol 109(1):76–84
doi: 10.1038/ajg.2013.406
Churpek MM, Yuen TC, Winslow C, Meltzer DO, Kattan MW, Edelson DP (2016) Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards. Crit Care Med 44(2):368–374
doi: 10.1097/CCM.0000000000001571
Awan SE, Sohel F, Sanfilippo FM, Bennamoun M, Dwivedi G (2018) Machine learning in heart failure: ready for prime time. Curr Opin Cardiol 33(2):190–195
doi: 10.1097/HCO.0000000000000491