Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Adverse pregnancy outcomes in women with systemic lupus erythematosus: can we improve predictions with machine learning?

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: BMJ Country of Publication: England NLM ID: 101633705 Publication Model: Print Cited Medium: Print ISSN: 2053-8790 (Print) Linking ISSN: 20538790 NLM ISO Abbreviation: Lupus Sci Med Subsets: MEDLINE
    • Publication Information:
      Original Publication: London : BMJ, [2014]-
    • Subject Terms:
      Antiphospholipid Syndrome*/complications ; Antiphospholipid Syndrome*/diagnosis ; Lupus Erythematosus, Systemic*/complications ; Lupus Erythematosus, Systemic*/drug therapy ; Pregnancy Complications*; Biomarkers ; Female ; Humans ; Infant, Newborn ; Lupus Coagulation Inhibitor ; Machine Learning ; Placenta ; Pregnancy ; Pregnancy Outcome
    • Abstract:
      Objectives: Nearly 20% of pregnancies in patients with SLE result in an adverse pregnancy outcome (APO). We previously developed an APO prediction model using logistic regression and data from Predictors of pRegnancy Outcome: bioMarkers In Antiphospholipid Antibody Syndrome and Systemic Lupus Erythematosus (PROMISSE), a large multicentre study of pregnant women with mild/moderate SLE and/or antiphospholipid antibodies. Our goal was to determine whether machine learning (ML) approaches improve APO prediction and identify other risk factors.
      Methods: The PROMISSE data included 41 predictors from 385 subjects; 18.4% had APO (preterm delivery due to placental insufficiency/pre-eclampsia, fetal/neonatal death, fetal growth restriction). Logistic regression with stepwise selection (LR-S), least absolute shrinkage and selection operator (LASSO), random forest (RF), neural network (NN), support vector machines (SVM-RBF), gradient boosting (GB) and SuperLearner (SL) were compared by cross-validated area under the ROC curve (AUC) and calibration.
      Results: Previously identified APO risk factors, antihypertensive medication use, low platelets, SLE disease activity and lupus anticoagulant (LAC), were confirmed as important with each algorithm. LASSO additionally revealed potential interactions between LAC and anticardiolipin IgG, among others. SL performed the best (AUC=0.78), but was statistically indistinguishable from LASSO, SVM-RBF and RF (AUC=0.77 for all). LR-S, NN and GB had worse AUC (0.71-0.74) and calibration scores.
      Conclusions: We predicted APO with reasonable accuracy using variables routinely assessed prior to the 12th week of pregnancy. LASSO and some ML methods performed better than a standard logistic regression approach. Substantial improvement in APO prediction will likely be realised, not with increasingly complex algorithms but by the discovery of new biomarkers and APO risk factors.
      Competing Interests: Competing interests: JS is an Associate Editor for Lupus Science & Medicine.
      (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)
    • References:
      JAMA Cardiol. 2021 Jun 1;6(6):633-641. (PMID: 33688915)
      J Clin Epidemiol. 2019 Jun;110:12-22. (PMID: 30763612)
      Ann Intern Med. 2015 Aug 4;163(3):153-63. (PMID: 26098843)
      Stat Appl Genet Mol Biol. 2007;6:Article25. (PMID: 17910531)
      Am J Obstet Gynecol. 2017 May;216(5):525.e1-525.e12. (PMID: 28153662)
      Am J Nephrol. 2021;52(2):152-160. (PMID: 33744876)
      PLoS One. 2017 Mar 22;12(3):e0174200. (PMID: 28329014)
      J Thromb Haemost. 2013 Aug;11(8):1527-31. (PMID: 23601766)
      Sci Rep. 2019 Jul 3;9(1):9617. (PMID: 31270349)
      Curr Med Res Opin. 2022 Feb;38(2):229-235. (PMID: 34873978)
      Comput Biol Med. 2018 Oct 1;101:199-209. (PMID: 30195164)
      Front Immunol. 2019 Aug 14;10:1948. (PMID: 31475009)
      Blood. 2003 Mar 1;101(5):1827-32. (PMID: 12393574)
      Arthritis Rheum. 1997 Sep;40(9):1725. (PMID: 9324032)
      Stat Med. 1986 Sep-Oct;5(5):421-33. (PMID: 3786996)
      Arthritis Rheum. 2012 Jul;64(7):2311-8. (PMID: 22275304)
      Radiology. 1982 Apr;143(1):29-36. (PMID: 7063747)
      Rheumatology (Oxford). 2021 Mar 2;60(3):1114-1124. (PMID: 32441742)
      JAMA Cardiol. 2021 Jun 1;6(6):621-623. (PMID: 33688913)
    • Grant Information:
      R21 AR076612 United States AR NIAMS NIH HHS
    • Contributed Indexing:
      Keywords: epidemiology; lupus nephritis; outcome assessment, health care
    • Accession Number:
      0 (Biomarkers)
      0 (Lupus Coagulation Inhibitor)
    • Publication Date:
      Date Created: 20220914 Date Completed: 20220916 Latest Revision: 20220928
    • Publication Date:
      20240513
    • Accession Number:
      PMC9476149
    • Accession Number:
      10.1136/lupus-2022-000769
    • Accession Number:
      36104120