{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T09:13:44Z","timestamp":1794561224787,"version":"4.9.1"},"reference-count":34,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T00:00:00Z","timestamp":1663113600000},"content-version":"unspecified","delay-in-days":13,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100002193","name":"Lupus Foundation of America","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002193","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["AR076612"],"award-info":[{"award-number":["AR076612"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Lupus Sci Med"],"published-print":{"date-parts":[[2022,9]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>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\u20130.74) and calibration scores.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/lupus-2022-000769","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T11:50:54Z","timestamp":1663156254000},"page":"e000769","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":29,"title":["Adverse pregnancy outcomes in women with systemic lupus erythematosus: can we improve predictions with machine learning?"],"prefix":"10.1136","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5674-3589","authenticated-orcid":false,"given":"Melissa J","family":"Fazzari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marta M","family":"Guerra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jane","family":"Salmon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mimi Y","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2022,9,14]]},"reference":[{"key":"2022123009104626000_9.1.e000769.1","doi-asserted-by":"publisher","DOI":"10.7326\/M14-2235"},{"key":"2022123009104626000_9.1.e000769.2","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-45989-0","article-title":"Machine learning approaches to predict lupus disease activity from gene expression data","volume":"9","author":"Kegerreis","year":"2019","journal-title":"Sci Rep"},{"key":"2022123009104626000_9.1.e000769.3","doi-asserted-by":"publisher","DOI":"10.1159\/000513566"},{"key":"2022123009104626000_9.1.e000769.4","doi-asserted-by":"crossref","DOI":"10.1002\/art.1780400928","article-title":"Updating the American College of rheumatology revised criteria for the classification of systemic lupus erythematosus","volume":"40","author":"Hochberg","year":"1997","journal-title":"Arthritis Rheum"},{"key":"2022123009104626000_9.1.e000769.5","doi-asserted-by":"publisher","DOI":"10.1002\/art.34402"},{"key":"2022123009104626000_9.1.e000769.6"},{"key":"2022123009104626000_9.1.e000769.7","doi-asserted-by":"crossref","unstructured":"Miller AJ . Subset selection in regression. London: Chapman and Hall, 1990.","DOI":"10.1007\/978-1-4899-2939-6"},{"key":"2022123009104626000_9.1.e000769.8","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"2022123009104626000_9.1.e000769.9","unstructured":"Ripley BD . Pattern recognition and neural networks. Cambridge university press, 2007."},{"key":"2022123009104626000_9.1.e000769.10","doi-asserted-by":"crossref","unstructured":"Cristianini N , Shawe-Taylor J . An introduction to support vector machines and other kernel-based learning methods. Cambrigde: Cambridge University Press, 2000. www.support-vector.net","DOI":"10.1017\/CBO9780511801389"},{"key":"2022123009104626000_9.1.e000769.11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2022123009104626000_9.1.e000769.12","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"2022123009104626000_9.1.e000769.13","doi-asserted-by":"crossref","unstructured":"van der Laan MJ , Polley EC , Hubbard AE . Super learner. Stat Appl Genet Mol Biol 2008;6.doi:10.2202\/1544-6115.1309","DOI":"10.2202\/1544-6115.1309"},{"key":"2022123009104626000_9.1.e000769.14","unstructured":"R Core Team . R: a language and environment for statistical computing. Vienna, Austria R Foundation for Statistical Computing; 2021. https:\/\/www.R-project.org\/"},{"key":"2022123009104626000_9.1.e000769.15","unstructured":"ed Hastie T , Tibshirani R , Jerome F . The Elements of Statistical Learning: Data Mining, Inference, and Prediction.. In: 2Nd ED. New York: Springer, 2009."},{"key":"2022123009104626000_9.1.e000769.16","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"2022123009104626000_9.1.e000769.17","doi-asserted-by":"crossref","unstructured":"Steyerberg EW . Clinical prediction models. New York: Springer, 2009.","DOI":"10.1007\/978-0-387-77244-8"},{"key":"2022123009104626000_9.1.e000769.18","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4780050506"},{"key":"2022123009104626000_9.1.e000769.19","first-page":"1","article-title":"DALEX: Explainers for complex predictive models in R","volume":"19","author":"Biecek","year":"2018","journal-title":"JMLR"},{"key":"2022123009104626000_9.1.e000769.20","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1001\/jamacardio.2021.0139","article-title":"Incremental benefits of machine Learning-When do we need a better Mousetrap?","volume":"6","author":"Engelhard","year":"2021","journal-title":"JAMA Cardiol"},{"key":"2022123009104626000_9.1.e000769.21","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1001\/jamacardio.2021.0122","article-title":"Use of machine learning models to predict death after acute myocardial infarction","volume":"6","author":"Khera","year":"2021","journal-title":"JAMA Cardiol"},{"key":"2022123009104626000_9.1.e000769.22","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1038\/s42256-021-00307-0","article-title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","volume":"3","author":"Roberts","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2022123009104626000_9.1.e000769.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2019.02.004"},{"key":"2022123009104626000_9.1.e000769.24","doi-asserted-by":"publisher","DOI":"10.1198\/016214502753479248"},{"key":"2022123009104626000_9.1.e000769.25","doi-asserted-by":"crossref","unstructured":"Rudin C , Radin J . Why are we using black box models in AI when we don\u2019t need to? A lesson from an explainable AI competition. Harv Data Sci Rev 2019;1.doi:10.1162\/99608f92.5a8a3a3d","DOI":"10.1162\/99608f92.5a8a3a3d"},{"key":"2022123009104626000_9.1.e000769.26","doi-asserted-by":"crossref","first-page":"525.e1","DOI":"10.1016\/j.ajog.2017.01.026","article-title":"Antiphospholipid antibody profile based obstetric outcomes of primary antiphospholipid syndrome: the PREGNANTS study","volume":"216","author":"Saccone","year":"2017","journal-title":"Am J Obstet Gynecol"},{"key":"2022123009104626000_9.1.e000769.27","doi-asserted-by":"crossref","DOI":"10.3389\/fimmu.2019.01948","article-title":"Triple antiphospholipid (aPL) antibodies positivity is associated with pregnancy complications in aPL carriers: a multicenter study on 62 pregnancies","volume":"10","author":"Lazzaroni","year":"2019","journal-title":"Front Immunol"},{"key":"2022123009104626000_9.1.e000769.28","doi-asserted-by":"publisher","DOI":"10.1111\/jth.12264"},{"key":"2022123009104626000_9.1.e000769.29","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2002-02-0441"},{"key":"2022123009104626000_9.1.e000769.30","doi-asserted-by":"crossref","first-page":"1114","DOI":"10.1093\/rheumatology\/keaa203","article-title":"Eureka algorithm predicts obstetric risk and response to treatment in women with different subsets of anti-phospholipid antibodies","volume":"60","author":"Pregnolato","year":"2021","journal-title":"Rheumatology"},{"key":"2022123009104626000_9.1.e000769.31","doi-asserted-by":"crossref","unstructured":"Hosmer WD , Lemeshow S , Sturdivant RX . Applied logistic regression. 398. John Wiley & Sons, 2013.","DOI":"10.1002\/9781118548387"},{"key":"2022123009104626000_9.1.e000769.32","doi-asserted-by":"crossref","unstructured":"Ceccarelli F , Sciandrone M , Perricone C . Prediction of chronic damage in systemic lupus erythematosus by using machine-learning models. PLoS One 201;7:e0174200.doi:10.1371\/journal.pone.0174200","DOI":"10.1371\/journal.pone.0174200"},{"key":"2022123009104626000_9.1.e000769.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.08.029"},{"key":"2022123009104626000_9.1.e000769.34","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1080\/03007995.2021.2015156","article-title":"Prediction and associated factors of hypothyroidism in systemic lupus erythematosus: a cross-sectional study based on multiple machine learning algorithms","volume":"38","author":"Huang","year":"2022","journal-title":"Curr Med Res Opin"}],"container-title":["Lupus Science &amp; Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/lupus-2022-000769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T12:18:55Z","timestamp":1672402735000},"score":1,"resource":{"primary":{"URL":"https:\/\/lupus.bmj.com\/lookup\/doi\/10.1136\/lupus-2022-000769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,9,14]]},"published-print":{"date-parts":[[2022,9]]}},"alternative-id":["10.1136\/lupus-2022-000769"],"URL":"https:\/\/doi.org\/10.1136\/lupus-2022-000769","relation":{},"ISSN":["2053-8790"],"issn-type":[{"value":"2053-8790","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}