{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T23:40:49Z","timestamp":1793749249455,"version":"4.6.1"},"reference-count":25,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100003123","name":"Fetal Medicine Foundation","doi-asserted-by":"publisher","award":["1037116"],"award-info":[{"award-number":["1037116"]}],"id":[{"id":"10.13039\/501100003123","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["obgyn.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Ultrasound in Obstet &amp;amp; Gyne"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate the accuracy of predicting the risk of developing pre\u2010eclampsia (PE) according to first\u2010trimester maternal demographic characteristics, medical history and biomarkers using artificial\u2010intelligence and machine\u2010learning methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      The data were derived from prospective non\u2010interventional screening for PE at 11\u201313\u2009weeks' gestation at two maternity hospitals in the UK. The data were divided into three subsets. The first set, including 30\u2009437 subjects, was used to develop the training process, the second set of 10\u2009000 subjects was utilized to optimize the machine\u2010learning hyperparameters and the third set of 20\u2009352 subjects was coded and used for model validation. An artificial neural network was used to predict from the demographic characteristics and medical history the prior risk that was then combined with biomarker values to determine the risk of PE and preterm PE with delivery at &lt;\u200937\u2009weeks' gestation. An additional network was trained without including race as input. Biomarkers included uterine artery pulsatility index (UtA\u2010PI), mean arterial blood pressure (MAP), placental growth factor (PlGF) and pregnancy\u2010associated plasma protein\u2010A. All markers were entered using raw values without conversion into standardized multiples of the median. The prediction accuracy was estimated using the area under the receiver\u2010operating\u2010characteristics curve (AUC). We further computed the detection rate at 10%, 20% and 40% false\u2010positive rates (FPR). The impact of taking aspirin was also added. Shapley values were calculated to evaluate the contribution of each parameter to the prediction of risk. We used a non\u2010parametric test to compare the expected AUC with the one obtained when we randomly scrambled the labels and kept the predictions. For the general prediction, we performed 10\u2009000 permutations of the labels. When the AUC was higher than the one obtained in all 10\u2009000 permutations, we reported a\n                      <jats:italic>P<\/jats:italic>\n                      \u2010value of &lt;\u20090.0001. For the race\u2010specific analysis, we performed 1000 permutations. When the AUC was higher than the AUC in permutations, we reported a\n                      <jats:italic>P<\/jats:italic>\n                      \u2010value of &lt;\u20090.001.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The detection rate for preterm PE\n                      <jats:italic>vs<\/jats:italic>\n                      no PE, at a 10% FPR, was 53.3% when screening by maternal factors only, and the corresponding AUC was 0.816; these increased to 75.3% and 0.909, respectively, with the addition of biomarkers into the model. Information on race was important for the prediction accuracy; when race was not used to train the model, at a 10% FPR, the detection rate of preterm PE\n                      <jats:italic>vs<\/jats:italic>\n                      no PE decreased to 34.5\u201345.5% (for different races) when screening by maternal factors only and to 55.0\u201362.1% when biomarkers were added. The major predictors of PE were high MAP and UtA\u2010PI, and low PlGF. The accuracy of prediction of all PE cases was lower than that for preterm PE. Aspirin use was recommended for cases who were at high risk of preterm PE. The AUC of all PE\n                      <jats:italic>vs<\/jats:italic>\n                      no PE was 0.770 when screening by maternal factors and 0.817 when the biomarkers were added; the respective detection rates, at a 10% FPR, were 41.3% and 52.9%.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Screening for PE using a non\u2010linear machine\u2010learning\u2010based approach does not require a population\u2010based normalization, and its performance is similar to that of logistic regression. Removing race information from the model reduces its prediction accuracy, especially for the non\u2010white populations when only maternal factors are considered. \u00a9 2022 International Society of Ultrasound in Obstetrics and Gynecology.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/uog.26105","type":"journal-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T13:59:50Z","timestamp":1669903190000},"page":"739-745","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Machine\u2010learning\u2010based prediction of pre\u2010eclampsia using first\u2010trimester maternal characteristics and biomarkers"],"prefix":"10.1002","volume":"60","author":[{"given":"Z.","family":"Ansbacher\u2010Feldman","sequence":"first","affiliation":[{"name":"Department of Mathematics Bar Ilan University  Ramat Gan Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5856-6072","authenticated-orcid":false,"given":"A.","family":"Syngelaki","sequence":"additional","affiliation":[{"name":"Fetal Medicine Research Institute King's College Hospital  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H.","family":"Meiri","sequence":"additional","affiliation":[{"name":"The ASPRE Consortium and TeleMarpe  Tel Aviv Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Cirkin","sequence":"additional","affiliation":[{"name":"Department of Mathematics Bar Ilan University  Ramat Gan Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K. H.","family":"Nicolaides","sequence":"additional","affiliation":[{"name":"Fetal Medicine Research Institute King's College Hospital  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Y.","family":"Louzoun","sequence":"additional","affiliation":[{"name":"Department of Mathematics Bar Ilan University  Ramat Gan Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,12,1]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.preghy.2021.09.008"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1097\/AOG.0000000000003891"},{"issue":"62","key":"e_1_2_8_4_1","first-page":"e1","article-title":"Competing risks model in screening for preeclampsia by maternal characteristics and medical history","volume":"213","author":"Wright D","year":"2015","journal-title":"Am J Obstet Gynecol"},{"issue":"103","key":"e_1_2_8_5_1","first-page":"e1","article-title":"Competing risks model in screening for preeclampsia by maternal factors and biomarkers at 11\u201013\u2009weeks gestation","volume":"214","author":"O'Gorman N","year":"2016","journal-title":"Am J Obstet Gynecol"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2019.11.1247"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1704559"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.14789"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.14783"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.14870"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.14811"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2018.e00938"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cca.2021.07.015"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/pd.6059"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-86320-0"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-020-09492-6"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.5157"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1159\/000335366"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"Zhang Zijun.Improved adam optimizer for deep neural networks. IEEE\/ACM 26th International Symposium on Quality of Service (IWQoS) 2018.","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.115.001593"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"e_1_2_8_22_1","first-page":"2242","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML 2019)","author":"Ghorbani A","year":"2019"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2017.11.561"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/ijgo.12802"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/uog.19112"},{"issue":"199","key":"e_1_2_8_26_1","first-page":"e1","article-title":"Predictive performance of the competing risk model in screening for preeclampsia","volume":"220","author":"Wright D","year":"2019","journal-title":"Am J Obstet Gynecol"}],"container-title":["Ultrasound in Obstetrics &amp; Gynecology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/uog.26105","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/uog.26105","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/uog.26105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T08:42:06Z","timestamp":1779093726000},"score":1,"resource":{"primary":{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/10.1002\/uog.26105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":25,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1002\/uog.26105"],"URL":"https:\/\/doi.org\/10.1002\/uog.26105","archive":["Portico"],"relation":{},"ISSN":["0960-7692","1469-0705"],"issn-type":[{"value":"0960-7692","type":"print"},{"value":"1469-0705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]},"assertion":[{"value":"2022-06-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}