{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T13:31:18Z","timestamp":1786627878244,"version":"build-2736575974"},"reference-count":19,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":19,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Birth Defects Research"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early prediction of pregnancy syndromes such as preeclampsia, gestational diabetes mellitus (GDM), and preterm birth is critical for improving maternal and fetal outcomes. Traditional risk assessment tools rely primarily on structured clinical data and often fail to fully utilize the rich unstructured textual information contained in electronic health records (EHRs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and evaluate an Adaptive Penguin\u2013Improved Long Short\u2010Term Memory (AP\u2010ILSTM) model that integrates natural language processing (NLP) of clinical narratives with structured longitudinal data for predicting the risk of preeclampsia, GDM, and preterm birth.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective observational study used de\u2010identified EHR data from 1248 consecutive pregnancies at a single regional hospital in China between April 2024 and April 2025. Structured clinical variables and unstructured free\u2010text clinical notes were preprocessed using standard NLP techniques, including tokenization, TF\u2010IDF weighting, and word embeddings. An Improved Long Short\u2010Term Memory (ILSTM) network with dropout regularization was optimized using the Adaptive Penguin algorithm with Gaussian exploration. The dataset was stratified into training (70%), validation (15%), and independent test (15%) sets. Model performance was assessed using accuracy, sensitivity (recall), positive predictive value (precision), F1\u2010score, specificity, negative predictive value, ROC\u2010AUC, and mean absolute error, and compared against baseline machine learning models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On the independent test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009188), the AP\u2010ILSTM model achieved an accuracy of 98.85%, sensitivity of 98.69%, positive predictive value of 98.75%, F1\u2010score of 98.72%, and ROC\u2010AUC of 0.993, with a mean absolute error of 4.05. It outperformed all baseline classifiers (XGBoost, CatBoost, KNN) and regression models. Clinical narrative embeddings ranked as the second most important predictor after blood pressure trends.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The AP\u2010ILSTM model, by effectively combining structured data with NLP\u2010derived features from clinical narratives and employing adaptive optimization, demonstrated superior performance for early multi\u2010syndrome pregnancy risk prediction. This multimodal temporal approach shows strong potential to support clinical decision\u2010making, although external validation and prospective implementation studies are required before clinical adoption.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/bdr2.70095","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T03:08:18Z","timestamp":1784603298000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and Evaluation of an Adaptive Penguin\u2013Improved\n                    <scp>LSTM<\/scp>\n                    Model Integrating Natural Language Processing for Early Prediction of Pregnancy Syndrome Risks"],"prefix":"10.1002","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1706-8709","authenticated-orcid":false,"given":"Yanqi","family":"Wu","sequence":"first","affiliation":[{"name":"Electrical Engineering Department Eindhoven University of Technology  Eindhoven the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"issue":"9","key":"e_1_2_13_2_1","article-title":"Artificial Intelligence for Early Detection of Preeclampsia and Gestational Diabetes Mellitus: A Systematic Review of Diagnostic Performance","volume":"17","author":"Alfaki Ahmed S. A.","year":"2025","journal-title":"Cureus"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2026.1841706"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108979"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14196974"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12889-025-22705-4"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-026-03395-3"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-07885-8"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-022-04594-2"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13300-026-01880-6"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.880034"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/jpm13060975"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108685"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1161\/ATVBAHA.124.321673"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-026-08856-1"},{"issue":"4","key":"e_1_2_13_17_1","first-page":"70","article-title":"Deep Learning Based Risk Level Prediction Model for Maternal Mortality","volume":"13","author":"Sahithi P.","year":"2023","journal-title":"International Journal of Engineering Research and Applications"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12978-025-02048-4"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44294-026-00138-7"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.preghy.2024.101127"}],"container-title":["Birth Defects Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bdr2.70095","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/bdr2.70095","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bdr2.70095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T12:42:40Z","timestamp":1786624960000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/bdr2.70095"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":19,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/bdr2.70095"],"URL":"https:\/\/doi.org\/10.1002\/bdr2.70095","archive":["Portico"],"relation":{},"ISSN":["2472-1727","2472-1727"],"issn-type":[{"value":"2472-1727","type":"print"},{"value":"2472-1727","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"2026-04-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70095"}}