{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T11:13:30Z","timestamp":1792494810891,"version":"4.5.0"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Ectopic pregnancy (EP) is well known for its critical maternal outcome. Early detection could make the difference between life and death in pregnancy. Our aim was to make a prompt diagnosis before the rupture occur. Thus, the predictive analytical models using both conventional statistics and machine learning (ML) methods were studied.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>A retrospective cohort study was conducted on 407 pregnancies with unknown location (PULs): 306 PULs for internal validation and 101 PULs for external validation, randomized with a nested cross-validation technique. Using a set of 22 study features based on clinical factors, serum marker and ultrasound findings from electronic medical records, analyzing with neural networks (NNs), decision tree (DT), support vector machines (SVMs), and a statistical logistic regression (LR). Diagnostic performances were compared with the area under the curve (ROC-AUC), including sensitivity and specificity for decisional use.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Comparing model performance (internal validation) to predict EP, LR ranked first, with a mean ROC-AUC \u00b1 SD of 0.879 \u00b1 0.010. In testing data (external validation), NNs ranked first, followed closely by LR, SVMs, and DT with average ROC-AUC \u00b1 SD of 0.898 \u00b1 0.027, 0.896 \u00b1 0.034, 0.882 \u00b1 0.029, and 0.856 \u00b1 0.033, respectively. For clinical aid, we report sensitivity of mean \u00b1 SD in LR: 90.20% \u00b1 3.49%; SVM: 89.79% \u00b1 3.66%; DT: 89.22% \u00b1 4.53%; and NNs: 86.92% \u00b1 3.24%, consecutively. However, specificity \u00b1 SD was ranked by NNs, followed by SVMs, LR, and DT, which were 82.02 \u00b1 8.34%, 80.37 \u00b1 5.15%, 79.65% \u00b1 6.01%, and 78.97% \u00b1 4.07%, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Both statistics and the ML model could achieve satisfactory predictions for EP. In model learning, the highest ranked model was LR, showing that EP prediction might possess linear or causal data pattern. However, in new testing data, NNs could overcome statistics. This highlights the potency of ML in solving complicated problems with various patterns, while overcoming generalization error of data.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2022.976829","type":"journal-article","created":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T06:12:51Z","timestamp":1663913571000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Predictive analytical model for ectopic pregnancy diagnosis: Statistics vs. machine learning"],"prefix":"10.3389","volume":"9","author":[{"given":"Ploywarong","family":"Rueangket","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristsanamon","family":"Rittiluechai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akara","family":"Prayote","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,9,23]]},"reference":[{"key":"B1","first-page":"1912","article-title":"Early pregnancy loss and ectopic pregnancy.","author":"Voedisch","year":"2019","journal-title":"Berek &amp; Novak\u2019s Gynecology."},{"key":"B2","first-page":"20","article-title":"Epidemiological study of ectopic pregnancy in lampang hospital. \u0e25\u0e33\u0e1b\u0e32\u0e07 \u0e40\u0e27\u0e0a \u0e2a\u0e32\u0e23","volume":"31","author":"Liampongsabhuddhi","year":"2010"},{"key":"B3","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1097\/01.AOG.0000120146.48098.f2","article-title":"Ectopic pregnancy in Africa: a population-based study.","volume":"103","author":"Leke","year":"2004","journal-title":"Obstet Gynecol."},{"key":"B4","article-title":"The Assessment of Emergency Obstetric Care (EMOC) in the Lower 5 Southern Provinces of Thailand [Internet]. Institute of Research and Development for Health of Southern","author":"Suetrakul","year":"2006"},{"key":"B5","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1097\/GRF.0b013e3182516d7b","article-title":"Ectopic pregnancy: history, incidence, epidemiology, and risk factors.","volume":"55","author":"Marion","year":"2012","journal-title":"Clin Obstet Gynecol."},{"key":"B6","author":"Drife","year":"2004","journal-title":"Why Mothers Die 2000\u20132002 \u2013 The Sixth Report of Confidential Enquiries into Maternal Deaths in the United Kingdom."},{"key":"B7","doi-asserted-by":"publisher","first-page":"141","DOI":"10.2147\/IJWH.S76837","article-title":"Ruptured tubal pregnancy: predictors of delays in seeking and obtaining care in a Nigerian population.","volume":"7","author":"Awoleke","year":"2015","journal-title":"Int J Womens Health."},{"key":"B8","year":"2020","journal-title":"The Diagnosis of Ectopic Pregnancy: an Independent Report [Internet]."},{"key":"B9","doi-asserted-by":"publisher","first-page":"m924","DOI":"10.1136\/bmj.m924","article-title":"Women are at serious risk of harm from late diagnosis of ectopic pregnancy.","volume":"368","author":"Thornton","year":"2020","journal-title":"BMJ."},{"key":"B10","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/0020-7292(82)90196-5","article-title":"Ectopic pregnancy early diagnosis limitations.","volume":"20","author":"Portuondo","year":"1982","journal-title":"Int J Gynaecol Obstet."},{"key":"B11","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/S0196-0644(96)70131-2","article-title":"Ectopic pregnancy: prospective study with improved diagnostic accuracy.","volume":"28","author":"Kaplan","year":"1996","journal-title":"Ann Emerg Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"e91","DOI":"10.1097\/AOG.0000000000002560","article-title":"Tubal ectopic pregnancy.","volume":"131","year":"2018","journal-title":"Obstet Gynecol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1080\/00016340802443822","article-title":"Why are some ectopic pregnancies characterized as pregnancies of unknown location at the initial transvaginal ultrasound examination?","volume":"87","author":"Kirk","year":"2008","journal-title":"Acta Obstet Gynecol Scand."},{"key":"B14","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1111\/j.1471-0528.2006.00924.x","article-title":"Failing pregnancies of unknown location: a prospective evaluation of the human chorionic gonadotrophin ratio.","volume":"113","author":"Condous","year":"2006","journal-title":"BJOG."},{"key":"B15","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1111\/j.1471-0528.2001.00031.x","article-title":"Expectant management of early pregnancies of unknown location: a prospective evaluation of methods to predict spontaneous resolution of pregnancy.","volume":"108","author":"Banerjee","year":"2001","journal-title":"BJOG."},{"key":"B16","first-page":"258","article-title":"Suspected ectopic pregnancy: expectant management in patients with negative sonographic findings and low serum hCG concentrations.","volume":"1","author":"Hajenius","year":"1995","journal-title":"Early Pregnancy."},{"key":"B17","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1097\/01.AOG.0000142712.80407.fd","article-title":"Decline of serum human chorionic gonadotropin and spontaneous complete abortion: defining the normal curve.","volume":"104","author":"Barnhart","year":"2004","journal-title":"Obstet Gynecol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/0735-6757(90)90154-R","article-title":"Ectopic pregnancy: ten common pitfalls in diagnosis.","volume":"8","author":"Abbott","year":"1990","journal-title":"Am J Emerg Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/S0196-0644(99)70160-5","article-title":"History and physical examination to estimate the risk of ectopic pregnancy: validation of a clinical prediction model.","volume":"34","author":"Buckley","year":"1999","journal-title":"Ann Emerg Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.fertnstert.2012.09.012","article-title":"Validation of a clinical risk scoring system, based solely on clinical presentation, for the management of pregnancy of unknown location.","volume":"99","author":"Barnhart","year":"2013","journal-title":"Fertil Steril."},{"key":"B21","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1111\/1471-0528.15442","article-title":"Diagnostic protocols for the management of pregnancy of unknown location: a systematic review and meta-analysis.","volume":"126","author":"Bobdiwala","year":"2019","journal-title":"BJOG."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.1093\/humrep\/deh341","article-title":"The use of a new logistic regression model for predicting the outcome of pregnancies of unknown location.","volume":"19","author":"Condous","year":"2004","journal-title":"Hum Reprod."},{"key":"B23","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1002\/uog.4015","article-title":"Prediction of ectopic pregnancy in women with a pregnancy of unknown location.","volume":"29","author":"Condous","year":"2007","journal-title":"Ultrasound Obstet Gynecol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1111\/j.1553-2712.1998.tb02711.x","article-title":"Subclassification of indeterminate pelvic ultrasonograms: stratifying the risk of ectopic pregnancy.","volume":"5","author":"Dart","year":"1998","journal-title":"Acad Emerg Med."},{"key":"B25","first-page":"870","author":"Mitchell","year":"1997","journal-title":"Machine Learning."},{"key":"B26","doi-asserted-by":"publisher","first-page":"646258","DOI":"10.3389\/fmed.2021.646258","article-title":"Predictive analytic model for diagnosis of ectopic pregnancy.","volume":"8","author":"Rueangket","year":"2021","journal-title":"Front Med."},{"key":"B27","author":"Rollins","year":"2015","journal-title":"Why We Need a Methodology for Data Science [Internet]."},{"key":"B28","doi-asserted-by":"publisher","first-page":"180304219","DOI":"10.5121\/csit.2018.80401","article-title":"Data science methodology for cybersecurity projects.","author":"Foroughi","year":"2018","journal-title":"arXiv."},{"key":"B29","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences.","volume":"20","author":"Cox","year":"1958","journal-title":"J R Stat Soc."},{"key":"B30","doi-asserted-by":"publisher","first-page":"229","DOI":"10.17535\/crorr.2016.0016","article-title":"Predicting company growth using logistic regression and neural networks.","volume":"7","author":"Zeki\u0107-Su\u0161ac","year":"2016","journal-title":"Croat Oper Res Rev."},{"key":"B31","first-page":"85","article-title":"Chapter 4\u2013Core technologies: machine learning and natural language processing.","author":"Nadkarni","year":"2016","journal-title":"Clinical Research Computing"},{"key":"B32","first-page":"774","article-title":"Pattern recognition using generalized portrait method.","volume":"24","author":"Vapnik","year":"1963","journal-title":"Autom Remote Control."},{"key":"B33","author":"Fan","year":"2004","journal-title":"On the Optimality of Probability Estimation by Random Decision Trees."},{"key":"B34","year":"2016","journal-title":"RapidMiner Named a Leader in the 2016 Gartner Magic Quadrant for Advanced Analytics Platforms."},{"key":"B35","doi-asserted-by":"publisher","first-page":"30","DOI":"10.14445\/22315381\/IJETT-V68I8P206S","article-title":"Experimental evaluation of open source data mining tools.","volume":"68","author":"Hemlata","year":"2019","journal-title":"Int J Eng Technol."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1201\/9780429492259","author":"Van Buuren","year":"2018","journal-title":"Flexible Imputation of Missing Data."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24834-9_49","article-title":"Early Alzheimer\u2019s disease prediction in machine learning setup: empirical analysis with missing value computation.","author":"Minhas","year":"2015","journal-title":"Proceedings of the International Conference on Intelligent Data Engineering and Automated Learning."},{"key":"B38","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10115-011-0424-2","article-title":"On the choice of the best imputation methods for missing values considering three groups of classification methods.","volume":"32","author":"Luengo","year":"2012","journal-title":"Knowl Inf Syst."},{"key":"B39","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.tjem.2018.08.001","article-title":"User\u2019s guide to correlation coefficients.","volume":"18","author":"Akoglu","year":"2018","journal-title":"Turk J Emerg Med."},{"key":"B40","doi-asserted-by":"publisher","first-page":"115222","DOI":"10.1016\/j.eswa.2021.115222","article-title":"Nested cross-validation when selecting classifiers is overzealous for most practical applications.","volume":"182","author":"Wainer","year":"2021","journal-title":"Expert Syst Appl."},{"key":"B41","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis.","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit Lett."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1093\/oxfordjournals.humrep.a136123","article-title":"The expectant management of early pregnancies of uncertain site.","volume":"10","author":"Hahlin","year":"1995","journal-title":"Hum Reprod."},{"key":"B43","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1046\/j.1469-0705.1999.14040231.x","article-title":"The expectant management of women with early pregnancy of unknown location.","volume":"14","author":"Banerjee","year":"1999","journal-title":"Ultrasound Obstet Gynecol."},{"key":"B44","first-page":"27","article-title":"Prediction of ectopic pregnancy in early pregnancy of unknown location.","volume":"91","author":"Malek-mellouli","year":"2013","journal-title":"Tunis Med."},{"key":"B45","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.ijar.2006.01.004","article-title":"Analysis of interpretability-accuracy tradeoff of fuzzy systems by multiobjective fuzzy genetics-based machine learning.","volume":"44","author":"Ishibuchi","year":"2007","journal-title":"Int J Approx Reason."},{"key":"B46","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1055\/s-0038-1676123","article-title":"Pregnancy of unknown location: the value of frozen section analysis and its relation to Beta-hCG Levels and endometrial thickness.","volume":"41","author":"Odeh","year":"2019","journal-title":"Rev Bras Ginecol Obstet."},{"key":"B47","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1016\/S0015-0282(98)00278-7","article-title":"Serum human chorionic gonadotropin measurement in the diagnosis of ectopic pregnancy when transvaginal sonography is inconclusive.","volume":"70","author":"Mol","year":"1998","journal-title":"Fertil Steril."},{"key":"B48","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.asoc.2015.08.048","article-title":"Data selection based on decision tree for SVM classification on large data sets.","volume":"37","author":"Cervantes","year":"2015","journal-title":"Appl Soft Comput."},{"key":"B49","doi-asserted-by":"publisher","first-page":"307","DOI":"10.3389\/fpubh.2017.00307","article-title":"Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice.","volume":"5","author":"Trevethan","year":"2017","journal-title":"Front Public Health."},{"key":"B50","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.4102\/phcfm.v10i1.1757","article-title":"An audit of the management of ectopic pregnancies in a district hospital, Gauteng, South Africa.","volume":"10","author":"Nzaumvila","year":"2018","journal-title":"Afr J Prim Health Care Fam Med."},{"key":"B51","author":"Alexander","year":"2015","journal-title":"Assessment of Diagnostic and Screening Tests."},{"key":"B52","author":"Linoff","year":"2011","journal-title":"Data Mining Techniques: for Marketing, Sales, and Customer Relationship Management."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.976829\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T06:13:06Z","timestamp":1663913586000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.976829\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":52,"alternative-id":["10.3389\/fmed.2022.976829"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2022.976829","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,23]]},"article-number":"976829"}}