{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T16:50:39Z","timestamp":1792342239575,"version":"4.4.0"},"reference-count":93,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T00:00:00Z","timestamp":1649203200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000124","name":"Office of Research on Women\u2019s Health","doi-asserted-by":"publisher","award":["NIH K12HD043441"],"award-info":[{"award-number":["NIH K12HD043441"]}],"id":[{"id":"10.13039\/100000124","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Vice President for Research and Partnerships of the University of Oklahoma"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Preeclampsia (PE) is a hypertensive complication affecting 8-10% of US pregnancies annually. While there is no cure for PE, aspirin may reduce complications for those at high risk for PE. Furthermore, PE disproportionately affects racial minorities, with a higher burden of morbidity and mortality. Previous studies have shown early prediction of PE would allow for prevention. We approached the prediction of PE using a new method based on a cost-sensitive deep neural network (CSDNN) by considering the severe imbalance and sparse nature of the data, as well as racial disparities. We validated our model using large extant rich data sources that represent a diverse cohort of minority populations in the US. These include Texas Public Use Data Files (PUDF), Oklahoma PUDF, and the Magee Obstetric Medical and Infant (MOMI) databases. We identified the most influential clinical and demographic features (predictor variables) relevant to PE for both general populations and smaller racial groups. We also investigated the effectiveness of multiple network architectures using three hyperparameter optimization algorithms: Bayesian optimization, Hyperband, and random search. Our proposed models equipped with focal loss function yield superior and reliable prediction performance compared with the state-of-the-art techniques with an average area under the curve (AUC) of 66.3% and 63.5% for the Texas and Oklahoma PUDF respectively, while the CSDNN model with weighted cross-entropy loss function outperforms with an AUC of 76.5% for the MOMI data. Furthermore, our CSDNN model equipped with focal loss function leads to an AUC of 66.7% for Texas African American and 57.1% for Native American. The best results are obtained with 62.3% AUC with CSDNN with weighted cross-entropy loss function for Oklahoma African American, 58% AUC with DNN and balanced batch for Oklahoma Native American, and 72.4% AUC using either CSDNN with weighted cross-entropy loss function or CSDNN with focal loss with balanced batch method for MOMI African American dataset. Our results provide the first evidence of the predictive power of clinical databases for PE prediction among minority populations.<\/jats:p>","DOI":"10.1371\/journal.pone.0266042","type":"journal-article","created":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T17:47:26Z","timestamp":1649267246000},"page":"e0266042","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":30,"title":["An imbalance-aware deep neural network for early prediction of preeclampsia"],"prefix":"10.1371","volume":"17","author":[{"given":"Rachel","family":"Bennett","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuber D.","family":"Mulla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavan","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alisse","family":"Hauspurg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8052-9876","authenticated-orcid":true,"given":"Talayeh","family":"Razzaghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,4,6]]},"reference":[{"issue":"1","key":"pone.0266042.ref001","first-page":"e1","article-title":"ACOG practice bulletin no. 202: gestational hypertension and preeclampsia","volume":"133","author":"American College of Obstetricians and Gynecologists","year":"2019","journal-title":"Obstet Gynecol"},{"issue":"7627","key":"pone.0266042.ref002","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1136\/bmj.39335.385301.BE","article-title":"Pre-eclampsia and risk of cardiovascular disease and cancer in later life: systematic review and meta-analysis","volume":"335","author":"L Bellamy","year":"2007","journal-title":"Bmj"},{"key":"pone.0266042.ref003","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.preghy.2018.06.013","article-title":"Prenatal exposure to preeclampsia as an independent risk factor for long-term cardiovascular morbidity of the offspring","volume":"13","author":"KN Sacks","year":"2018","journal-title":"Pregnancy hypertension"},{"issue":"2","key":"pone.0266042.ref004","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1097\/AOG.0b013e3181e9322a","article-title":"Prevention of preeclampsia and intrauterine growth restriction with aspirin started in early pregnancy: a meta-analysis","volume":"116","author":"E Bujold","year":"2010","journal-title":"Obstetrics & Gynecology"},{"issue":"3","key":"pone.0266042.ref005","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1161\/HYPERTENSIONAHA.114.03578","article-title":"Early pregnancy prediction of preeclampsia in nulliparous women, combining clinical risk and biomarkers: the Screening for Pregnancy Endpoints (SCOPE) international cohort study","volume":"64","author":"LC Kenny","year":"2014","journal-title":"Hypertension"},{"issue":"11","key":"pone.0266042.ref006","doi-asserted-by":"crossref","first-page":"e0225716","DOI":"10.1371\/journal.pone.0225716","article-title":"Clinical risk assessment in early pregnancy for preeclampsia in nulliparous women: A population based cohort study","volume":"14","author":"A Sandstr\u00f6m","year":"2019","journal-title":"PloS one"},{"key":"pone.0266042.ref007","doi-asserted-by":"crossref","unstructured":"Moreira MW, Rodrigues JJ, Oliveira AM, Saleem K, Neto AJ. Predicting hypertensive disorders in high-risk pregnancy using the random forest approach. In2017 IEEE International Conference on Communications (ICC) 2017 May 21 (pp. 1-5). IEEE.","DOI":"10.1109\/ICC.2017.7996964"},{"key":"pone.0266042.ref008","doi-asserted-by":"crossref","first-page":"102710","DOI":"10.1016\/j.ebiom.2020.102710","article-title":"Artificial intelligence-assisted prediction of preeclampsia: Development and external validation of a nationwide health insurance dataset of the BPJS Kesehatan in Indonesia","volume":"54","author":"H Sufriyana","year":"2020","journal-title":"EBioMedicine"},{"issue":"1","key":"pone.0266042.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-8-25","article-title":"Bias in random forest variable importance measures: Illustrations, sources and a solution","volume":"8","author":"C Strobl","year":"2007","journal-title":"BMC bioinformatics"},{"issue":"2","key":"pone.0266042.ref010","doi-asserted-by":"crossref","first-page":"100100","DOI":"10.1016\/j.ajogmf.2020.100100","article-title":"Early prediction of preeclampsia via machine learning","volume":"2","author":"I Mari\u0107","year":"2020","journal-title":"American Journal of Obstetrics & Gynecology MFM"},{"key":"pone.0266042.ref011","article-title":"Does race or ethnicity play a role in the origin, pathophysiology, and outcomes of preeclampsia? An expert review of the literature","author":"JD Johnson","year":"2020","journal-title":"American journal of obstetrics and gynecology"},{"issue":"5","key":"pone.0266042.ref012","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1097\/AOG.0000000000002937","article-title":"Racial and ethnic disparities in the incidence of severe maternal morbidity in the United States, 2012\u20132015","volume":"132","author":"LK Admon","year":"2018","journal-title":"Obstetrics & Gynecology"},{"issue":"4","key":"pone.0266042.ref013","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1097\/AOG.0000000000003167","article-title":"A nudge toward universal aspirin for preeclampsia prevention","volume":"133","author":"NK Ayala","year":"2019","journal-title":"Obstetrics & Gynecology"},{"issue":"35","key":"pone.0266042.ref014","doi-asserted-by":"crossref","first-page":"762","DOI":"10.15585\/mmwr.mm6835a3","article-title":"Racial\/ethnic disparities in pregnancy-related deaths\u2014United States, 2007\u20132016","volume":"68","author":"EE Petersen","year":"2019","journal-title":"Morbidity and Mortality Weekly Report"},{"issue":"1","key":"pone.0266042.ref015","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.ajog.2015.08.019","article-title":"Black-white differences in severe maternal morbidity and site of care","volume":"214","author":"EA Howell","year":"2016","journal-title":"American journal of obstetrics and gynecology"},{"key":"pone.0266042.ref016","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.annepidem.2019.02.007","article-title":"Racial and ethnic disparities in severe maternal morbidity prevalence and trends","volume":"33","author":"SA Leonard","year":"2019","journal-title":"Annals of epidemiology"},{"issue":"11","key":"pone.0266042.ref017","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1089\/jwh.2014.4749","article-title":"Differences in preeclampsia rates between African American and Caucasian women: trends from the National Hospital Discharge Survey","volume":"23","author":"K Breathett","year":"2014","journal-title":"Journal of women\u2019s health"},{"issue":"4","key":"pone.0266042.ref018","doi-asserted-by":"crossref","first-page":"506","DOI":"10.3109\/10641955.2015.1090581","article-title":"Racial disparities in comorbidities, complications, and maternal and fetal outcomes in women with preeclampsia\/eclampsia","volume":"34","author":"S Shahul","year":"2015","journal-title":"Hypertension in pregnancy"},{"key":"pone.0266042.ref019","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1053\/j.semperi.2017.04.001","article-title":"Epidemiology of racial\/ethnic disparities in severe maternal morbidity and mortality","volume":"Vol. 41","author":"SJ Somer","year":"2017","journal-title":"InSeminars in perinatology"},{"issue":"2","key":"pone.0266042.ref020","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1097\/OGX.0000000000000747","article-title":"Preeclampsia among African American pregnant women: an update on prevalence, complications, etiology, and biomarkers","volume":"75","author":"M Zhang","year":"2020","journal-title":"Obstetrical & gynecological survey"},{"issue":"11","key":"pone.0266042.ref021","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1007\/s10995-016-2126-6","article-title":"Pre-eclampsia in American Indians\/Alaska natives and whites: the significance of body mass index","volume":"20","author":"A Zamora-Kapoor","year":"2016","journal-title":"Maternal and child health journal"},{"issue":"2","key":"pone.0266042.ref022","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1089\/jwh.2020.8890","article-title":"Maternal mortality among American Indian\/Alaska Native women: A scoping review","volume":"30","author":"JL Heck","year":"2021","journal-title":"Journal of Women\u2019s Health"},{"key":"pone.0266042.ref023","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/978-1-4614-7548-4_12","volume-title":"Ethnic Differences in Fertility and Assisted Reproduction","author":"R Menon","year":"2013"},{"issue":"1","key":"pone.0266042.ref024","doi-asserted-by":"crossref","first-page":"54","DOI":"10.3109\/10641950902777754","article-title":"Risk factors for a prolonged length of stay in women hospitalized for preeclampsia in Texas","volume":"29","author":"ZD Mulla","year":"2010","journal-title":"Hypertension in pregnancy"},{"issue":"13","key":"pone.0266042.ref025","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1161\/CIRCULATIONAHA.118.038080","article-title":"Preeclampsia and cardiovascular disease in a large UK pregnancy cohort of linked electronic health records: a CALIBER study","volume":"140","author":"LJ Leon","year":"2019","journal-title":"Circulation"},{"issue":"2","key":"pone.0266042.ref026","first-page":"e003497","article-title":"Preeclampsia and future cardiovascular health: a systematic review and meta-analysis","volume":"10","author":"P Wu","year":"2017","journal-title":"Circulation: Cardiovascular Quality and Outcomes"},{"issue":"3","key":"pone.0266042.ref027","doi-asserted-by":"crossref","first-page":"238","DOI":"10.2174\/1573403X11666141122220003","article-title":"Disparities in cardiovascular disease risk in the United States","volume":"11","author":"G Graham","year":"2015","journal-title":"Current cardiology reviews"},{"key":"pone.0266042.ref028","doi-asserted-by":"crossref","first-page":"56","DOI":"10.2307\/2648213","article-title":"Psychosocial factors and the timing of prenatal care among women in New Jersey\u2019s HealthStart program","author":"DL Pagnini","year":"2000","journal-title":"Family planning perspectives"},{"key":"pone.0266042.ref029","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1016\/j.egyr.2021.12.012","article-title":"A new predictive energy management system: Deep learned type-2 fuzzy system based on singular value decommission","volume":"8","author":"Y Cao","year":"2022","journal-title":"Energy Reports"},{"issue":"21","key":"pone.0266042.ref030","doi-asserted-by":"crossref","first-page":"10392","DOI":"10.3390\/app112110392","article-title":"A New General Type-2 Fuzzy Predictive Scheme for PID Tuning","volume":"11","author":"J Tavoosi","year":"2021","journal-title":"Applied Sciences"},{"issue":"9","key":"pone.0266042.ref031","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"H He","year":"2009","journal-title":"IEEE Transactions on knowledge and data engineering"},{"issue":"1","key":"pone.0266042.ref032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1007730.1007733","article-title":"Special issue on learning from imbalanced data sets","volume":"6","author":"NV Chawla","year":"2004","journal-title":"ACM SIGKDD explorations newsletter"},{"key":"pone.0266042.ref033","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","article-title":"Learning from class-imbalanced data: Review of methods and applications","volume":"73","author":"G Haixiang","year":"2017","journal-title":"Expert systems with applications"},{"issue":"1","key":"pone.0266042.ref034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10479-019-03156-8","article-title":"Predictive models for bariatric surgery risks with imbalanced medical datasets","volume":"280","author":"T Razzaghi","year":"2019","journal-title":"Annals of Operations Research"},{"issue":"5","key":"pone.0266042.ref035","doi-asserted-by":"crossref","first-page":"e0155119","DOI":"10.1371\/journal.pone.0155119","article-title":"Multilevel weighted support vector machine for classification on healthcare data with missing values","volume":"11","author":"T Razzaghi","year":"2016","journal-title":"PloS one"},{"key":"pone.0266042.ref036","volume-title":"Deep learning","author":"I Goodfellow","year":"2016"},{"key":"pone.0266042.ref037","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"J Schmidhuber","year":"2015","journal-title":"Neural networks"},{"issue":"1","key":"pone.0266042.ref038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-014-0007-7","article-title":"Deep learning applications and challenges in big data analytics","volume":"2","author":"MM Najafabadi","year":"2015","journal-title":"Journal of big data"},{"key":"pone.0266042.ref039","doi-asserted-by":"crossref","DOI":"10.3389\/fninf.2021.667375","article-title":"Medical image interpolation using recurrent type-2 fuzzy neural network","volume":"15","author":"J Tavoosi","year":"2021","journal-title":"Frontiers in Neuroinformatics"},{"issue":"14","key":"pone.0266042.ref040","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.1080\/00207721.2020.1799257","article-title":"Consensus tracking of multi-agent systems using constrained neural-optimiser-based sliding mode control","volume":"51","author":"R Rahmani","year":"2020","journal-title":"International Journal of Systems Science"},{"key":"pone.0266042.ref041","doi-asserted-by":"crossref","first-page":"113275","DOI":"10.1016\/j.eswa.2020.113275","article-title":"A cost-sensitive convolution neural network learning for control chart pattern recognition","volume":"150","author":"D Fuqua","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"pone.0266042.ref042","article-title":"Integrated Learning: Screening Optimal Biomarkers for Identifying Preeclampsia in Placental mRNA Samples","volume":"2021","author":"R Guo","year":"2021","journal-title":"Computational and Mathematical Methods in Medicine"},{"issue":"5","key":"pone.0266042.ref043","doi-asserted-by":"crossref","first-page":"e15411","DOI":"10.2196\/15411","article-title":"Prediction of preeclampsia and intrauterine growth restriction: development of machine learning models on a prospective cohort","volume":"8","author":"H Sufriyana","year":"2020","journal-title":"JMIR medical informatics"},{"issue":"5","key":"pone.0266042.ref044","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1002\/uog.12264","article-title":"Prediction of early and late pre-eclampsia from maternal characteristics, uterine artery Doppler and markers of vasculogenesis during first trimester of pregnancy","volume":"41","author":"M Parra-Cordero","year":"2013","journal-title":"Ultrasound in Obstetrics & Gynecology"},{"issue":"8","key":"pone.0266042.ref045","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1002\/pd.4113","article-title":"First trimester prediction of early onset preeclampsia using demographic, clinical, and sonographic data: a cohort study","volume":"33","author":"J Caradeux","year":"2013","journal-title":"Prenatal diagnosis"},{"key":"pone.0266042.ref046","article-title":"Value of Ultrasonic Image Features in Diagnosis of Perinatal Outcomes of Severe Preeclampsia on account of Deep Learning Algorithm","volume":"2022","author":"Q Wang","year":"2022","journal-title":"Computational and Mathematical Methods in Medicine"},{"key":"pone.0266042.ref047","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision 2017 (pp. 2980-2988).","DOI":"10.1109\/ICCV.2017.324"},{"key":"pone.0266042.ref048","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.preghy.2021.10.006","article-title":"Novel electronic health records applied for prediction of pre-eclampsia: Machine-learning algorithms","volume":"26","author":"YX Li","year":"2021","journal-title":"Pregnancy Hypertension"},{"issue":"11","key":"pone.0266042.ref049","first-page":"959","article-title":"Predicting preeclampsia and related risk factors using data mining approaches: A cross-sectional study","volume":"19","author":"Z Manoochehri","year":"2021","journal-title":"International Journal of Reproductive BioMedicine"},{"issue":"4","key":"pone.0266042.ref050","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"WS McCulloch","year":"1943","journal-title":"The bulletin of mathematical biophysics"},{"issue":"14-15","key":"pone.0266042.ref051","doi-asserted-by":"crossref","first-page":"2627","DOI":"10.1016\/S1352-2310(97)00447-0","article-title":"Artificial neural networks (the multilayer perceptron)\u2014a review of applications in the atmospheric sciences","volume":"32","author":"MW Gardner","year":"1998","journal-title":"Atmospheric environment"},{"issue":"12","key":"pone.0266042.ref052","first-page":"310","article-title":"Activation functions in neural networks","volume":"6","author":"S Sharma","year":"2017","journal-title":"towards data science"},{"key":"pone.0266042.ref053","doi-asserted-by":"crossref","unstructured":"Wanriko S, Hnoohom N, Wongpatikaseree K, Jitpattanakul A, Musigavong O. Risk assessment of pregnancy-induced hypertension using a machine learning approach. In2021 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering 2021 Mar 3 (pp. 233-237). IEEE.","DOI":"10.1109\/ECTIDAMTNCON51128.2021.9425764"},{"issue":"3","key":"pone.0266042.ref054","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.ajog.2012.12.016","article-title":"Performance of a first-trimester screening of preeclampsia in a routine care low-risk setting","volume":"208","author":"E Scazzocchio","year":"2013","journal-title":"American journal of obstetrics and gynecology"},{"key":"pone.0266042.ref055","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.d1875","article-title":"Clinical risk prediction for pre-eclampsia in nulliparous women: development of model in international prospective cohort","volume":"342","author":"RA North","year":"2011","journal-title":"Bmj"},{"issue":"8","key":"pone.0266042.ref056","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1016\/j.placenta.2011.05.006","article-title":"First-trimester placental protein 13, PAPP-A, uterine artery Doppler and maternal characteristics in the prediction of pre-eclampsia","volume":"32","author":"AO Odibo","year":"2011","journal-title":"Placenta"},{"issue":"2","key":"pone.0266042.ref057","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.ajog.2004.12.014","article-title":"An integrated model for the prediction of preeclampsia using maternal factors and uterine artery Doppler velocimetry in unselected low-risk women","volume":"193","author":"Fetal Medicine Foundation Second Trimester Screening Group","year":"2005","journal-title":"American journal of obstetrics and gynecology"},{"key":"pone.0266042.ref058","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"A Krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"pone.0266042.ref059","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. InProceedings of the IEEE international conference on computer vision 2015 (pp. 1026-1034).","DOI":"10.1109\/ICCV.2015.123"},{"issue":"11","key":"pone.0266042.ref060","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Y LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"pone.0266042.ref061","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Bahdanau D, Bengio Y. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259. 2014 Sep 3.","DOI":"10.3115\/v1\/W14-4012"},{"key":"pone.0266042.ref062","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. 2014 Sep 1."},{"key":"pone.0266042.ref063","doi-asserted-by":"crossref","unstructured":"Graves A, Mohamed AR, Hinton G. Speech recognition with deep recurrent neural networks. In2013 IEEE international conference on acoustics, speech and signal processing 2013 May 26 (pp. 6645-6649). Ieee.","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"10","key":"pone.0266042.ref064","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","article-title":"Convolutional neural networks for speech recognition","volume":"22","author":"O Abdel-Hamid","year":"2014","journal-title":"IEEE\/ACM Transactions on audio, speech, and language processing"},{"issue":"2","key":"pone.0266042.ref065","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1007\/s00521-004-0413-4","article-title":"An ensemble of neural networks for weather forecasting","volume":"13","author":"I Maqsood","year":"2004","journal-title":"Neural Computing & Applications"},{"issue":"1","key":"pone.0266042.ref066","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1016\/j.eswa.2012.07.051","article-title":"Credit scoring models for the microfinance industry using neural networks: Evidence from Peru","volume":"40","author":"A Blanco","year":"2013","journal-title":"Expert Systems with applications"},{"key":"pone.0266042.ref067","doi-asserted-by":"crossref","unstructured":"Joshi DM, Rana NK, Misra V. Classification of brain cancer using artificial neural network. In2010 2nd international conference on electronic computer technology 2010 May 7 (pp. 112-116). IEEE.","DOI":"10.1109\/ICECTECH.2010.5479975"},{"issue":"2","key":"pone.0266042.ref068","doi-asserted-by":"crossref","first-page":"3465","DOI":"10.1016\/j.eswa.2008.02.064","article-title":"An expert system for detection of breast cancer based on association rules and neural network","volume":"36","author":"M Karabatak","year":"2009","journal-title":"Expert systems with Applications"},{"key":"pone.0266042.ref069","doi-asserted-by":"crossref","unstructured":"Yavuz E, Eyupoglu C, Sanver U, Yazici R. An ensemble of neural networks for breast cancer diagnosis. In2017 International Conference on Computer Science and Engineering (UBMK) 2017 Oct 5 (pp. 538-543). IEEE.","DOI":"10.1109\/UBMK.2017.8093456"},{"issue":"6088","key":"pone.0266042.ref070","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"DE Rumelhart","year":"1986","journal-title":"nature"},{"key":"pone.0266042.ref071","unstructured":"Ruder S. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747. 2016 Sep 15."},{"key":"pone.0266042.ref072","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014 Dec 22."},{"key":"pone.0266042.ref073","unstructured":"Dozat T. Incorporating nesterov momentum into adam."},{"key":"pone.0266042.ref074","unstructured":"Tieleman T, Hinton G. Rmsprop: Divide the gradient by a running average of its recent magnitude. coursera: Neural networks for machine learning. COURSERA Neural Networks Mach. Learn. 2012."},{"key":"pone.0266042.ref075","unstructured":"Yang J, Nguyen MN, San PP, Li XL, Krishnaswamy S. Deep convolutional neural networks on multichannel time series for human activity recognition. InTwenty-fourth international joint conference on artificial intelligence 2015 Jun 27."},{"issue":"1","key":"pone.0266042.ref076","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-018-0151-6","article-title":"A survey on addressing high-class imbalance in big data","volume":"5","author":"JL Leevy","year":"2018","journal-title":"Journal of Big Data"},{"key":"pone.0266042.ref077","unstructured":"Kukar M, Kononenko I. Cost-sensitive learning with neural networks. InECAI 1998 Aug 23 (Vol. 15, No. 27, pp. 88-94)."},{"issue":"1","key":"pone.0266042.ref078","first-page":"559","article-title":"Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"G Lema\u00eetre","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"pone.0266042.ref079","unstructured":"Liu H, Setiono R. Chi2: Feature selection and discretization of numeric attributes. InProceedings of 7th IEEE International Conference on Tools with Artificial Intelligence 1995 Nov 5 (pp. 388-391). IEEE."},{"key":"pone.0266042.ref080","unstructured":"Texas Department of Health and Human Services. TEXAS HOSPITAL INPATIENT DISCHARGE PUBLIC USE DATA FILE (PUDF): 2016. Center for Health Statistics. Texas Health Care Information Collection. [Online]. Available from: https:\/\/www.dshs.texas.gov\/thcic\/hospitals\/DataDictionary4Q2016.pdf."},{"key":"pone.0266042.ref081","unstructured":"Texas Hospital Inpatient Public Use Data File 2013. Texas Department of State Health Services, Center for Health Statistics, Texas Health Care Information Collection, Austin, TX. 2020."},{"key":"pone.0266042.ref082","unstructured":"Department of State Health Services Map of Border Area. Accessed: 2020-10-30."},{"key":"pone.0266042.ref083","unstructured":"World Health Organization. International Statistical Classification of Diseases and Related Health Problems: Alphabetical index. World Health Organization; 2004."},{"key":"pone.0266042.ref084","first-page":"1","article-title":"mice: Multivariate imputation by chained equations in R","volume":"45","author":"S Van Buuren","year":"2011","journal-title":"Journal of statistical software"},{"issue":"Jun","key":"pone.0266042.ref085","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"ME Tipping","year":"2001","journal-title":"Journal of machine learning research"},{"key":"pone.0266042.ref086","unstructured":"Chollet F. Keras: The python deep learning library. Astrophysics source code library. 2018 Jun:ascl-1806."},{"key":"pone.0266042.ref087","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467. 2016 Mar 14."},{"key":"pone.0266042.ref088","doi-asserted-by":"crossref","unstructured":"Breunig MM, Kriegel HP, Ng RT, Sander J. LOF: identifying density-based local outliers. InProceedings of the 2000 ACM SIGMOD international conference on Management of data 2000 May 16 (pp. 93-104).","DOI":"10.1145\/335191.335388"},{"issue":"2","key":"pone.0266042.ref089","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"J Bergstra","year":"2012","journal-title":"Journal of machine learning research"},{"key":"pone.0266042.ref090","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"J Snoek","year":"2012","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"pone.0266042.ref091","first-page":"6765","article-title":"Hyperband: A novel bandit-based approach to hyperparameter optimization","volume":"18","author":"L Li","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"pone.0266042.ref092","unstructured":"O\u2019Malley T, Bursztein E, Long J, Chollet F, Jin H, Invernizzi L, et al. Keras Tuner. 2019."},{"key":"pone.0266042.ref093","article-title":"Modern neural networks generalize on small data sets","volume":"31","author":"M Olson","year":"2018","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0266042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T17:48:59Z","timestamp":1649267339000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0266042"}},"subtitle":[],"editor":[{"given":"Ardashir","family":"Mohammadzadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,4,6]]},"references-count":93,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0266042","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,6]]}}}