1
|
Edvinsson C, Björnsson O, Erlandsson L, Hansson SR. Predicting intensive care need in women with preeclampsia using machine learning - a pilot study. Hypertens Pregnancy 2024; 43:2312165. [PMID: 38385188 DOI: 10.1080/10641955.2024.2312165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/04/2023] [Accepted: 01/02/2024] [Indexed: 02/23/2024]
Abstract
BACKGROUND Predicting severe preeclampsia with need for intensive care is challenging. To better predict high-risk pregnancies to prevent adverse outcomes such as eclampsia is still an unmet need worldwide. In this study we aimed to develop a prediction model for severe outcomes using routine biomarkers and clinical characteristics. METHODS We used machine learning models based on data from an intensive care cohort with severe preeclampsia (n=41) and a cohort of preeclampsia controls (n=40) with the objective to find patterns for severe disease not detectable with traditional logistic regression models. RESULTS The best model was generated by including the laboratory parameters aspartate aminotransferase (ASAT), uric acid and body mass index (BMI) with a cross-validation accuracy of 0.88 and an area under the curve (AUC) of 0.91. Our model was internally validated on a test-set where the accuracy was lower, 0.82, with an AUC of 0.85. CONCLUSION The clinical routine blood parameters ASAT and uric acid as well as BMI, were the parameters most indicative of severe disease. Aspartate aminotransferase reflects liver involvement, uric acid might be involved in several steps of the pathophysiologic process of preeclampsia, and obesity is a well-known risk factor for development of both severe and non-severe preeclampsia likely involving inflammatory pathways..[Figure: see text].
Collapse
Affiliation(s)
- Camilla Edvinsson
- Division of Obstetrics and Gynecology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden
- Division of Anaesthesia and Intensive Care, Department of Clinical Sciences Lund, Lund University, Lund, Sweden
- Department of Anaesthesia and Intensive Care, Helsingborg Hospital, Helsingborg, Sweden
| | - Ola Björnsson
- Division of Mathematical Statistics, Centre for Mathematical Sciences, Lund University, Lund, Sweden
- Department of Energy Sciences, Faculty of Engineering, Lund University, Lund, Sweden
| | - Lena Erlandsson
- Division of Obstetrics and Gynecology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden
| | - Stefan R Hansson
- Division of Obstetrics and Gynecology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden
- Department of Obstetrics and Gynecology, Skåne University Hospital, Lund/Malmö, Sweden
| |
Collapse
|
2
|
Parker J, Hofstee P, Brennecke S. Prevention of Pregnancy Complications Using a Multimodal Lifestyle, Screening, and Medical Model. J Clin Med 2024; 13:4344. [PMID: 39124610 PMCID: PMC11313446 DOI: 10.3390/jcm13154344] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2024] [Revised: 07/16/2024] [Accepted: 07/22/2024] [Indexed: 08/12/2024] Open
Abstract
Prevention of pregnancy complications related to the "great obstetrical syndromes" (preeclampsia, fetal growth restriction, spontaneous preterm labor, and stillbirth) is a global research and clinical management priority. These syndromes share many common pathophysiological mechanisms that may contribute to altered placental development and function. The resulting adverse pregnancy outcomes are associated with increased maternal and perinatal morbidity and mortality and increased post-partum risk of cardiometabolic disease. Maternal nutritional and environmental factors are known to play a significant role in altering bidirectional communication between fetal-derived trophoblast cells and maternal decidual cells and contribute to abnormal placentation. As a result, lifestyle-based interventions have increasingly been recommended before, during, and after pregnancy, in order to reduce maternal and perinatal morbidity and mortality and decrease long-term risk. Antenatal screening strategies have been developed following extensive studies in diverse populations. Multivariate preeclampsia screening using a combination of maternal, biophysical, and serum biochemical markers is recommended at 11-14 weeks' gestation and can be performed at the same time as the first-trimester ultrasound and blood tests. Women identified as high-risk can be offered prophylactic low dose aspirin and monitored with angiogenic factor assessment from 22 weeks' gestation, in combination with clinical assessment, serum biochemistry, and ultrasound. Lifestyle factors can be reassessed during counseling related to antenatal screening interventions. The integration of lifestyle interventions, pregnancy screening, and medical management represents a conceptual advance in pregnancy care that has the potential to significantly reduce pregnancy complications and associated later life cardiometabolic adverse outcomes.
Collapse
Affiliation(s)
- Jim Parker
- School of Medicine, University of Wollongong, Wollongong 2522, Australia;
| | - Pierre Hofstee
- School of Medicine, University of Wollongong, Wollongong 2522, Australia;
- Tweed Hospital, Northern New South Wales Local Health District, Tweed Heads 2485, Australia
| | - Shaun Brennecke
- Department of Maternal-Fetal Medicine, Pregnancy Research Centre, The Royal Women’s Hospital, Melbourne 3052, Australia;
- Department of Obstetrics and Gynaecology, The University of Melbourne, Melbourne 3052, Australia
| |
Collapse
|
3
|
Tiruneh SA, Vu TTT, Rolnik DL, Teede HJ, Enticott J. Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review. Curr Hypertens Rep 2024; 26:309-323. [PMID: 38806766 PMCID: PMC11199280 DOI: 10.1007/s11906-024-01297-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/23/2024] [Indexed: 05/30/2024]
Abstract
PURPOSE OF REVIEW Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia. RECENT FINDINGS From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.
Collapse
Affiliation(s)
- Sofonyas Abebaw Tiruneh
- Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia
| | - Tra Thuan Thanh Vu
- Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia
| | - Daniel Lorber Rolnik
- Department of Obstetrics and Gynaecology, Monash University, Clayton, VIC, Australia
| | - Helena J Teede
- Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia
| | - Joanne Enticott
- Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.
| |
Collapse
|
4
|
Li YX, Liu YC, Wang M, Huang YL. Prediction of gestational diabetes mellitus at the first trimester: machine-learning algorithms. Arch Gynecol Obstet 2024; 309:2557-2566. [PMID: 37477677 DOI: 10.1007/s00404-023-07131-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2023] [Accepted: 06/27/2023] [Indexed: 07/22/2023]
Abstract
PURPOSE Short- and long-term complications of gestational diabetes mellitus (GDM) involving pregnancies and offspring warrant the development of an effective individualized risk prediction model to reduce and prevent GDM together with its associated co-morbidities. The aim is to use machine learning (ML) algorithms to study data gathered throughout the first trimester in order to predict GDM. METHODS Two independent cohorts with forty-five features gathered through first trimester were included. We constructed prediction models based on three different algorithms and traditional logistic regression, and deployed additional two ensemble algorithms to identify the importance of individual features. RESULTS 4799 and 2795 pregnancies were included in the Xinhua Hospital Chongming branch (XHCM) and the Shanghai Pudong New Area People's Hospital (SPNPH) cohorts, respectively. Extreme gradient boosting (XGBoost) predicted GDM with moderate performance (the area under the receiver operating curve (AUC) = 0.75) at pregnancy initiation and good-to-excellent performance (AUC = 0.99) at the end of the first trimester in the XHCM cohort. The trained XGBoost showed moderate performance in the SPNPH cohort (AUC = 0.83). The top predictive features for GDM diagnosis were pre-pregnancy BMI and maternal abdominal circumference at pregnancy initiation, and FPG and HbA1c at the end of the first trimester. CONCLUSION Our work demonstrated that ML models based on the data gathered throughout the first trimester achieved moderate performance in the external validation cohort.
Collapse
Affiliation(s)
- Yi-Xin Li
- Department of Obstetrics and Gynecology, Chongming Hospital Affiliated to Shanghai University of Medicine and Health Sciences (Xinhua Hospital Chongming Branch), Shanghai, China
| | - Yi-Chen Liu
- Department of Nephrology, Chongming Hospital Affiliated to Shanghai University of Medicine and Health Sciences (Xinhua Hospital Chongming Branch), Shanghai, China
| | - Mei Wang
- Department of Gynecology, Shanghai Pudong New Area People's Hospital, Shanghai, China
| | - Yu-Li Huang
- Department of Obstetrics and Gynecology, Chongming Hospital Affiliated to Shanghai University of Medicine and Health Sciences (Xinhua Hospital Chongming Branch), Shanghai, China.
| |
Collapse
|
5
|
Kovacheva VP, Eberhard BW, Cohen RY, Maher M, Saxena R, Gray KJ. Preeclampsia Prediction Using Machine Learning and Polygenic Risk Scores From Clinical and Genetic Risk Factors in Early and Late Pregnancies. Hypertension 2024; 81:264-272. [PMID: 37901968 PMCID: PMC10842389 DOI: 10.1161/hypertensionaha.123.21053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Accepted: 10/12/2023] [Indexed: 10/31/2023]
Abstract
BACKGROUND Preeclampsia, a pregnancy-specific condition associated with new-onset hypertension after 20-weeks gestation, is a leading cause of maternal and neonatal morbidity and mortality. Predictive tools to understand which individuals are most at risk are needed. METHODS We identified a cohort of N=1125 pregnant individuals who delivered between May 2015 and May 2022 at Mass General Brigham Hospitals with available electronic health record data and linked genetic data. Using clinical electronic health record data and systolic blood pressure polygenic risk scores derived from a large genome-wide association study, we developed machine learning (XGBoost) and logistic regression models to predict preeclampsia risk. RESULTS Pregnant individuals with a systolic blood pressure polygenic risk score in the top quartile had higher blood pressures throughout pregnancy compared with patients within the lowest quartile systolic blood pressure polygenic risk score. In the first trimester, the most predictive model was XGBoost, with an area under the curve of 0.74. In late pregnancy, with data obtained up to the delivery admission, the best-performing model was XGBoost using clinical variables, which achieved an area under the curve of 0.91. Adding the systolic blood pressure polygenic risk score to the models did not improve the performance significantly based on De Long test comparing the area under the curve of models with and without the polygenic score. CONCLUSIONS Integrating clinical factors into predictive models can inform personalized preeclampsia risk and achieve higher predictive power than the current practice. In the future, personalized tools can be implemented to identify high-risk patients for preventative therapies and timely intervention to improve adverse maternal and neonatal outcomes.
Collapse
Affiliation(s)
- Vesela P Kovacheva
- Department of Anesthesiology, Perioperative and Pain Medicine (V.P.K., B.W.E., R.Y.C.), Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | - Braden W Eberhard
- Department of Anesthesiology, Perioperative and Pain Medicine (V.P.K., B.W.E., R.Y.C.), Brigham and Women's Hospital, Harvard Medical School, Boston, MA
| | - Raphael Y Cohen
- Department of Anesthesiology, Perioperative and Pain Medicine (V.P.K., B.W.E., R.Y.C.), Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- PathAI, Boston, MA (R.Y.C.)
| | - Matthew Maher
- Department of Anesthesia, Critical Care and Pain Medicine, Center for Genomic Medicine, Massachusetts General Hospital, Boston (M.M., R.S., K.J.G.)
| | - Richa Saxena
- Department of Anesthesia, Critical Care and Pain Medicine, Center for Genomic Medicine, Massachusetts General Hospital, Boston (M.M., R.S., K.J.G.)
- Department of Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Harvard Medical School, Boston (R.S.)
| | - Kathryn J Gray
- Division of Maternal-Fetal Medicine (K.J.G.), Brigham and Women's Hospital, Harvard Medical School, Boston, MA
- Department of Anesthesia, Critical Care and Pain Medicine, Center for Genomic Medicine, Massachusetts General Hospital, Boston (M.M., R.S., K.J.G.)
| |
Collapse
|
6
|
Ranjbar A, Montazeri F, Ghamsari SR, Mehrnoush V, Roozbeh N, Darsareh F. Machine learning models for predicting preeclampsia: a systematic review. BMC Pregnancy Childbirth 2024; 24:6. [PMID: 38166801 PMCID: PMC10759509 DOI: 10.1186/s12884-023-06220-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2023] [Accepted: 12/20/2023] [Indexed: 01/05/2024] Open
Abstract
BACKGROUND This systematic review provides an overview of machine learning (ML) approaches for predicting preeclampsia. METHOD This review adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyzes (PRISMA) guidelines. We searched the Cochrane Central Register, PubMed, EMBASE, ProQuest, Scopus, and Google Scholar up to February 2023. Search terms were limited to "preeclampsia" AND "artificial intelligence" OR "machine learning" OR "deep learning." All studies that used ML-based analysis for predicting preeclampsia in pregnant women were considered. Non-English articles and those that are unrelated to the topic were excluded. The PROBAST was used to assess the risk of bias and applicability of each included study. RESULTS The search strategy yielded 128 citations; after duplicates were removed and title and abstract screening was completed, 18 full-text articles were evaluated for eligibility. Four studies were included in this review. Two studies were at low risk of bias, and two had low to moderate risk. All of the study designs included were retrospective cohort studies. Nine distinct models were chosen as ML models from the four studies. Maternal characteristics, medical history, medication intake, obstetrical history, and laboratory and ultrasound findings obtained during prenatal care visits were candidate predictors to train the ML model. Elastic net, stochastic gradient boosting, extreme gradient boosting, and Random forest were among the best models to predict preeclampsia. All four studies used metrics such as the area under the curve, true positive rate, negative positive rate, accuracy, precision, recall, and F1 score. The AUC of ML models varied from 0.860 to 0.973 in four studies. CONCLUSION The results of studies yielded high prediction performance of ML models for preeclampsia risk from routine early pregnancy information.
Collapse
Affiliation(s)
- Amene Ranjbar
- Fertility and Infertility Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
| | - Farideh Montazeri
- Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
| | - Sepideh Rezaei Ghamsari
- Department of Midwifery and Reproductive Health, Tehran University of Medical Sciences, Tehran, Iran
| | - Vahid Mehrnoush
- Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
| | - Nasibeh Roozbeh
- Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
| | - Fatemeh Darsareh
- Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran.
| |
Collapse
|
7
|
Kovacheva VP, Eberhard BW, Cohen RY, Maher M, Saxena R, Gray KJ. Prediction of Preeclampsia from Clinical and Genetic Risk Factors in Early and Late Pregnancy Using Machine Learning and Polygenic Risk Scores. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.02.03.23285385. [PMID: 36798188 PMCID: PMC9934723 DOI: 10.1101/2023.02.03.23285385] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
Background Preeclampsia, a pregnancy-specific condition associated with new-onset hypertension after 20 weeks gestation, is a leading cause of maternal and neonatal morbidity and mortality. Predictive tools to understand which individuals are most at risk are needed. Methods We identified a cohort of N=1,125 pregnant individuals who delivered between 05/2015-05/2022 at Mass General Brigham hospitals with available electronic health record (EHR) data and linked genetic data. Using clinical EHR data and systolic blood pressure polygenic risk scores (SBP PRS) derived from a large genome-wide association study, we developed machine learning (xgboost) and linear regression models to predict preeclampsia risk. Results Pregnant individuals with an SBP PRS in the top quartile had higher blood pressures throughout pregnancy compared to patients within the lowest quartile SBP PRS. In the first trimester, the most predictive model was xgboost, with an area under the curve (AUC) of 0.73. Adding the SBP PRS to the models improved the performance only of the linear regression model from AUC 0.70 to 0.71; the predictive power of other models remained unchanged. In late pregnancy, with data obtained up to the delivery admission, the best performing model was xgboost using clinical variables, which achieved an AUC of 0.91. Conclusions Integrating clinical and genetic factors into predictive models can inform personalized preeclampsia risk and achieve higher predictive power than the current practice. In the future, personalized tools can be implemented in clinical practice to identify high-risk patients for preventative therapies and timely intervention to improve adverse maternal and neonatal outcomes.
Collapse
|
8
|
Liu M, Yang X, Chen G, Ding Y, Shi M, Sun L, Huang Z, Liu J, Liu T, Yan R, Li R. Development of a prediction model on preeclampsia using machine learning-based method: a retrospective cohort study in China. Front Physiol 2022; 13:896969. [PMID: 36035487 PMCID: PMC9413067 DOI: 10.3389/fphys.2022.896969] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2022] [Accepted: 07/05/2022] [Indexed: 12/03/2022] Open
Abstract
Objective: The aim of this study was to use machine learning methods to analyze all available clinical and laboratory data obtained during prenatal screening in early pregnancy to develop predictive models in preeclampsia (PE). Material and Methods: Data were collected by retrospective medical records review. This study used 5 machine learning algorithms to predict the PE: deep neural network (DNN), logistic regression (LR), support vector machine (SVM), decision tree (DT), and random forest (RF). Our model incorporated 18 variables including maternal characteristics, medical history, prenatal laboratory results, and ultrasound results. The area under the receiver operating curve (AUROC), calibration and discrimination were evaluated by cross-validation. Results: Compared with other prediction algorithms, the RF model showed the highest accuracy rate. The AUROC of RF model was 0.86 (95% CI 0.80–0.92), the accuracy was 0.74 (95% CI 0.74–0.75), the precision was 0.82 (95% CI 0.79–0.84), the recall rate was 0.42 (95% CI 0.41–0.44), and Brier score was 0.17 (95% CI 0.17–0.17). Conclusion: The machine learning method in our study automatically identified a set of important predictive features, and produced high predictive performance on the risk of PE from the early pregnancy information.
Collapse
Affiliation(s)
- Mengyuan Liu
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Xiaofeng Yang
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Guolu Chen
- School of Information and Communication Engineering, Harbin Engineering University, Harbin, China
| | - Yuzhen Ding
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Meiting Shi
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Lu Sun
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Zhengrui Huang
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Jia Liu
- The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Tong Liu
- School of Information and Communication Engineering, Harbin Engineering University, Harbin, China
- *Correspondence: Tong Liu, ; Ruiling Yan, ; Ruiman Li,
| | - Ruiling Yan
- The First Affiliated Hospital of Jinan University, Guangzhou, China
- *Correspondence: Tong Liu, ; Ruiling Yan, ; Ruiman Li,
| | - Ruiman Li
- The First Affiliated Hospital of Jinan University, Guangzhou, China
- *Correspondence: Tong Liu, ; Ruiling Yan, ; Ruiman Li,
| |
Collapse
|
9
|
Bennett R, Mulla ZD, Parikh P, Hauspurg A, Razzaghi T. An imbalance-aware deep neural network for early prediction of preeclampsia. PLoS One 2022; 17:e0266042. [PMID: 35385525 PMCID: PMC8985991 DOI: 10.1371/journal.pone.0266042] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2021] [Accepted: 03/12/2022] [Indexed: 11/18/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Rachel Bennett
- School of Industrial and Systems Engineering, University of Oklahoma, Norman, Oklahoma, United States of America
| | - Zuber D. Mulla
- Department of Obstetrics and Gynecology, and Office of Faculty Development, Paul L. Foster School of Medicine, Texas Tech University Health Sciences Center El Paso, El Paso, Texas, United States of America
- Department of Public Health, Texas Tech University Health Sciences Center, Lubbock, Texas, United States of America
| | - Pavan Parikh
- Division of Maternal Fetal Medicine, University of Oklahoma Health Science Center, Oklahoma City, Oklahoma, United States of America
| | - Alisse Hauspurg
- Division of Maternal-Fetal Medicine, Department of Obstetrics, Gynecology, and Reproductive Sciences, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States of America
| | - Talayeh Razzaghi
- School of Industrial and Systems Engineering, University of Oklahoma, Norman, Oklahoma, United States of America
| |
Collapse
|