Prediction of High-Risk Pregnancy Based on Machine Learning Algorithms

Prediction of High-Risk Pregnancy Based on Machine Learning Algorithms | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Prediction of High-Risk Pregnancy Based on Machine Learning Algorithms Xinyu Pi, Junzhi Wang, Liangliang Chu, Guochun Zhang, Wenli Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5869497/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 04 May, 2025 Read the published version in Scientific Reports → Version 1 posted 3 You are reading this latest preprint version Abstract This study explores the application of machine learning algorithms in predicting high-risk pregnancy among expectant mothers, aiming to construct an efficient predictive model to improve maternal health management. The study is based on the Maternal Health Risk Dataset (MHRD) from Bangladesh, covering multiple hospitals, community clinics, and maternal healthcare centers, and encompassing health data from 1,014 pregnant women. Six machine learning algorithms—Multilayer Perceptron (MLP), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—are employed to construct predictive models. It is worth noting that MLP demonstrates superior performance compared with the other five algorithms. By applying the MLP method, the study successfully established an efficient pregnancy risk prediction model. The model evaluation results indicate that it has high accuracy in predicting pregnancy risks, with an overall accuracy rate of 82%, and particularly high accuracy in high-risk predictions, reaching 91%. With the computational support of an NVIDIA GPU RTX3050Ti, the model demonstrated excellent data processing capabilities, capable of predicting and processing 500 sets of data items per second. This study not only showcases the enormous potential of machine learning technology in the healthcare field, especially in the rapid and accurate identification of high-risk pregnancies, providing a powerful decision-support tool for medical professionals, but also offers significant reference value for future research in this area. Health sciences/Medical research Health sciences/Risk factors High-Risk Pregnancy Machine Learning Multilayer Perceptron Nursing Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 1. Introduction During pregnancy, certain complications or pathogenic factors may threaten the life safety of the pregnant woman, fetus, and newborn, which are defined as high-risk pregnancies 1 . In recent years, researchers such as Mavreli et al. 2 have emphasized that early identification of high-risk pregnancies can effectively reduce the risk of perinatal mortality, pregnancy-related complications, and neonatal complications. However, due to a lack of professional knowledge and assessment skills, junior nursing staff may have deficiencies in clinical decision-making capabilities, which could affect the accuracy of pregnancy risk stratification 3 .It is noteworthy that significant progress has been made in the field of obstetrics and gynecology using machine learning technology. Researchers like Kovacheva 4 have predicted early and late pregnancy risks from clinical and genetic perspectives through machine learning and polygenic risk scores. Chu et al. 5 used machine learning methods to predict the risk of adverse events in pregnant women with congenital heart disease. These advances indicate that, with the development of smart medicine, machine learning technology has shown great advantages in the field of disease prediction and diagnosis 6, 7 . It is crucial to identify high-risk vulnerable populations as early as possible during pregnancy 8, 9 . Developing innovative predictive methods is essential for identifying high-risk pregnant women 10, 11 . This study introduces an innovative predictive model based on the MLP machine learning algorithm for identifying high-risk pregnancies. Compared with five other machine learning algorithms, it demonstrates superior performance, filling a gap in the existing research on MLP-based predictive models for high-risk pregnancies. The model's performance is evaluated by assessing its accuracy, precision, recall, F1 score, and AUC in predicting high-, medium-, and low-risk pregnancies. This approach enables healthcare providers to detect high-risk pregnancies using basic clinical parameters, including age, systolic and diastolic blood pressure, blood glucose levels, body temperature, and heart rate. This facilitates the implementation of preventive measures. After prediction, pregnant women can receive targeted care based on their predicted risk levels, ensuring a smooth pregnancy and reducing the occurrence of complications 12 . Therefore, this study aims to explore the use of machine learning models for high-risk pregnancy risk prediction and evaluation, hoping to provide valuable reference for healthcare professionals in assessing and treating high-risk pregnant women. 2. Methods 2.1 Research Process This study harnessed the open-source MHRD from Bangladeshi medical institutions, covering multiple hospitals, community clinics, and maternal healthcare centers, and encompassing data on 1,014 pregnant women. Records of pregnant women aged 10–18 years were excluded due to ethical concerns and data sparsity, ensuring the dataset’s clinical validity. Risk levels are stratified into low, medium, and high categories. Post-data preprocessing, the dataset is randomly divided into a training set of 362 and a test set of 90, adhering to an 8:2 ratio. To curb overfitting in the MLP model, early stopping is employed 13 . The model's predictive accuracy is gauged through a confusion matrix and Receiver Operating Characteristic (ROC) curve, with the research flowchart delineated in Fig. 1 . 2.2 Data Distribution The input features include maternal age, systolic blood pressure, diastolic blood pressure, blood glucose levels, body temperature, heart rate, and risk level. These features were selected based on their established medical relevance to pregnancy risk assessment. After data cleaning and deduplication, a total of 452 data entries were obtained in this study, including 234 low-risk entries, 106 medium-risk entries, and 112 high-risk entries. The data distribution is shown in Fig. 2 . In Fig. 3 , there are three box plots and one histogram. Figure 3 (a) , Fig. 3 (b) , and Fig. 3 (d) are box plots representing the distribution of age, blood sugar, and heart rate across different risk levels in the dataset, respectively. Figure 3 (c) is a histogram showing the distribution of risk levels corresponding to different heart rates. From Figs. 3 (a) to 3(d), it is evident that individuals with a high pregnancy risk level have higher age, blood sugar, and heart rate compared to those with medium and low risk levels, which aligns with medical objective principles. 2.3 Machine Learning Methods Six machine learning algorithms—MLP, LR, DT, RF, XGBoost, and SVM—are employed to construct predictive models. It is worth noting that MLP demonstrates superior performance compared with the other five algorithms. This choice is based on the comprehensive evaluation of each algorithm's performance in terms of accuracy, precision, and other relevant metrics. In this study, we've adopted a multifaceted strategy to refine the accuracy and generalization of our MLP model, which includes data preprocessing, the application of the SMOTE algorithm to address class imbalance, and the implementation of early stopping to prevent overfitting. The MLP model consists of three hidden layers, with 256, 128, and 64 neurons respectively. All hidden layers utilize the ReLU activation function and are followed by a SoftMax output layer. To prevent overfitting, Dropout layers with a dropout rate of 0.5 are inserted after the first two hidden layers. The model was trained using the Adam optimizer with a learning rate of 0.001 and a cross-entropy loss function. The batch size was set to 32, and the maximum number of training epochs was 10,000. Training would be halted if the validation loss did not improve for 300 epochs. Our data cleaning process was essential for ensuring data quality, where we removed erroneous, duplicate, or irrelevant information from the open-source dataset from Bangladesh, including outliers such as records of pregnant women aged between 10 and 18 years. We quantified risk levels numerically, assigning values of 2, 1, and 0 to high, medium, and low risks, respectively, to facilitate subsequent analysis. To accurately assess model performance, we divided the dataset into a training set, comprising 80% of the data, and a test set, comprising 20%, using stratified random sampling to maintain the distribution of each category across both sets. To combat overfitting and enhance the model's ability to learn from the minority class, we applied the SMOTE algorithm and introduced Dropout layers within the MLP model. We applied SMOTE exclusively to the training set post-split to avoid data leakage The test set remained unmodified to ensure unbiased evaluation. Additionally, we employed early stopping with a patience parameter P, which monitors performance on the test set and halts training if there's no improvement for P consecutive epochs, reverting the model to its best-performing state. This approach not only prevents overfitting but also ensures that the model retains its peak performance. For model interpretability analysis, we utilized a confusion matrix and ROC curve to assess the performance of the optimal model. The confusion matrix provides a clear view of the model's predictive accuracy, while the ROC curve offers an intuitive representation of the model's overall performance by comparing true positive and false positive rates across various thresholds. These methods validate the model's risk level predictions and enhance the interpretability of the results, thereby ensuring the reliability of our predictions. 2.4 Experimental Platform This study was conducted on a computer equipped with an NVIDIA GPU RTX3050Ti, a CPU model AMD Ryzen 7 5800H, and 1.5TB of disk space. All experiments were based on the Python programming language. To build and train the MLP model, TensorFlow (2.18.0) and Keras (3.6.0) libraries were used. Data processing and analysis benefited from Pandas (2.2.3) and NumPy (1.24.4), while data visualization was performed using Matplotlib (3.5.1). Model optimization was achieved using Sklearn (1.5.2). 3. Results Table 1 presents a comparison of the performance parameters of the MLP model with five other algorithms. Among these five algorithms, the one using LR for high-risk pregnancy prediction achieved the lowest performance, with an accuracy of 0.61 and precision of 0.59. In contrast, the RF algorithm demonstrated the highest performance for high-risk pregnancy prediction, with an accuracy of 0.78 and precision of 0.79. Compared with these five algorithms, the MLP model constructed in this study exhibited superior performance, achieving an accuracy of 0.81 and precision of 0.82. Table 1 Comparison of the Performance of MLP with Five Other Machine Learning Algorithms Algorithm Accuracy Precision Recall F1-Score MLP 0.81 0.82 0.82 0.82 LR 0.61 0.59 0.61 0.60 DT 0.73 0.75 0.73 0.74 RF 0.78 0.79 0.78 0.78 XGBoost 0.76 0.77 0.76 0.76 SVM 0.63 0.61 0.63 0.62 Table 2 illustrates that the MLP model performs well across different risk categories, particularly in the high-risk category, achieving an accuracy, recall, and F1 score of 0.91. The performance in the medium-risk category is slightly lower, with an accuracy and recall of 0.80 and 0.83, respectively, and an F1 score of 0.81. The low-risk category has slightly lower accuracy, recall, and F1 scores of 0.77, 0.73, and 0.75, respectively. The overall accuracy is 0.82, indicating excellent overall performance of the model. Table 2 This is Prediction Performance of MLP Model on Pregnancy Risk Levels Precision Recall F1-Score AUC Sample size High Risk 0.91 0.91 0.91 0.99 22 Mid Risk 0.80 0.83 0.81 0.91 21 Low Risk 0.77 0.73 0.75 0.91 47 Total 0.82 - - - 90 The normalized confusion matrix shows the performance of the MLP model in predicting risk levels in high-risk pregnancies, covering high, medium, and low risk levels. The model excels in high-risk prediction with an accuracy of 91%, with misclassification rates of 2% for low risk and 7% for medium risk. The accuracy for low-risk prediction is 83%, with a 14% misclassification rate for medium risk. Medium-risk prediction accuracy stands at 73%, with misclassification rates of 24% for low risk and 3% for high risk. Overall, the model is reliable in predicting pregnancy risk for pregnant women. The ROC curve analysis shows that the MLP model achieves an AUC value of 0.99 for the high-risk category when predicting pregnancy risk levels, indicating near-perfect identification. The ROC curve closely aligns with the top left corner, demonstrating the ability to achieve a high true positive rate at a very low false positive rate. 4. Discussion 4.1 Accurate Prediction and Treatment Options for Pregnancy Risk are Crucial This study aims to develop a machine learning model for predicting high-risk pregnancy in expectant mothers. By analyzing the health data of pregnant women, the model can accurately assess pregnancy risk levels, demonstrating excellent accuracy and efficiency 14 . This tool can support clinical nurses in making more precise risk assessments during evaluations, thereby enabling appropriate interventions to reduce pregnancy risks. High-risk pregnancy refers to a pregnancy state that faces higher risks due to various high-risk factors (such as personal health issues, pregnancy complications, adverse environmental impacts, etc.) 1,2 during the pregnancy period. Such pregnancy conditions increase maternal and neonatal morbidity and mortality rates. Taking China as an example, with the development of society, the implementation of the universal two-child policy, and the popularization of assisted reproductive technology, the incidence of high-risk pregnancies is increasing year by year. Compared to normal pregnancies, high-risk pregnancies significantly increase the risk of adverse pregnancy outcomes, including preterm birth, low birth weight, neonatal complications, and death. Moreover, the diagnosis of high-risk pregnancy may lead to reduced coping ability, decreased well-being, and increased psychiatric symptoms in pregnant women, including stress, depression, and anxiety 15 . Therefore, accurately and early identifying pregnancy risks and implementing effective management measures are crucial for improving maternal and infant health. Nurses, as the first medical team members to contact pregnant women and collect their basic information, play a critical role in the early identification and management of high-risk pregnancies 16 . However, since the health status of pregnant women may change over time, continuous monitoring by nurses is required, which is time-consuming and labor-intensive. Therefore, developing a simple yet accurate tool for identifying high-risk pregnancies is particularly important for ensuring the health and safety of mothers and newborns. 4.2 Artificial Intelligence-Assisted Diagnosis and Treatment of Pregnancy Risk Becomes Possible High-risk pregnancies pose significant health risks to mothers and newborns, involving various complex factors such as advanced maternal age, multiple pregnancies, and pregnancy complications, leading to increased rates of difficult labor and cesarean sections, as well as an increase in neonatal health issues 17 . These situations place high professional demands on medical and nursing staff, emphasizing the need for rigorous and professional measures. The World Health Organization points out that most deaths related to pregnancy and childbirth can be prevented through timely identification and response to pregnancy risks 18 . Timely intervention in pregnancy risks and quality healthcare services are key. In 2017, China implemented a pregnancy risk assessment and management system, adopting a five-color grading system to assess maternal risk levels and adjust medical resource allocation accordingly, effectively reducing adverse outcomes of high-risk pregnancies 19 . However, traditional risk assessment methods have issues with large workloads and low efficiency. The machine learning method based on the MLP proposed in this study demonstrates remarkable performance in predicting high-risk pregnancies. Compared with other methods, it achieves an accuracy rate of up to 91% in predicting high-risk cases. Moreover, the method is highly efficient, with the capability to process up to 500 sets of data per second. This method not only improves the efficiency and accuracy of risk assessment but also reduces the workload on medical staff and the demand for medical resources, showing great potential in optimizing pregnancy risk management using advanced technology. Additionally, by utilizing the SMOTE algorithm 20 and early stopping mechanisms 21 , our model has demonstrated remarkable generalization capabilities. It effectively addresses the issue of data imbalance and prevents overfitting. This ensures that the model performs well not only on the training data but also maintains high accuracy and reliability when applied to unseen data. This study is innovative not only in its technical approach but also in its practical application. By accurately predicting the risks associated with high-risk pregnancies, our model serves as an important decision-support tool for clinical practice. It enables healthcare professionals to take preemptive interventions, thereby reducing the risk of complications for both mothers and infants 12 . 5. Conclusions This study successfully developed a machine learning based high-risk pregnancy prediction model, which estimates pregnancy risk by analyzing the health data of pregnant women, with an accuracy rate of up to 91%, and can accurately assess the level of pregnancy risk. At the same time, it also has a fast prediction speed, which not only improves the efficiency of pregnancy risk assessment, but also reduces the workload of medical personnel and the demand for medical resources, demonstrating the huge potential of using advanced technology to optimize pregnancy risk management. Abbreviations MHRD, Maternal Health Risk Dataset; MLP, multilayer perceptron; LR, Logistic Regression; DT, Decision Tree; RF, Random Forest; XGBoost, eXtreme Gradient Boosting; SVM, Support Vector Machine; ROC, receiver operating characteristic. Declarations Availability of Data and Materials The data used in this study originates from Bangladesh and is titled "Maternal Health Risk Data," which can be accessed through the following link: https://www.kaggle.com/datasets/csafrit2/maternal-health-risk-data. This dataset is publicly available and can be used without additional permission. For any further inquiries regarding the dataset or other materials used in this study, please contact the corresponding author at the email address [email protected] . Author Contributions PXY—prepared the first draft. WJZ and ZGC—revised the manuscript. CLL—Provide assistance in data analysis, ZWL—edited and finalized the manuscript. All authors contributed to editorial changes in the manuscript. All authors read and approved the final manuscript. Ethics Approval and Consent to Participate Since the data for this study is sourced from open-source datasets, ethical review is not required. Acknowledgment Not applicable. Funding This research was funded by the Shandong Province Medical Staff Science and Technology Innovation Program Project (Project No.: SDYWZGKCJH2022056) and the Shandong Nursing Association Scientific Research Project (Project No.: SDHLKT202202). Conflict of Interest The authors declare no conflict of interest. References Phillips, S. E., Celi, A. C., Margo, J., Wehbe, A., Karlage, A., & Zera, C. A. Improving Care Beyond Birth: A Qualitative Study of Postpartum Care After High-Risk Pregnancy. J Womens Health . 33 , 1720-1729. https://doi.org/10.1089/jwh.2024.0108 (2024). Mavreli, D., Theodora, M., & Kolialexi, A. Known biomarkers for monitoring pregna-ncy complications. Expert Rev. Mol. Diagn . 21 , 1115-1117. https://doi.org/10.1080/14737159.2021.1971078(2021). Dewi, N. A., Yetti, K., & Nuraini, T. Nurses’ critical thinking and clinical decision-making abilities are correlated with the quality of nursing handover. Enferm Clin 31 , S271-S275. https://doi.org/10.1016/j.enfcli.2020.09.014 (2021). Kovacheva, V. P., Eberhard, B. W., Cohen, R. Y., Maher, M., Saxena, R., & Gray, K. J. Preeclampsia prediction using machine learning and polygenic risk scores from cl-inical and genetic risk factors in early and late pregnancies. Hypertension . 81 , 264-272. https://doi.org/10.1161/HYPERTENSIONAHA.123.21053 (2024). Chu, R., Chen, W., Song, G., Yao, S., Xie, L., Song, L., ... & Kong, B. Predicting the risk of adverse events in pregnant women with congenital heart disease. J Am Heart Assoc . 9 , e016371. https://doi.org/10.1161/JAHA.120.016371 (2020). Montgomery-Csobán, T., Kavanagh, K., Murray, P., Robertson, C., Barry, S. J., Ukah, U. V., ... & Widmer, M. Machine learning-enabled maternal risk assessment for women with pre-eclampsia (the PIERS-ML model): a modelling study. Lancet Digit Health . 6 , e238-e250. https://doi.org/10.1016/S2589-7500(23)00267-4 (2024). Bowe, A. K., Lightbody, G., Staines, A., Murray, D. M., & Norman, M. Prediction of 2-year cognitive outcomes in very preterm infants using machine learning methods. JAMA Network Open . 6 , e2349111-e2349111. https://doi.org/10.1001/jamanetworkopen.2023.49111(2023). Deng, Z., Duan, L., & Wang, K. Advancing comprehensive care for high-risk pregna-ncies: integrating social and clinical perspectives. Am J Obstet Gynecol . https://doi.org/10.1016/j.ajog.2025.02.002(2025). Correa-de-Araujo, R., & Yoon, S. S. Clinical outcomes in high-risk pregnancies due to advanced maternal age. J Womens Health. 30 , 160-167. https://doi.org/10.1089/jwh.2020.8860 (2021). Cooray, S. D., Boyle, J. A., Soldatos, G., Allotey, J., Wang, H., Fernandez-Felix, B. M., ... & Teede, H. J. Development, validation and clinical utility of a risk prediction model for adverse pregnancy outcomes in women with gestational diabetes: The PeRSonal GDM model. EClinicalMedicine . 52 .https://doi.org/10.1016/j.eclinm.2022.101637 (2022). Li, S., Wang, Z., Vieira, L. A., Zheutlin, A. B., Ru, B., Schadt, E., ... & Li, L. Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data. NPJ Digit. Med . 5 68. https://doi.org/10.1038/s41746-022-00612-x(2022). Li, M., Grewal, J., Hinkle, S. N., Yisahak, S. F., Grobman, W. A., Newman, R. B., ... & Zhang, C. Healthy dietary patterns and common pregnancy complications: a prospective and longitudinal study. Am. J. Clin. Nutr. 114 , 1229-1237. https://doi.org/10.1093/ajcn/nqab145 (2021). An, L., Wang, L., & Li, Y. HEA-Net: Attention and MLP hybrid encoder architecture for medical image segmentation. Sensors . 22 , 7024. https://doi.org/10.3390/s22187024 (2022). Al Mashrafi, S. S., Tafakori, L., & Abdollahian, M. Predicting maternal risk level using machine learning models. BMC PREGNANCY CHILDB. 24 , 820.https://doi.org/10.1186/s12884-024-07030-9 (2024). Williamson, S. P., Moffitt, R. L., Broadbent, J., Neumann, D. L., & Hamblin, P. S. Coping, wellbeing, and psychopathology during high-risk pregnancy: A systematic review. Midwifery . 116 , 103556. https://doi.org/10.1016/j.midw.2022.103556 (2023). Tahmasebi T. High-risk pregnancy: Managing complications for a safe and healthy outcome. J Preg Neonatal Med . 8 , 226.https://doi.org/10.35841/aapnm-8.5.226 (2024) Nazari, M., Moayed Rezaie, S., Yaseri, F., Sadr, H., & Nazari, E. Design and analysis of a telemonitoring system for high-risk pregnant women in need of special care or attention. BMC Pregnancy and Childbirth . 24 , 817. https://doi.org/10.1186/s12884-024-07019-4(2024). Lattof, S. R., Tunçalp, Ö., Moran, A. C., Bucagu, M., Chou, D., Diaz, T., & Gülmezoglu, A. M. Developing measures for WHO recommendations on antenatal care for a positive pregnancy experience: a conceptual framework and scoping review. BMJ open . 9 , e024130. https://doi.org/10.1136/bmjopen-2018-024130 (2020). Liu, Y., Luo, R., & Huang, A. The distribution of pregnant women with different pregnancy risks—4 cities, China, 2019. China CDC Weekly . 3 , 50.https://doi.org/10.46234/ccdcw2021.016 (2021). Kosolwattana, T., Liu, C., Hu, R., Han, S., Chen, H., & Lin, Y. A self-inspected adaptive SMOTE algorithm (SASMOTE) for highly imbalanced data classification in healthcare. Bio Data Mining . 16 , 15. https://doi.org/10.1186/s13040-023-00330-4(2023). Nguyen, M. H., Abbass, H. A., & McKay, R. I. Stopping criteria for ensemble of evolutionary artificial neural networks. Appl. Soft Comput . 6 , 100-107. https://doi.org/10.1016/j.asoc.2004.12.005 (2005). Additional Declarations No competing interests reported. Supplementary Files file.xlsx Cite Share Download PDF Status: Published Journal Publication published 04 May, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Accepted 28 Apr, 2025 Submission checks completed at journal 21 Apr, 2025 First submitted to journal 21 Apr, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5869497","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":449052394,"identity":"45fbc295-a8f0-4688-9ab0-db9f5beabe25","order_by":0,"name":"Xinyu Pi","email":"","orcid":"","institution":"Shandong First Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Pi","suffix":""},{"id":449052395,"identity":"c36a2741-3950-47c3-8474-1a40d6a74151","order_by":1,"name":"Junzhi Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYBACef7G9h8fKmzs+NmbDxCnxXDG4QOSM86kJUv2HEsg0poDaQnSvC2HGTfM8DEgTgdjwxkDY94GZmYDCZ6PN94w2MnpNhDQws7cY5A4dwcbn7l072bLOQzJxmYHiLDlwNszPMyWc85uk+ZhOJC4jZAWhgM5hg28bRKMG27kPCNWS1oyI2+bAUgLG3FagIF8jHHGmQRQIBtbzjEgwi/AqGxj+FDxHxSVD2+8qbCTI6gFBUjwEBk1yFpI1TEKRsEoGAUjAgAAf2hHnrq6incAAAAASUVORK5CYII=","orcid":"","institution":"Shandong Provincial QianFoShan Hospital","correspondingAuthor":true,"prefix":"","firstName":"Junzhi","middleName":"","lastName":"Wang","suffix":""},{"id":449052396,"identity":"4cfdc732-2c9b-4766-b3c7-007c79ed7528","order_by":2,"name":"Liangliang Chu","email":"","orcid":"","institution":"Shandong Provincial QianFoShan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Liangliang","middleName":"","lastName":"Chu","suffix":""},{"id":449052397,"identity":"f48d5a6b-e484-4aea-a62a-ba5a3abae530","order_by":3,"name":"Guochun Zhang","email":"","orcid":"","institution":"Shandong Provincial QianFoShan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Guochun","middleName":"","lastName":"Zhang","suffix":""},{"id":449052398,"identity":"66b409e9-7817-4c59-ac64-36a9d61cf35b","order_by":4,"name":"Wenli Zhang","email":"","orcid":"","institution":"Shandong First Medical University","correspondingAuthor":false,"prefix":"","firstName":"Wenli","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-01-21 02:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5869497/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5869497/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-00450-3","type":"published","date":"2025-05-04T15:57:47+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":81802497,"identity":"f4ba75f2-2d10-4262-8662-92ec4aba3b90","added_by":"auto","created_at":"2025-05-02 06:23:14","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":211444,"visible":true,"origin":"","legend":"\u003cp\u003eResearch Flowchart\u003c/p\u003e","description":"","filename":"image1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/8b155657ea48a388a0a109de.jpg"},{"id":81802493,"identity":"83bb1348-5d93-4ca7-8d61-338e498dbced","added_by":"auto","created_at":"2025-05-02 06:23:14","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":9911,"visible":true,"origin":"","legend":"\u003cp\u003eRisk Level Distribution\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/0426e4f607f702f1daa3a81f.png"},{"id":81802499,"identity":"35d8b691-0a70-4e0d-bb4c-f55d1b5396d3","added_by":"auto","created_at":"2025-05-02 06:23:15","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":31514,"visible":true,"origin":"","legend":"\u003cp\u003eDistribution Chart of Risk Levels for Different Ages, Blood Sugar, and Heart Rates\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/b061251052957de61eea9409.png"},{"id":81803274,"identity":"1cd3e0e4-43b4-45e8-a34f-c74d31f08d48","added_by":"auto","created_at":"2025-05-02 06:31:14","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":54549,"visible":true,"origin":"","legend":"\u003cp\u003eConfusion matrix of MLP model predictions for different risk levels on the test set\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/f8de579029f1d92016b7387f.png"},{"id":81802494,"identity":"e2c59ed8-4a61-4c30-a57b-3421a03e5d52","added_by":"auto","created_at":"2025-05-02 06:23:14","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":40263,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eROC Curves for Predictions of Different Risk Levels on the Test Set by the MLP Model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/1dffd8e5250603b3e3d6965d.png"},{"id":81987813,"identity":"2bd4299c-1d02-4345-ba13-ca7150938715","added_by":"auto","created_at":"2025-05-05 16:06:15","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":983837,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/b2f7d5af-a1c9-4422-8da3-a646fe79c4e6.pdf"},{"id":81802492,"identity":"2613cab6-125a-4259-b502-947b091b6f61","added_by":"auto","created_at":"2025-05-02 06:23:13","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":41650,"visible":true,"origin":"","legend":"","description":"","filename":"file.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5869497/v1/21a7b87c4aba517d688c5f88.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of High-Risk Pregnancy Based on Machine Learning Algorithms","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eDuring pregnancy, certain complications or pathogenic factors may threaten the life safety of the pregnant woman, fetus, and newborn, which are defined as high-risk pregnancies\u003csup\u003e1\u003c/sup\u003e. In recent years, researchers such as Mavreli et al.\u003csup\u003e2\u003c/sup\u003e have emphasized that early identification of high-risk pregnancies can effectively reduce the risk of perinatal mortality, pregnancy-related complications, and neonatal complications. However, due to a lack of professional knowledge and assessment skills, junior nursing staff may have deficiencies in clinical decision-making capabilities, which could affect the accuracy of pregnancy risk stratification\u003csup\u003e3\u003c/sup\u003e.It is noteworthy that significant progress has been made in the field of obstetrics and gynecology using machine learning technology. Researchers like Kovacheva\u003csup\u003e4\u003c/sup\u003e have predicted early and late pregnancy risks from clinical and genetic perspectives through machine learning and polygenic risk scores. Chu et al.\u003csup\u003e5\u003c/sup\u003e used machine learning methods to predict the risk of adverse events in pregnant women with congenital heart disease. These advances indicate that, with the development of smart medicine, machine learning technology has shown great advantages in the field of disease prediction and diagnosis\u003csup\u003e6, 7\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIt is crucial to identify high-risk vulnerable populations as early as possible during pregnancy\u003csup\u003e8, 9\u003c/sup\u003e. Developing innovative predictive methods is essential for identifying high-risk pregnant women\u003csup\u003e10, 11\u003c/sup\u003e. This study introduces an innovative predictive model based on the MLP machine learning algorithm for identifying high-risk pregnancies. Compared with five other machine learning algorithms, it demonstrates superior performance, filling a gap in the existing research on MLP-based predictive models for high-risk pregnancies.\u003c/p\u003e \u003cp\u003eThe model's performance is evaluated by assessing its accuracy, precision, recall, F1 score, and AUC in predicting high-, medium-, and low-risk pregnancies. This approach enables healthcare providers to detect high-risk pregnancies using basic clinical parameters, including age, systolic and diastolic blood pressure, blood glucose levels, body temperature, and heart rate. This facilitates the implementation of preventive measures. After prediction, pregnant women can receive targeted care based on their predicted risk levels, ensuring a smooth pregnancy and reducing the occurrence of complications\u003csup\u003e12\u003c/sup\u003e. Therefore, this study aims to explore the use of machine learning models for high-risk pregnancy risk prediction and evaluation, hoping to provide valuable reference for healthcare professionals in assessing and treating high-risk pregnant women.\u003c/p\u003e"},{"header":"2. Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Research Process\u003c/h2\u003e \u003cp\u003eThis study harnessed the open-source MHRD from Bangladeshi medical institutions, covering multiple hospitals, community clinics, and maternal healthcare centers, and encompassing data on 1,014 pregnant women. Records of pregnant women aged 10\u0026ndash;18 years were excluded due to ethical concerns and data sparsity, ensuring the dataset\u0026rsquo;s clinical validity. Risk levels are stratified into low, medium, and high categories. Post-data preprocessing, the dataset is randomly divided into a training set of 362 and a test set of 90, adhering to an 8:2 ratio. To curb overfitting in the MLP model, early stopping is employed\u003csup\u003e13\u003c/sup\u003e. The model's predictive accuracy is gauged through a confusion matrix and Receiver Operating Characteristic (ROC) curve, with the research flowchart delineated in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Data Distribution\u003c/h2\u003e \u003cp\u003eThe input features include maternal age, systolic blood pressure, diastolic blood pressure, blood glucose levels, body temperature, heart rate, and risk level. These features were selected based on their established medical relevance to pregnancy risk assessment. After data cleaning and deduplication, a total of 452 data entries were obtained in this study, including 234 low-risk entries, 106 medium-risk entries, and 112 high-risk entries. The data distribution is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIn Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, there are three box plots and one histogram. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e\u003cb\u003e(a)\u003c/b\u003e, Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e\u003cb\u003e(b)\u003c/b\u003e, and Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e\u003cb\u003e(d)\u003c/b\u003e are box plots representing the distribution of age, blood sugar, and heart rate across different risk levels in the dataset, respectively. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e \u003cb\u003e(c)\u003c/b\u003e is a histogram showing the distribution of risk levels corresponding to different heart rates. From Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e(a) to 3(d), it is evident that individuals with a high pregnancy risk level have higher age, blood sugar, and heart rate compared to those with medium and low risk levels, which aligns with medical objective principles.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Machine Learning Methods\u003c/h2\u003e \u003cp\u003eSix machine learning algorithms\u0026mdash;MLP, LR, DT, RF, XGBoost, and SVM\u0026mdash;are employed to construct predictive models. It is worth noting that MLP demonstrates superior performance compared with the other five algorithms. This choice is based on the comprehensive evaluation of each algorithm's performance in terms of accuracy, precision, and other relevant metrics. In this study, we've adopted a multifaceted strategy to refine the accuracy and generalization of our MLP model, which includes data preprocessing, the application of the SMOTE algorithm to address class imbalance, and the implementation of early stopping to prevent overfitting. The MLP model consists of three hidden layers, with 256, 128, and 64 neurons respectively. All hidden layers utilize the ReLU activation function and are followed by a SoftMax output layer. To prevent overfitting, Dropout layers with a dropout rate of 0.5 are inserted after the first two hidden layers. The model was trained using the Adam optimizer with a learning rate of 0.001 and a cross-entropy loss function. The batch size was set to 32, and the maximum number of training epochs was 10,000. Training would be halted if the validation loss did not improve for 300 epochs.\u003c/p\u003e \u003cp\u003eOur data cleaning process was essential for ensuring data quality, where we removed erroneous, duplicate, or irrelevant information from the open-source dataset from Bangladesh, including outliers such as records of pregnant women aged between 10 and 18 years. We quantified risk levels numerically, assigning values of 2, 1, and 0 to high, medium, and low risks, respectively, to facilitate subsequent analysis. To accurately assess model performance, we divided the dataset into a training set, comprising 80% of the data, and a test set, comprising 20%, using stratified random sampling to maintain the distribution of each category across both sets. To combat overfitting and enhance the model's ability to learn from the minority class, we applied the SMOTE algorithm and introduced Dropout layers within the MLP model. We applied SMOTE exclusively to the training set post-split to avoid data leakage The test set remained unmodified to ensure unbiased evaluation. Additionally, we employed early stopping with a patience parameter P, which monitors performance on the test set and halts training if there's no improvement for P consecutive epochs, reverting the model to its best-performing state. This approach not only prevents overfitting but also ensures that the model retains its peak performance.\u003c/p\u003e \u003cp\u003eFor model interpretability analysis, we utilized a confusion matrix and ROC curve to assess the performance of the optimal model. The confusion matrix provides a clear view of the model's predictive accuracy, while the ROC curve offers an intuitive representation of the model's overall performance by comparing true positive and false positive rates across various thresholds. These methods validate the model's risk level predictions and enhance the interpretability of the results, thereby ensuring the reliability of our predictions.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Experimental Platform\u003c/h2\u003e \u003cp\u003eThis study was conducted on a computer equipped with an NVIDIA GPU RTX3050Ti, a CPU model AMD Ryzen 7 5800H, and 1.5TB of disk space. All experiments were based on the Python programming language. To build and train the MLP model, TensorFlow (2.18.0) and Keras (3.6.0) libraries were used. Data processing and analysis benefited from Pandas (2.2.3) and NumPy (1.24.4), while data visualization was performed using Matplotlib (3.5.1). Model optimization was achieved using Sklearn (1.5.2).\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e presents a comparison of the performance parameters of the MLP model with five other algorithms. Among these five algorithms, the one using LR for high-risk pregnancy prediction achieved the lowest performance, with an accuracy of 0.61 and precision of 0.59. In contrast, the RF algorithm demonstrated the highest performance for high-risk pregnancy prediction, with an accuracy of 0.78 and precision of 0.79. Compared with these five algorithms, the MLP model constructed in this study exhibited superior performance, achieving an accuracy of 0.81 and precision of 0.82.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison of the Performance of MLP with Five Other Machine Learning Algorithms\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAlgorithm\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAccuracy\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eF1-Score\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMLP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.82\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.60\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDT\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.74\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.78\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eXGBoost\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.76\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSVM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.62\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e illustrates that the MLP model performs well across different risk categories, particularly in the high-risk category, achieving an accuracy, recall, and F1 score of 0.91. The performance in the medium-risk category is slightly lower, with an accuracy and recall of 0.80 and 0.83, respectively, and an F1 score of 0.81. The low-risk category has slightly lower accuracy, recall, and F1 scores of 0.77, 0.73, and 0.75, respectively. The overall accuracy is 0.82, indicating excellent overall performance of the model.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThis is Prediction Performance of MLP Model on Pregnancy Risk Levels\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-Score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eAUC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSample size\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHigh Risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMid Risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.83\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLow Risk\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e47\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.82\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e90\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe normalized confusion matrix shows the performance of the MLP model in predicting risk levels in high-risk pregnancies, covering high, medium, and low risk levels. The model excels in high-risk prediction with an accuracy of 91%, with misclassification rates of 2% for low risk and 7% for medium risk. The accuracy for low-risk prediction is 83%, with a 14% misclassification rate for medium risk. Medium-risk prediction accuracy stands at 73%, with misclassification rates of 24% for low risk and 3% for high risk. Overall, the model is reliable in predicting pregnancy risk for pregnant women.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe ROC curve analysis shows that the MLP model achieves an AUC value of 0.99 for the high-risk category when predicting pregnancy risk levels, indicating near-perfect identification. The ROC curve closely aligns with the top left corner, demonstrating the ability to achieve a high true positive rate at a very low false positive rate.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"4. Discussion","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Accurate Prediction and Treatment Options for Pregnancy Risk are Crucial\u003c/h2\u003e \u003cp\u003eThis study aims to develop a machine learning model for predicting high-risk pregnancy in expectant mothers. By analyzing the health data of pregnant women, the model can accurately assess pregnancy risk levels, demonstrating excellent accuracy and efficiency\u003csup\u003e14\u003c/sup\u003e. This tool can support clinical nurses in making more precise risk assessments during evaluations, thereby enabling appropriate interventions to reduce pregnancy risks.\u003c/p\u003e \u003cp\u003eHigh-risk pregnancy refers to a pregnancy state that faces higher risks due to various high-risk factors (such as personal health issues, pregnancy complications, adverse environmental impacts, etc.)\u003csup\u003e1,2\u003c/sup\u003e during the pregnancy period. Such pregnancy conditions increase maternal and neonatal morbidity and mortality rates. Taking China as an example, with the development of society, the implementation of the universal two-child policy, and the popularization of assisted reproductive technology, the incidence of high-risk pregnancies is increasing year by year. Compared to normal pregnancies, high-risk pregnancies significantly increase the risk of adverse pregnancy outcomes, including preterm birth, low birth weight, neonatal complications, and death. Moreover, the diagnosis of high-risk pregnancy may lead to reduced coping ability, decreased well-being, and increased psychiatric symptoms in pregnant women, including stress, depression, and anxiety\u003csup\u003e15\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eTherefore, accurately and early identifying pregnancy risks and implementing effective management measures are crucial for improving maternal and infant health. Nurses, as the first medical team members to contact pregnant women and collect their basic information, play a critical role in the early identification and management of high-risk pregnancies\u003csup\u003e16\u003c/sup\u003e. However, since the health status of pregnant women may change over time, continuous monitoring by nurses is required, which is time-consuming and labor-intensive. Therefore, developing a simple yet accurate tool for identifying high-risk pregnancies is particularly important for ensuring the health and safety of mothers and newborns.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e4.2 Artificial Intelligence-Assisted Diagnosis and Treatment of Pregnancy Risk Becomes Possible\u003c/h2\u003e \u003cp\u003eHigh-risk pregnancies pose significant health risks to mothers and newborns, involving various complex factors such as advanced maternal age, multiple pregnancies, and pregnancy complications, leading to increased rates of difficult labor and cesarean sections, as well as an increase in neonatal health issues\u003csup\u003e17\u003c/sup\u003e. These situations place high professional demands on medical and nursing staff, emphasizing the need for rigorous and professional measures. The World Health Organization points out that most deaths related to pregnancy and childbirth can be prevented through timely identification and response to pregnancy risks\u003csup\u003e18\u003c/sup\u003e. Timely intervention in pregnancy risks and quality healthcare services are key.\u003c/p\u003e \u003cp\u003eIn 2017, China implemented a pregnancy risk assessment and management system, adopting a five-color grading system to assess maternal risk levels and adjust medical resource allocation accordingly, effectively reducing adverse outcomes of high-risk pregnancies\u003csup\u003e19\u003c/sup\u003e. However, traditional risk assessment methods have issues with large workloads and low efficiency.\u003c/p\u003e \u003cp\u003eThe machine learning method based on the MLP proposed in this study demonstrates remarkable performance in predicting high-risk pregnancies. Compared with other methods, it achieves an accuracy rate of up to 91% in predicting high-risk cases. Moreover, the method is highly efficient, with the capability to process up to 500 sets of data per second. This method not only improves the efficiency and accuracy of risk assessment but also reduces the workload on medical staff and the demand for medical resources, showing great potential in optimizing pregnancy risk management using advanced technology.\u003c/p\u003e \u003cp\u003eAdditionally, by utilizing the SMOTE algorithm\u003csup\u003e20\u003c/sup\u003e and early stopping mechanisms\u003csup\u003e21\u003c/sup\u003e, our model has demonstrated remarkable generalization capabilities. It effectively addresses the issue of data imbalance and prevents overfitting. This ensures that the model performs well not only on the training data but also maintains high accuracy and reliability when applied to unseen data.\u003c/p\u003e \u003cp\u003eThis study is innovative not only in its technical approach but also in its practical application. By accurately predicting the risks associated with high-risk pregnancies, our model serves as an important decision-support tool for clinical practice. It enables healthcare professionals to take preemptive interventions, thereby reducing the risk of complications for both mothers and infants\u003csup\u003e12\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e"},{"header":"5. Conclusions","content":"\u003cp\u003eThis study successfully developed a machine learning based high-risk pregnancy prediction model, which estimates pregnancy risk by analyzing the health data of pregnant women, with an accuracy rate of up to 91%, and can accurately assess the level of pregnancy risk. At the same time, it also has a fast prediction speed, which not only improves the efficiency of pregnancy risk assessment, but also reduces the workload of medical personnel and the demand for medical resources, demonstrating the huge potential of using advanced technology to optimize pregnancy risk management.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eMHRD, Maternal Health Risk Dataset; MLP, multilayer perceptron; LR, Logistic Regression; DT, Decision Tree; RF, Random Forest; XGBoost, eXtreme Gradient Boosting; SVM, Support Vector Machine; ROC, receiver operating characteristic.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAvailability of Data and Materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data used in this study originates from Bangladesh and is titled \u0026quot;Maternal Health Risk Data,\u0026quot; which can be accessed through the following link: https://www.kaggle.com/datasets/csafrit2/maternal-health-risk-data. This dataset is publicly available and can be used without additional permission. For any further inquiries regarding the dataset or other materials used in this study, please contact the corresponding author at the email address [email protected].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor Contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePXY\u0026mdash;prepared the first draft. WJZ and ZGC\u0026mdash;revised the manuscript. CLL\u0026mdash;Provide assistance in data analysis, ZWL\u0026mdash;edited and finalized the manuscript. All authors contributed to editorial changes in the manuscript. All authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Approval and Consent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSince the data for this study is sourced from open-source datasets, ethical review is not required.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgment\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis research was funded by the Shandong Province Medical Staff Science and Technology Innovation Program Project (Project No.: SDYWZGKCJH2022056) and the Shandong Nursing Association Scientific Research Project (Project No.: SDHLKT202202).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of Interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no conflict of interest.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003ePhillips, S. E., Celi, A. C., Margo, J., Wehbe, A., Karlage, A., \u0026amp; Zera, C. A. Improving Care Beyond Birth: A Qualitative Study of Postpartum Care After High-Risk Pregnancy. \u003cem\u003eJ Womens Health\u003c/em\u003e. \u003cstrong\u003e33\u003c/strong\u003e, 1720-1729. https://doi.org/10.1089/jwh.2024.0108 (2024).\u003c/li\u003e\n\u003cli\u003eMavreli, D., Theodora, M., \u0026amp; Kolialexi, A. Known biomarkers for monitoring pregna-ncy complications. \u003cem\u003eExpert Rev. Mol. Diagn\u003c/em\u003e. \u003cstrong\u003e21\u003c/strong\u003e, 1115-1117. https://doi.org/10.1080/14737159.2021.1971078(2021).\u003c/li\u003e\n\u003cli\u003eDewi, N. A., Yetti, K., \u0026amp; Nuraini, T. Nurses\u0026rsquo; critical thinking and clinical decision-making abilities are correlated with the quality of nursing handover. \u003cem\u003eEnferm Clin\u003c/em\u003e \u003cstrong\u003e31\u003c/strong\u003e, S271-S275. https://doi.org/10.1016/j.enfcli.2020.09.014 (2021).\u003c/li\u003e\n\u003cli\u003eKovacheva, V. P., Eberhard, B. W., Cohen, R. Y., Maher, M., Saxena, R., \u0026amp; Gray, K. J. Preeclampsia prediction using machine learning and polygenic risk scores from cl-inical and genetic risk factors in early and late pregnancies. \u003cem\u003eHypertension\u003c/em\u003e. \u003cstrong\u003e81\u003c/strong\u003e, 264-272. https://doi.org/10.1161/HYPERTENSIONAHA.123.21053 (2024).\u003c/li\u003e\n\u003cli\u003eChu, R., Chen, W., Song, G., Yao, S., Xie, L., Song, L., ... \u0026amp; Kong, B. Predicting the risk of adverse events in pregnant women with congenital heart disease. \u003cem\u003eJ Am Heart Assoc\u003c/em\u003e. \u003cstrong\u003e9\u003c/strong\u003e, e016371. https://doi.org/10.1161/JAHA.120.016371 (2020).\u003c/li\u003e\n\u003cli\u003eMontgomery-Csob\u0026aacute;n, T., Kavanagh, K., Murray, P., Robertson, C., Barry, S. J., Ukah, U. V., ... \u0026amp; Widmer, M. Machine learning-enabled maternal risk assessment for women with pre-eclampsia (the PIERS-ML model): a modelling study. \u003cem\u003eLancet Digit Health\u003c/em\u003e. \u003cstrong\u003e6\u003c/strong\u003e, e238-e250. https://doi.org/10.1016/S2589-7500(23)00267-4 (2024).\u003c/li\u003e\n\u003cli\u003eBowe, A. K., Lightbody, G., Staines, A., Murray, D. M., \u0026amp; Norman, M. Prediction of 2-year cognitive outcomes in very preterm infants using machine learning methods. \u003cem\u003eJAMA Network Open\u003c/em\u003e. \u003cstrong\u003e6\u003c/strong\u003e, e2349111-e2349111. https://doi.org/10.1001/jamanetworkopen.2023.49111(2023).\u003c/li\u003e\n\u003cli\u003eDeng, Z., Duan, L., \u0026amp; Wang, K. Advancing comprehensive care for high-risk pregna-ncies: integrating social and clinical perspectives. \u003cem\u003eAm J Obstet Gynecol\u003c/em\u003e. https://doi.org/10.1016/j.ajog.2025.02.002(2025).\u003c/li\u003e\n\u003cli\u003eCorrea-de-Araujo, R., \u0026amp; Yoon, S. S. Clinical outcomes in high-risk pregnancies due to advanced maternal age. \u003cem\u003eJ Womens Health.\u003c/em\u003e \u003cstrong\u003e30\u003c/strong\u003e, 160-167. https://doi.org/10.1089/jwh.2020.8860 (2021).\u003c/li\u003e\n\u003cli\u003eCooray, S. D., Boyle, J. A., Soldatos, G., Allotey, J., Wang, H., Fernandez-Felix, B. M., ... \u0026amp; Teede, H. J. Development, validation and clinical utility of a risk prediction model for adverse pregnancy outcomes in women with gestational diabetes: The PeRSonal GDM model. \u003cem\u003eEClinicalMedicine\u003c/em\u003e.\u003cem\u003e52\u003c/em\u003e.https://doi.org/10.1016/j.eclinm.2022.101637 (2022).\u003c/li\u003e\n\u003cli\u003eLi, S., Wang, Z., Vieira, L. A., Zheutlin, A. B., Ru, B., Schadt, E., ... \u0026amp; Li, L. Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data. \u003cem\u003eNPJ Digit. Med\u003c/em\u003e.\u003cstrong\u003e 5\u003c/strong\u003e 68. https://doi.org/10.1038/s41746-022-00612-x(2022).\u003c/li\u003e\n\u003cli\u003eLi, M., Grewal, J., Hinkle, S. N., Yisahak, S. F., Grobman, W. A., Newman, R. B., ... \u0026amp; Zhang, C. Healthy dietary patterns and common pregnancy complications: a prospective and longitudinal study. \u003cem\u003eAm. J. Clin. Nutr.\u003c/em\u003e \u003cstrong\u003e114\u003c/strong\u003e, 1229-1237. https://doi.org/10.1093/ajcn/nqab145 (2021).\u003c/li\u003e\n\u003cli\u003eAn, L., Wang, L., \u0026amp; Li, Y. HEA-Net: Attention and MLP hybrid encoder architecture for medical image segmentation. \u003cem\u003eSensors\u003c/em\u003e. \u003cstrong\u003e22\u003c/strong\u003e, 7024. https://doi.org/10.3390/s22187024 (2022).\u003c/li\u003e\n\u003cli\u003eAl Mashrafi, S. S., Tafakori, L., \u0026amp; Abdollahian, M. Predicting maternal risk level using machine learning models. \u003cem\u003eBMC PREGNANCY CHILDB.\u003c/em\u003e \u003cstrong\u003e24\u003c/strong\u003e, 820.https://doi.org/10.1186/s12884-024-07030-9 (2024).\u003c/li\u003e\n\u003cli\u003eWilliamson, S. P., Moffitt, R. L., Broadbent, J., Neumann, D. L., \u0026amp; Hamblin, P. S. Coping, wellbeing, and psychopathology during high-risk pregnancy: A systematic review. \u003cem\u003eMidwifery\u003c/em\u003e. \u003cstrong\u003e116\u003c/strong\u003e, 103556. https://doi.org/10.1016/j.midw.2022.103556 (2023).\u003c/li\u003e\n\u003cli\u003eTahmasebi T. High-risk pregnancy: Managing complications for a safe and healthy outcome. \u003cem\u003eJ Preg Neonatal Med\u003c/em\u003e. \u003cstrong\u003e8\u003c/strong\u003e, 226.https://doi.org/10.35841/aapnm-8.5.226 (2024)\u003c/li\u003e\n\u003cli\u003eNazari, M., Moayed Rezaie, S., Yaseri, F., Sadr, H., \u0026amp; Nazari, E. Design and analysis of a telemonitoring system for high-risk pregnant women in need of special care or attention. \u003cem\u003eBMC Pregnancy and Childbirth\u003c/em\u003e. \u003cstrong\u003e24\u003c/strong\u003e, 817. https://doi.org/10.1186/s12884-024-07019-4(2024).\u003c/li\u003e\n\u003cli\u003eLattof, S. R., Tun\u0026ccedil;alp, \u0026Ouml;., Moran, A. C., Bucagu, M., Chou, D., Diaz, T., \u0026amp; G\u0026uuml;lmezoglu, A. M. Developing measures for WHO recommendations on antenatal care for a positive pregnancy experience: a conceptual framework and scoping review. \u003cem\u003eBMJ open\u003c/em\u003e. \u003cstrong\u003e9\u003c/strong\u003e, e024130. https://doi.org/10.1136/bmjopen-2018-024130 (2020).\u003c/li\u003e\n\u003cli\u003eLiu, Y., Luo, R., \u0026amp; Huang, A. The distribution of pregnant women with different pregnancy risks\u0026mdash;4 cities, China, 2019. \u003cem\u003eChina CDC Weekly\u003c/em\u003e. \u003cstrong\u003e3\u003c/strong\u003e, 50.https://doi.org/10.46234/ccdcw2021.016 (2021).\u003c/li\u003e\n\u003cli\u003eKosolwattana, T., Liu, C., Hu, R., Han, S., Chen, H., \u0026amp; Lin, Y. A self-inspected adaptive SMOTE algorithm (SASMOTE) for highly imbalanced data classification in healthcare. \u003cem\u003eBio Data Mining\u003c/em\u003e. \u003cstrong\u003e16\u003c/strong\u003e, 15. https://doi.org/10.1186/s13040-023-00330-4(2023).\u003c/li\u003e\n\u003cli\u003eNguyen, M. H., Abbass, H. A., \u0026amp; McKay, R. I. Stopping criteria for ensemble of evolutionary artificial neural networks. \u003cem\u003eAppl. Soft Comput\u003c/em\u003e.\u003cstrong\u003e 6\u003c/strong\u003e, 100-107. https://doi.org/10.1016/j.asoc.2004.12.005 (2005).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"High-Risk Pregnancy, Machine Learning, Multilayer Perceptron, Nursing","lastPublishedDoi":"10.21203/rs.3.rs-5869497/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5869497/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study explores the application of machine learning algorithms in predicting high-risk pregnancy among expectant mothers, aiming to construct an efficient predictive model to improve maternal health management. The study is based on the Maternal Health Risk Dataset (MHRD) from Bangladesh, covering multiple hospitals, community clinics, and maternal healthcare centers, and encompassing health data from 1,014 pregnant women. Six machine learning algorithms\u0026mdash;Multilayer Perceptron (MLP), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)\u0026mdash;are employed to construct predictive models. It is worth noting that MLP demonstrates superior performance compared with the other five algorithms. By applying the MLP method, the study successfully established an efficient pregnancy risk prediction model. The model evaluation results indicate that it has high accuracy in predicting pregnancy risks, with an overall accuracy rate of 82%, and particularly high accuracy in high-risk predictions, reaching 91%. With the computational support of an NVIDIA GPU RTX3050Ti, the model demonstrated excellent data processing capabilities, capable of predicting and processing 500 sets of data items per second. This study not only showcases the enormous potential of machine learning technology in the healthcare field, especially in the rapid and accurate identification of high-risk pregnancies, providing a powerful decision-support tool for medical professionals, but also offers significant reference value for future research in this area.\u003c/p\u003e","manuscriptTitle":"Prediction of High-Risk Pregnancy Based on Machine Learning Algorithms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-02 06:23:08","doi":"10.21203/rs.3.rs-5869497/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-04-28T11:05:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-21T10:05:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-21T08:55:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"03969e4b-e64f-42ed-af82-8aafc29449c3","owner":[],"postedDate":"May 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":47783427,"name":"Health sciences/Medical research"},{"id":47783428,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2025-05-05T16:02:18+00:00","versionOfRecord":{"articleIdentity":"rs-5869497","link":"https://doi.org/10.1038/s41598-025-00450-3","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-05-04 15:57:47","publishedOnDateReadable":"May 4th, 2025"},"versionCreatedAt":"2025-05-02 06:23:08","video":"","vorDoi":"10.1038/s41598-025-00450-3","vorDoiUrl":"https://doi.org/10.1038/s41598-025-00450-3","workflowStages":[]},"version":"v1","identity":"rs-5869497","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5869497","identity":"rs-5869497","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}