A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia
Background: To construct a predictive model for fetal growth restriction (FGR) in preeclampsia (PE) patients using extreme Gradient Boosting (XGBoost) algorithm. Methods: A prospective study was conducted in the Obstetrics Department of Wuming Hospital from October 1, 2016, to October 1, 2021. A tot...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IMR Press
2023-08-01
|
| Series: | Clinical and Experimental Obstetrics & Gynecology |
| Subjects: | |
| Online Access: | https://www.imrpress.com/journal/CEOG/50/8/10.31083/j.ceog5008172 |
| _version_ | 1797733125896273920 |
|---|---|
| author | Haijuan Li Sumei Wang Chunyu Zhan |
| author_facet | Haijuan Li Sumei Wang Chunyu Zhan |
| author_sort | Haijuan Li |
| collection | DOAJ |
| description | Background: To construct a predictive model for fetal growth restriction (FGR) in preeclampsia (PE) patients using extreme Gradient Boosting (XGBoost) algorithm. Methods: A prospective study was conducted in the Obstetrics Department of Wuming Hospital from October 1, 2016, to October 1, 2021. A total of 303 preeclampsia patients were divided into two groups based on FGR status (restricted vs. unrestricted group). The clinical data and laboratory indicators between the two groups were compared. Logistics multivariate analysis and the XGBoost algorithm model were used to identify the risk factors for FGR in preeclampsia. Moreover, we used the receiver operating characteristic (ROC) curve to verify the accuracy of the XGBoost algorithm model. Results: Multivariate analysis and XGBoost algorithm modeling could predict the risk factors for FGR using clinical data and laboratory indicators. ROC analysis revealed that the area under the curve of the XGBoost algorithm model was 0.851, indicating a good fit. Conclusions: The XGBoost algorithm model can predict the occurrence of FGR in preeclampsia patients. The top three risk factors, triglyceride (TG), total cholesterol (TC), and lipoprotein (a) [Lp (a)], can be used as important predictors of poor patient prognosis in clinical settings. |
| first_indexed | 2024-03-12T12:23:38Z |
| format | Article |
| id | doaj.art-5bb516b0718d401880b9e5b66e78a600 |
| institution | Directory Open Access Journal |
| issn | 0390-6663 |
| language | English |
| last_indexed | 2024-03-12T12:23:38Z |
| publishDate | 2023-08-01 |
| publisher | IMR Press |
| record_format | Article |
| series | Clinical and Experimental Obstetrics & Gynecology |
| spelling | doaj.art-5bb516b0718d401880b9e5b66e78a6002023-08-30T05:21:34ZengIMR PressClinical and Experimental Obstetrics & Gynecology0390-66632023-08-0150817210.31083/j.ceog5008172S0390-6663(23)02116-4A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with PreeclampsiaHaijuan Li0Sumei Wang1Chunyu Zhan2Department of Obstetrics, Wuming Hospital Affiliated to Guangxi Medical University, 530100 Nanning, Guangxi, ChinaDepartment of Obstetrics, The First Affiliated Hospital of Guangxi Medical University, 530021 Nanning, Guangxi, ChinaDepartment of Obstetrics, The First Affiliated Hospital of Guangxi Medical University, 530021 Nanning, Guangxi, ChinaBackground: To construct a predictive model for fetal growth restriction (FGR) in preeclampsia (PE) patients using extreme Gradient Boosting (XGBoost) algorithm. Methods: A prospective study was conducted in the Obstetrics Department of Wuming Hospital from October 1, 2016, to October 1, 2021. A total of 303 preeclampsia patients were divided into two groups based on FGR status (restricted vs. unrestricted group). The clinical data and laboratory indicators between the two groups were compared. Logistics multivariate analysis and the XGBoost algorithm model were used to identify the risk factors for FGR in preeclampsia. Moreover, we used the receiver operating characteristic (ROC) curve to verify the accuracy of the XGBoost algorithm model. Results: Multivariate analysis and XGBoost algorithm modeling could predict the risk factors for FGR using clinical data and laboratory indicators. ROC analysis revealed that the area under the curve of the XGBoost algorithm model was 0.851, indicating a good fit. Conclusions: The XGBoost algorithm model can predict the occurrence of FGR in preeclampsia patients. The top three risk factors, triglyceride (TG), total cholesterol (TC), and lipoprotein (a) [Lp (a)], can be used as important predictors of poor patient prognosis in clinical settings.https://www.imrpress.com/journal/CEOG/50/8/10.31083/j.ceog5008172fetal growth restrictionmachine learningmultivariate analysispreeclampsiarisk factorsxgboost algorithm |
| spellingShingle | Haijuan Li Sumei Wang Chunyu Zhan A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia Clinical and Experimental Obstetrics & Gynecology fetal growth restriction machine learning multivariate analysis preeclampsia risk factors xgboost algorithm |
| title | A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia |
| title_full | A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia |
| title_fullStr | A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia |
| title_full_unstemmed | A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia |
| title_short | A New XGBoost Algorithm Based Prediction Model for Fetal Growth Restriction in Patients with Preeclampsia |
| title_sort | new xgboost algorithm based prediction model for fetal growth restriction in patients with preeclampsia |
| topic | fetal growth restriction machine learning multivariate analysis preeclampsia risk factors xgboost algorithm |
| url | https://www.imrpress.com/journal/CEOG/50/8/10.31083/j.ceog5008172 |
| work_keys_str_mv | AT haijuanli anewxgboostalgorithmbasedpredictionmodelforfetalgrowthrestrictioninpatientswithpreeclampsia AT sumeiwang anewxgboostalgorithmbasedpredictionmodelforfetalgrowthrestrictioninpatientswithpreeclampsia AT chunyuzhan anewxgboostalgorithmbasedpredictionmodelforfetalgrowthrestrictioninpatientswithpreeclampsia AT haijuanli newxgboostalgorithmbasedpredictionmodelforfetalgrowthrestrictioninpatientswithpreeclampsia AT sumeiwang newxgboostalgorithmbasedpredictionmodelforfetalgrowthrestrictioninpatientswithpreeclampsia AT chunyuzhan newxgboostalgorithmbasedpredictionmodelforfetalgrowthrestrictioninpatientswithpreeclampsia |