Predictive models of hypertensive disorders in pregnancy based on support vector machine algorithm
| Autor: | Lin Yang, Hongqing Jiang, Ge Sun, Mingzhou Xu, Dongmei Hao, Xuwen Li, Yimin Yang, Jing Shao, Anran Wang, Song Zhang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Pediatrics
Support vector machine algorithm Support Vector Machine Blood Pressure Early pregnancy factor 02 engineering and technology 0302 clinical medicine Pregnancy Risk Factors Prediction methods Early prediction Data Mining Hematologic Tests biology Epidemiological Factors machine learning model research Radial Artery Female Algorithms Research Article Information Systems Adult medicine.medical_specialty 0206 medical engineering Biomedical Engineering Biophysics Gestational Age Health Informatics Bioengineering Pulse Wave Analysis Biomaterials 03 medical and health sciences Predictive Value of Tests medicine Humans business.industry Body Weight Hemodynamics Hypertension Pregnancy-Induced medicine.disease 020601 biomedical engineering Support vector machine Early Diagnosis Socioeconomic Factors biology.protein business 030217 neurology & neurosurgery Predictive modelling |
| Zdroj: | Technology and Health Care |
| ISSN: | 1878-7401 0928-7329 |
| DOI: | 10.3233/thc-209018 |
| Popis: | BACKGROUND: The risk factors of hypertensive disorders in pregnancy (HDP) could be summarized into three categories: clinical epidemiological factors, hemodynamic factors and biochemical factors. OBJECTIVE: To establish models for early prediction and intervention of HDP. METHODS: This study used the three types of risk factors and support vector machine (SVM) to establish prediction models of HDP at different gestational weeks. RESULTS: The average accuracy of the model was gradually increased when the pregnancy progressed, especially in the late pregnancy 28–34 weeks and ⩾ 35 weeks, it reached more than 92%. CONCLUSION: Multi-risk factors combined with dynamic gestational weeks’ prediction of HDP based on machine learning was superior to static and single-class conventional prediction methods. Multiple continuous tests could be performed from early pregnancy to late pregnancy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|