A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics
Cardiovascular disease (CVD) risk prediction shows great significance for disease diagnosis and treatment, especially early intervention for CVD, which has a direct impact on preventing and reducing adverse outcomes. In this paper, we collected clinical indicators and outcomes of 14,832 patients wit...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/2/893 |
| _version_ | 1797446617327992832 |
|---|---|
| author | Mengxiao Peng Fan Hou Zhixiang Cheng Tongtong Shen Kaixian Liu Cai Zhao Wen Zheng |
| author_facet | Mengxiao Peng Fan Hou Zhixiang Cheng Tongtong Shen Kaixian Liu Cai Zhao Wen Zheng |
| author_sort | Mengxiao Peng |
| collection | DOAJ |
| description | Cardiovascular disease (CVD) risk prediction shows great significance for disease diagnosis and treatment, especially early intervention for CVD, which has a direct impact on preventing and reducing adverse outcomes. In this paper, we collected clinical indicators and outcomes of 14,832 patients with cardiovascular disease in Shanxi, China, and proposed a cardiovascular disease risk prediction model, XGBH, based on key contributing characteristics to perform risk scoring of patients’ clinical outcomes. The XGBH risk prediction model had high accuracy, with a significant improvement compared to the baseline risk score (AUC = 0.80 vs. AUC = 0.65). At the same time, we found that with the addition of conventional biometric variables, the accuracy of the model’s CVD risk prediction would also be improved. Finally, we designed a simpler model to quantify disease risk based on only three questions answered by the patient, with only a modest reduction in accuracy (AUC = 0.79), and providing a valid risk assessment for CVD. Overall, our models may allow early-stage intervention in high-risk patients, as well as a cost-effective screening approach. Further prospective studies and studies in other populations are needed to assess the actual clinical effect of XGBH risk prediction models. |
| first_indexed | 2024-03-09T13:44:09Z |
| format | Article |
| id | doaj.art-57b0909497bb4ab98c55d60a2624b35a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:44:09Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-57b0909497bb4ab98c55d60a2624b35a2023-11-30T21:03:02ZengMDPI AGApplied Sciences2076-34172023-01-0113289310.3390/app13020893A Cardiovascular Disease Risk Score Model Based on High Contribution CharacteristicsMengxiao Peng0Fan Hou1Zhixiang Cheng2Tongtong Shen3Kaixian Liu4Cai Zhao5Wen Zheng6Institute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaInstitute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaInstitute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaInstitute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaInstitute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaInstitute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaInstitute of Public-Safety and Big Data, College of Data Science, Taiyuan University of Technology, University Street, Yuci District, Jinzhong 030600, ChinaCardiovascular disease (CVD) risk prediction shows great significance for disease diagnosis and treatment, especially early intervention for CVD, which has a direct impact on preventing and reducing adverse outcomes. In this paper, we collected clinical indicators and outcomes of 14,832 patients with cardiovascular disease in Shanxi, China, and proposed a cardiovascular disease risk prediction model, XGBH, based on key contributing characteristics to perform risk scoring of patients’ clinical outcomes. The XGBH risk prediction model had high accuracy, with a significant improvement compared to the baseline risk score (AUC = 0.80 vs. AUC = 0.65). At the same time, we found that with the addition of conventional biometric variables, the accuracy of the model’s CVD risk prediction would also be improved. Finally, we designed a simpler model to quantify disease risk based on only three questions answered by the patient, with only a modest reduction in accuracy (AUC = 0.79), and providing a valid risk assessment for CVD. Overall, our models may allow early-stage intervention in high-risk patients, as well as a cost-effective screening approach. Further prospective studies and studies in other populations are needed to assess the actual clinical effect of XGBH risk prediction models.https://www.mdpi.com/2076-3417/13/2/893cardiovascular diseasemachine learningrisk score |
| spellingShingle | Mengxiao Peng Fan Hou Zhixiang Cheng Tongtong Shen Kaixian Liu Cai Zhao Wen Zheng A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics Applied Sciences cardiovascular disease machine learning risk score |
| title | A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics |
| title_full | A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics |
| title_fullStr | A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics |
| title_full_unstemmed | A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics |
| title_short | A Cardiovascular Disease Risk Score Model Based on High Contribution Characteristics |
| title_sort | cardiovascular disease risk score model based on high contribution characteristics |
| topic | cardiovascular disease machine learning risk score |
| url | https://www.mdpi.com/2076-3417/13/2/893 |
| work_keys_str_mv | AT mengxiaopeng acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT fanhou acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT zhixiangcheng acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT tongtongshen acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT kaixianliu acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT caizhao acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT wenzheng acardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT mengxiaopeng cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT fanhou cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT zhixiangcheng cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT tongtongshen cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT kaixianliu cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT caizhao cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics AT wenzheng cardiovasculardiseaseriskscoremodelbasedonhighcontributioncharacteristics |