Machine learning in a real-world PFO study: analysis of data from multi-centers in China
Abstract Purpose The association of patent foreman ovale (PFO) and cryptogenic stroke has been studied for years. Although device closure overall decreases the risk for recurrent stroke, treatment effects varied across different studies. In this study, we aimed to detect sub-clusters in post-closure...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-11-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-02048-5 |
| _version_ | 1797986702570029056 |
|---|---|
| author | Dongling Luo Ziyang Yang Gangcheng Zhang Qunshan Shen Hongwei Zhang Junxing Lai Hui Hu Jianxin He Shulin Wu Caojin Zhang |
| author_facet | Dongling Luo Ziyang Yang Gangcheng Zhang Qunshan Shen Hongwei Zhang Junxing Lai Hui Hu Jianxin He Shulin Wu Caojin Zhang |
| author_sort | Dongling Luo |
| collection | DOAJ |
| description | Abstract Purpose The association of patent foreman ovale (PFO) and cryptogenic stroke has been studied for years. Although device closure overall decreases the risk for recurrent stroke, treatment effects varied across different studies. In this study, we aimed to detect sub-clusters in post-closure PFO patients and identify potential predictors for adverse outcomes. Methods We analyzed patients with embolic stroke of undetermined sources and PFO from 7 centers in China. Machine learning and Cox regression analysis were used. Results Using unsupervised hierarchical clustering on principal components, two main clusters were identified and a total of 196 patients were included. The average age was 42.7 (12.37) years and 64.80% (127/196) were female. During a median follow-up of 739 days, 12 (6.9%) adverse events happened, including 6 (3.45%) recurrent stroke, 5 (2.87%) transient ischemic attack (TIA) and one death (0.6%). Compared to cluster 1 (n = 77, 39.20%), patients in cluster 2 (n = 119, 60.71%) were more likely to be male, had higher systolic and diastolic blood pressure, higher body mass index, lower high-density lipoprotein cholesterol and increased proportion of presence of atrial septal aneurysm. Using random forest survival (RFS) analysis, eight top ranking features were selected and used for prediction model construction. As a result, the RFS model outperformed the traditional Cox regression model (C-index: 0.87 vs. 0.54). Conclusions There were 2 main clusters in post-closure PFO patients. Traditional cardiovascular profiles remain top ranking predictors for future recurrence of stroke or TIA. However, whether maximizing the management of these factors would provide extra benefits warrants further investigations. |
| first_indexed | 2024-04-11T07:36:13Z |
| format | Article |
| id | doaj.art-3bbd88ae53944503a38c94a264556394 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-11T07:36:13Z |
| publishDate | 2022-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-3bbd88ae53944503a38c94a2645563942022-12-22T04:36:43ZengBMCBMC Medical Informatics and Decision Making1472-69472022-11-012211810.1186/s12911-022-02048-5Machine learning in a real-world PFO study: analysis of data from multi-centers in ChinaDongling Luo0Ziyang Yang1Gangcheng Zhang2Qunshan Shen3Hongwei Zhang4Junxing Lai5Hui Hu6Jianxin He7Shulin Wu8Caojin Zhang9Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical SciencesGuangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical SciencesZhongnan Hospital of Wuhan UniversityWuhan Asian Heart HospitalHubei Huiyi Cardiovascular CenterJiang Men Central HospitalThe First People’s Hospital of FoshanGeneral Hospital of Southern Theatre Command of PLAGuangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical SciencesGuangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical SciencesAbstract Purpose The association of patent foreman ovale (PFO) and cryptogenic stroke has been studied for years. Although device closure overall decreases the risk for recurrent stroke, treatment effects varied across different studies. In this study, we aimed to detect sub-clusters in post-closure PFO patients and identify potential predictors for adverse outcomes. Methods We analyzed patients with embolic stroke of undetermined sources and PFO from 7 centers in China. Machine learning and Cox regression analysis were used. Results Using unsupervised hierarchical clustering on principal components, two main clusters were identified and a total of 196 patients were included. The average age was 42.7 (12.37) years and 64.80% (127/196) were female. During a median follow-up of 739 days, 12 (6.9%) adverse events happened, including 6 (3.45%) recurrent stroke, 5 (2.87%) transient ischemic attack (TIA) and one death (0.6%). Compared to cluster 1 (n = 77, 39.20%), patients in cluster 2 (n = 119, 60.71%) were more likely to be male, had higher systolic and diastolic blood pressure, higher body mass index, lower high-density lipoprotein cholesterol and increased proportion of presence of atrial septal aneurysm. Using random forest survival (RFS) analysis, eight top ranking features were selected and used for prediction model construction. As a result, the RFS model outperformed the traditional Cox regression model (C-index: 0.87 vs. 0.54). Conclusions There were 2 main clusters in post-closure PFO patients. Traditional cardiovascular profiles remain top ranking predictors for future recurrence of stroke or TIA. However, whether maximizing the management of these factors would provide extra benefits warrants further investigations.https://doi.org/10.1186/s12911-022-02048-5Machine learningPatent foreman ovaleDevice closureRecurrent strokeTransient ischemic attack |
| spellingShingle | Dongling Luo Ziyang Yang Gangcheng Zhang Qunshan Shen Hongwei Zhang Junxing Lai Hui Hu Jianxin He Shulin Wu Caojin Zhang Machine learning in a real-world PFO study: analysis of data from multi-centers in China BMC Medical Informatics and Decision Making Machine learning Patent foreman ovale Device closure Recurrent stroke Transient ischemic attack |
| title | Machine learning in a real-world PFO study: analysis of data from multi-centers in China |
| title_full | Machine learning in a real-world PFO study: analysis of data from multi-centers in China |
| title_fullStr | Machine learning in a real-world PFO study: analysis of data from multi-centers in China |
| title_full_unstemmed | Machine learning in a real-world PFO study: analysis of data from multi-centers in China |
| title_short | Machine learning in a real-world PFO study: analysis of data from multi-centers in China |
| title_sort | machine learning in a real world pfo study analysis of data from multi centers in china |
| topic | Machine learning Patent foreman ovale Device closure Recurrent stroke Transient ischemic attack |
| url | https://doi.org/10.1186/s12911-022-02048-5 |
| work_keys_str_mv | AT donglingluo machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT ziyangyang machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT gangchengzhang machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT qunshanshen machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT hongweizhang machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT junxinglai machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT huihu machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT jianxinhe machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT shulinwu machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina AT caojinzhang machinelearninginarealworldpfostudyanalysisofdatafrommulticentersinchina |