Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus
BackgroundThis study aimed to apply four machine learning algorithms to develop the optimal model to predict decline in platelet count (DPC) after interventional closure in children with patent ductus arteriosus (PDA).MethodsData from children with PDA who underwent successful transcatheter closure...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-02-01
|
| Series: | Frontiers in Pediatrics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fped.2025.1519002/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832087110303088640 |
|---|---|
| author | Song-Yue Zhang Yi-Dong Zhang Hao Li Qiao-Yu Wang Qiao-Fang Ye Xun-Min Wang Tian-He Xia Yue-E He Xing Rong Ting-Ting Wu Rong-Zhou Wu |
| author_facet | Song-Yue Zhang Yi-Dong Zhang Hao Li Qiao-Yu Wang Qiao-Fang Ye Xun-Min Wang Tian-He Xia Yue-E He Xing Rong Ting-Ting Wu Rong-Zhou Wu |
| author_sort | Song-Yue Zhang |
| collection | DOAJ |
| description | BackgroundThis study aimed to apply four machine learning algorithms to develop the optimal model to predict decline in platelet count (DPC) after interventional closure in children with patent ductus arteriosus (PDA).MethodsData from children with PDA who underwent successful transcatheter closure at the Second Affiliated Hospital of Wenzhou Medical University and Yuying Children's Hospital from January 2016, to December 2022, were collected. The cohort data were split into training and testing sets. DPC following the intervention is defined as a percentage DPC ≥25% [(baseline platelet count−nadir platelet count)/baseline platelet count]. The extra tree algorithm was used for feature selection and four ML algorithms [random forest (RF), adaptive boosting, extreme gradient boosting, and logistic regression] were established. Moreover, SHapley Additive exPlanation (SHAP) to explain the importance of features and the ML models.ResultsThis study included 330 children who underwent successful transcatheter closure of PDA, of which 113 (34.2%) experienced DPC. After 62 clinical features were considered, the extra tree algorithm selected six clinical features to build the ML models. Amongst the four ML algorithms, the RF model achieved the greatest AUC. SHAP analysis revealed that pulmonary artery systolic pressure, size of defect and weight were the top three most important clinical features in the RF model. Furthermore, clinical descriptions of two children with PDA, with accurate predictions, and explanations of the prediction results were provided.ConclusionIn this study, an ML model (RF) capable of predicting post-intervention DPC in children with PDA undergoing transcatheter closure was established. |
| format | Article |
| id | doaj-art-38dfcdb8b7d24b6789935cf2f9191c1f |
| institution | Kabale University |
| issn | 2296-2360 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pediatrics |
| spelling | doaj-art-38dfcdb8b7d24b6789935cf2f9191c1f2025-02-06T07:09:18ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602025-02-011310.3389/fped.2025.15190021519002Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosusSong-Yue Zhang0Yi-Dong Zhang1Hao Li2Qiao-Yu Wang3Qiao-Fang Ye4Xun-Min Wang5Tian-He Xia6Yue-E He7Xing Rong8Ting-Ting Wu9Rong-Zhou Wu10Children's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaFujian Children's Hospital, Fujian, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaChildren's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, ChinaBackgroundThis study aimed to apply four machine learning algorithms to develop the optimal model to predict decline in platelet count (DPC) after interventional closure in children with patent ductus arteriosus (PDA).MethodsData from children with PDA who underwent successful transcatheter closure at the Second Affiliated Hospital of Wenzhou Medical University and Yuying Children's Hospital from January 2016, to December 2022, were collected. The cohort data were split into training and testing sets. DPC following the intervention is defined as a percentage DPC ≥25% [(baseline platelet count−nadir platelet count)/baseline platelet count]. The extra tree algorithm was used for feature selection and four ML algorithms [random forest (RF), adaptive boosting, extreme gradient boosting, and logistic regression] were established. Moreover, SHapley Additive exPlanation (SHAP) to explain the importance of features and the ML models.ResultsThis study included 330 children who underwent successful transcatheter closure of PDA, of which 113 (34.2%) experienced DPC. After 62 clinical features were considered, the extra tree algorithm selected six clinical features to build the ML models. Amongst the four ML algorithms, the RF model achieved the greatest AUC. SHAP analysis revealed that pulmonary artery systolic pressure, size of defect and weight were the top three most important clinical features in the RF model. Furthermore, clinical descriptions of two children with PDA, with accurate predictions, and explanations of the prediction results were provided.ConclusionIn this study, an ML model (RF) capable of predicting post-intervention DPC in children with PDA undergoing transcatheter closure was established.https://www.frontiersin.org/articles/10.3389/fped.2025.1519002/fullchildrendecline in platelet countinterventional closuremachine learningpatent ductus arteriosus |
| spellingShingle | Song-Yue Zhang Yi-Dong Zhang Hao Li Qiao-Yu Wang Qiao-Fang Ye Xun-Min Wang Tian-He Xia Yue-E He Xing Rong Ting-Ting Wu Rong-Zhou Wu Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus Frontiers in Pediatrics children decline in platelet count interventional closure machine learning patent ductus arteriosus |
| title | Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus |
| title_full | Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus |
| title_fullStr | Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus |
| title_full_unstemmed | Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus |
| title_short | Explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus |
| title_sort | explainable machine learning model for predicting decline in platelet count after interventional closure in children with patent ductus arteriosus |
| topic | children decline in platelet count interventional closure machine learning patent ductus arteriosus |
| url | https://www.frontiersin.org/articles/10.3389/fped.2025.1519002/full |
| work_keys_str_mv | AT songyuezhang explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT yidongzhang explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT haoli explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT qiaoyuwang explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT qiaofangye explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT xunminwang explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT tianhexia explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT yueehe explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT xingrong explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT tingtingwu explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus AT rongzhouwu explainablemachinelearningmodelforpredictingdeclineinplateletcountafterinterventionalclosureinchildrenwithpatentductusarteriosus |