A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy
ObjectiveWe used machine-learning (ML) models based on ultrasound radiomics to construct a nomogram for noninvasive evaluation of the crescent status in immunoglobulin A (IgA) nephropathy.MethodsPatients with IgA nephropathy diagnosed by renal biopsy (n=567) were divided into training (n=398) and te...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Endocrinology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2023.1093452/full |
| _version_ | 1797947001354059776 |
|---|---|
| author | Xiachuan Qin Xiachuan Qin Linlin Xia Xiaomin Hu Weihan Xiao Xian Huaming Xie Xisheng Chaoxue Zhang |
| author_facet | Xiachuan Qin Xiachuan Qin Linlin Xia Xiaomin Hu Weihan Xiao Xian Huaming Xie Xisheng Chaoxue Zhang |
| author_sort | Xiachuan Qin |
| collection | DOAJ |
| description | ObjectiveWe used machine-learning (ML) models based on ultrasound radiomics to construct a nomogram for noninvasive evaluation of the crescent status in immunoglobulin A (IgA) nephropathy.MethodsPatients with IgA nephropathy diagnosed by renal biopsy (n=567) were divided into training (n=398) and test cohorts (n=169). Ultrasound radiomic features were extracted from ultrasound images. After selecting the most significant features using univariate analysis and the least absolute shrinkage and selection operator algorithm, three ML algorithms were assessed for final radiomic model establishment. Next, clinical, ultrasound radiomic, and combined clinical−radiomic models were compared for their ability to detect IgA crescents. The diagnostic performance of the three models was evaluated using receiver operating characteristic curve analysis.ResultsThe average area under the curve (AUC) of the three ML radiomic models was 0.762. The logistic regression model performed best, with AUC values in the training and test cohorts of 0.838 and 0.81, respectively. Among the final models, the combined model based on clinical characteristics and the Rad score showed good discrimination, with AUC values in the training and test cohorts of 0.883 and 0.862, respectively. The decision curve analysis verified the clinical practicability of the combined nomogram.ConclusionML classifier based on ultrasound radiomics has a potential value for noninvasive diagnosis of IgA nephropathy with or without crescents. The nomogram constructed by combining ultrasound radiomic and clinical features can provide clinicians with more comprehensive and personalized image information, which is of great significance for selecting treatment strategies. |
| first_indexed | 2024-04-10T21:19:54Z |
| format | Article |
| id | doaj.art-ab117f2dfed049b38cc239555b8d9df3 |
| institution | Directory Open Access Journal |
| issn | 1664-2392 |
| language | English |
| last_indexed | 2024-04-10T21:19:54Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Endocrinology |
| spelling | doaj.art-ab117f2dfed049b38cc239555b8d9df32023-01-20T07:14:13ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922023-01-011410.3389/fendo.2023.10934521093452A novel clinical−radiomic nomogram for the crescent status in IgA nephropathyXiachuan Qin0Xiachuan Qin1Linlin Xia2Xiaomin Hu3Weihan Xiao4Xian Huaming5Xie Xisheng6Chaoxue Zhang7Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, ChinaDepartment of Ultrasound, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nanchong, Sichuan, ChinaDepartment of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, ChinaDepartment of Ultrasound, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nanchong, Sichuan, ChinaDepartment of Ultrasound, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nanchong, Sichuan, ChinaDepartment of Nephrology, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nanchong, Sichuan, ChinaDepartment of Nephrology, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College (University), Nanchong, Sichuan, ChinaDepartment of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, Anhui, ChinaObjectiveWe used machine-learning (ML) models based on ultrasound radiomics to construct a nomogram for noninvasive evaluation of the crescent status in immunoglobulin A (IgA) nephropathy.MethodsPatients with IgA nephropathy diagnosed by renal biopsy (n=567) were divided into training (n=398) and test cohorts (n=169). Ultrasound radiomic features were extracted from ultrasound images. After selecting the most significant features using univariate analysis and the least absolute shrinkage and selection operator algorithm, three ML algorithms were assessed for final radiomic model establishment. Next, clinical, ultrasound radiomic, and combined clinical−radiomic models were compared for their ability to detect IgA crescents. The diagnostic performance of the three models was evaluated using receiver operating characteristic curve analysis.ResultsThe average area under the curve (AUC) of the three ML radiomic models was 0.762. The logistic regression model performed best, with AUC values in the training and test cohorts of 0.838 and 0.81, respectively. Among the final models, the combined model based on clinical characteristics and the Rad score showed good discrimination, with AUC values in the training and test cohorts of 0.883 and 0.862, respectively. The decision curve analysis verified the clinical practicability of the combined nomogram.ConclusionML classifier based on ultrasound radiomics has a potential value for noninvasive diagnosis of IgA nephropathy with or without crescents. The nomogram constructed by combining ultrasound radiomic and clinical features can provide clinicians with more comprehensive and personalized image information, which is of great significance for selecting treatment strategies.https://www.frontiersin.org/articles/10.3389/fendo.2023.1093452/fullIgA nephropathycrescentsmachine learningradiomicsnomogram |
| spellingShingle | Xiachuan Qin Xiachuan Qin Linlin Xia Xiaomin Hu Weihan Xiao Xian Huaming Xie Xisheng Chaoxue Zhang A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy Frontiers in Endocrinology IgA nephropathy crescents machine learning radiomics nomogram |
| title | A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy |
| title_full | A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy |
| title_fullStr | A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy |
| title_full_unstemmed | A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy |
| title_short | A novel clinical−radiomic nomogram for the crescent status in IgA nephropathy |
| title_sort | novel clinical radiomic nomogram for the crescent status in iga nephropathy |
| topic | IgA nephropathy crescents machine learning radiomics nomogram |
| url | https://www.frontiersin.org/articles/10.3389/fendo.2023.1093452/full |
| work_keys_str_mv | AT xiachuanqin anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiachuanqin anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT linlinxia anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiaominhu anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT weihanxiao anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xianhuaming anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiexisheng anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT chaoxuezhang anovelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiachuanqin novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiachuanqin novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT linlinxia novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiaominhu novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT weihanxiao novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xianhuaming novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT xiexisheng novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy AT chaoxuezhang novelclinicalradiomicnomogramforthecrescentstatusiniganephropathy |