Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images
Abstract The clinical symptoms of ≤ 5 cm gastric stromal tumor (GST) and gastric schwannoma (GS) are similar, but the treatment regimens are different. This study explored the value of computed tomography (CT) combined with machine learning (ML) algorithms to find the best model to discriminate them...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-10-01
|
| Series: | Discover Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s12672-023-00801-4 |
| _version_ | 1797558786371616768 |
|---|---|
| author | Guoxian Chen Lifang Fan Jie Liu Shujian Wu |
| author_facet | Guoxian Chen Lifang Fan Jie Liu Shujian Wu |
| author_sort | Guoxian Chen |
| collection | DOAJ |
| description | Abstract The clinical symptoms of ≤ 5 cm gastric stromal tumor (GST) and gastric schwannoma (GS) are similar, but the treatment regimens are different. This study explored the value of computed tomography (CT) combined with machine learning (ML) algorithms to find the best model to discriminate them. A total of 126 patients with GST ≤ 5 cm and 35 patients with GS ≤ 5 during 2013–2022 were included. CT imaging features included qualitative data (tumor location, growth pattern, lobulation, surface ulcer status, necrosis, calcification, and surrounding lymph nodes) and quantitative data [long diameter (LD); short diameter (SD); LD/SD ratio; degree of enhancement (DE); heterogeneous degree (HD)]. Patients were randomly divided into a training set (n = 112) and test set (n = 49) using 7:3 stratified sampling. The univariate and multivariate logistic regression analysis were used to identify independent risk factors. Five ML algorithms were used to build prediction models: Support Vector Machine, k-Nearest Neighbor, Random Forest, Extra Trees, and Extreme Gradient Boosting Machine. The analysis identified that HDv, lobulation, and tumor growth site were independent risk factors (P < 0.05). We should focus on these three imaging features of tumors, which are relatively easy to obtain. The area under the curve for the SVM, KNN, RF, ET, and XGBoost prediction models were, respectively, 0.790, 0.895, 0.978, 0.988, and 0.946 for the training set, and were, respectively, 0.848, 0.892, 0.887, 0.912, and 0.867 for the test set. The CT combined with ML algorithms generated predictive models to improve the differential diagnosis of ≤ 5 cm GST and GS which has important clinical practical value. The Extra Trees algorithm resulted in the optimal model. |
| first_indexed | 2024-03-10T17:36:18Z |
| format | Article |
| id | doaj.art-2ed6362572294d5f9ee7bb34da3d0151 |
| institution | Directory Open Access Journal |
| issn | 2730-6011 |
| language | English |
| last_indexed | 2024-03-10T17:36:18Z |
| publishDate | 2023-10-01 |
| publisher | Springer |
| record_format | Article |
| series | Discover Oncology |
| spelling | doaj.art-2ed6362572294d5f9ee7bb34da3d01512023-11-20T09:50:20ZengSpringerDiscover Oncology2730-60112023-10-0114111010.1007/s12672-023-00801-4Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT imagesGuoxian Chen0Lifang Fan1Jie Liu2Shujian Wu3School of Clinical Medicine, Wannan Medical CollegeSchool of Medical Imageology, Wannan Medical CollegeDepartment of Pediatric Surgery, Yijishan Hospital of Wannan Medical College, Wannan Medical CollegeDepartment of Radiology, Yijishan Hospital of Wannan Medical College, Wannan Medical CollegeAbstract The clinical symptoms of ≤ 5 cm gastric stromal tumor (GST) and gastric schwannoma (GS) are similar, but the treatment regimens are different. This study explored the value of computed tomography (CT) combined with machine learning (ML) algorithms to find the best model to discriminate them. A total of 126 patients with GST ≤ 5 cm and 35 patients with GS ≤ 5 during 2013–2022 were included. CT imaging features included qualitative data (tumor location, growth pattern, lobulation, surface ulcer status, necrosis, calcification, and surrounding lymph nodes) and quantitative data [long diameter (LD); short diameter (SD); LD/SD ratio; degree of enhancement (DE); heterogeneous degree (HD)]. Patients were randomly divided into a training set (n = 112) and test set (n = 49) using 7:3 stratified sampling. The univariate and multivariate logistic regression analysis were used to identify independent risk factors. Five ML algorithms were used to build prediction models: Support Vector Machine, k-Nearest Neighbor, Random Forest, Extra Trees, and Extreme Gradient Boosting Machine. The analysis identified that HDv, lobulation, and tumor growth site were independent risk factors (P < 0.05). We should focus on these three imaging features of tumors, which are relatively easy to obtain. The area under the curve for the SVM, KNN, RF, ET, and XGBoost prediction models were, respectively, 0.790, 0.895, 0.978, 0.988, and 0.946 for the training set, and were, respectively, 0.848, 0.892, 0.887, 0.912, and 0.867 for the test set. The CT combined with ML algorithms generated predictive models to improve the differential diagnosis of ≤ 5 cm GST and GS which has important clinical practical value. The Extra Trees algorithm resulted in the optimal model.https://doi.org/10.1007/s12672-023-00801-4Computed tomographyMachine learningGastric tumorsGastric stromal tumorGastric schwannoma |
| spellingShingle | Guoxian Chen Lifang Fan Jie Liu Shujian Wu Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images Discover Oncology Computed tomography Machine learning Gastric tumors Gastric stromal tumor Gastric schwannoma |
| title | Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images |
| title_full | Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images |
| title_fullStr | Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images |
| title_full_unstemmed | Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images |
| title_short | Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images |
| title_sort | machine learning based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on ct images |
| topic | Computed tomography Machine learning Gastric tumors Gastric stromal tumor Gastric schwannoma |
| url | https://doi.org/10.1007/s12672-023-00801-4 |
| work_keys_str_mv | AT guoxianchen machinelearningbasedpredictivemodelforthedifferentialdiagnosisof5cmgastricstromaltumorandgastricschwannomabasedonctimages AT lifangfan machinelearningbasedpredictivemodelforthedifferentialdiagnosisof5cmgastricstromaltumorandgastricschwannomabasedonctimages AT jieliu machinelearningbasedpredictivemodelforthedifferentialdiagnosisof5cmgastricstromaltumorandgastricschwannomabasedonctimages AT shujianwu machinelearningbasedpredictivemodelforthedifferentialdiagnosisof5cmgastricstromaltumorandgastricschwannomabasedonctimages |