Value of enhanced CT machine learning models combined with clinicoradiological characteristics in predicting lymphatic tissue metastasis in colon cancer.
{"title":"Value of enhanced CT machine learning models combined with clinicoradiological characteristics in predicting lymphatic tissue metastasis in colon cancer.","authors":"Xinyi Li, Ziwei Tang, Yong Liu, Yanni Du, Yuxue Xing, Zixin Zhang, Ruming Xie","doi":"10.1007/s00117-024-01412-y","DOIUrl":null,"url":null,"abstract":"<p><p>This study aimed to assess the effectiveness of various machine learning models in identifying lymph node metastasis in colon cancer patients and to explore the potential benefits of combining clinicoradiological and radiomics features for improved diagnosis. A total of 260 patients with pathologically confirmed colon cancer were retrospectively included in study center 1 and study center 2 from January 2015 to August 2024. A total of 198 patients with colon cancer in center 1 were randomly divided into a training set (n = 138) and an internal testing set (n = 60) at a ratio of 7:3. Patients in center 2 were included in the external testing set (n = 62). Five clinical radiological features were used to establish a clinical model. Radiomics features were extracted from the computed tomography venous phase images, and four classifiers, including logistic regression, support vector machine, decision tree, and k‑nearest neighbor, were used to build machine learning models. In addition, a combined model was constructed by joining clinical, radiological, and radiogenomic features. The performance of these models was evaluated in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), receiver operating curve (ROC) and calibration curves in the training set, internal testing set, and external testing set to determine the diagnostic model with the highest predictive efficiency and to evaluate the stability of the model. Among the four machine learning models, the SVM model had the best predictive performance, with an area under the ROC (AUC) of 0.813, 0.724, and 0.721 for the training set, internal testing set, and external testing set, respectively. The clinical model, radiomics model, and combined model had an AUC of 0.823, 0.813, 0.817, 0.508, 0.724, 0.751, 0.582, 0.721, and 0.744 in the training set, internal testing set, and external testing set, respectively. In conclusion, the combined model performed significantly better than the clinical model (p = 0.017, 0.038), but there was no significant difference between the radiomics model and the combined model (p = 0.556, 0.614).</p>","PeriodicalId":74635,"journal":{"name":"Radiologie (Heidelberg, Germany)","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiologie (Heidelberg, Germany)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s00117-024-01412-y","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This study aimed to assess the effectiveness of various machine learning models in identifying lymph node metastasis in colon cancer patients and to explore the potential benefits of combining clinicoradiological and radiomics features for improved diagnosis. A total of 260 patients with pathologically confirmed colon cancer were retrospectively included in study center 1 and study center 2 from January 2015 to August 2024. A total of 198 patients with colon cancer in center 1 were randomly divided into a training set (n = 138) and an internal testing set (n = 60) at a ratio of 7:3. Patients in center 2 were included in the external testing set (n = 62). Five clinical radiological features were used to establish a clinical model. Radiomics features were extracted from the computed tomography venous phase images, and four classifiers, including logistic regression, support vector machine, decision tree, and k‑nearest neighbor, were used to build machine learning models. In addition, a combined model was constructed by joining clinical, radiological, and radiogenomic features. The performance of these models was evaluated in terms of accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), receiver operating curve (ROC) and calibration curves in the training set, internal testing set, and external testing set to determine the diagnostic model with the highest predictive efficiency and to evaluate the stability of the model. Among the four machine learning models, the SVM model had the best predictive performance, with an area under the ROC (AUC) of 0.813, 0.724, and 0.721 for the training set, internal testing set, and external testing set, respectively. The clinical model, radiomics model, and combined model had an AUC of 0.823, 0.813, 0.817, 0.508, 0.724, 0.751, 0.582, 0.721, and 0.744 in the training set, internal testing set, and external testing set, respectively. In conclusion, the combined model performed significantly better than the clinical model (p = 0.017, 0.038), but there was no significant difference between the radiomics model and the combined model (p = 0.556, 0.614).