Radiomics based on machine learning algorithms could predict prognosis and postoperative chemotherapy benefits of patients with gastric cancer: a retrospective cohort study

被引:1
|
作者
Xiang, Yilan [1 ]
Hu, Yuanbo [2 ]
Zhi, Huaiqing [2 ]
Zhang, Zhao [1 ]
Lu, Mingdong [3 ,4 ]
Chen, Xietao [2 ]
Luo, Zhixian [1 ]
Chen, Sian [4 ,5 ]
Dias-Neto, Emmanuel [6 ,7 ]
Pizzini, Paolo [8 ]
Chen, Xinxin [3 ,4 ]
Chen, Xiaodong [2 ,9 ]
Zhuang, Yuandi [1 ,10 ]
Dong, Qiantong [2 ,9 ]
机构
[1] Wenzhou Med Univ, Affiliated Hosp 1, Dept Radiol, Wenzhou, Peoples R China
[2] Wenzhou Med Univ, Affiliated Hosp 1, Dept Gen Surg, Wenzhou, Peoples R China
[3] Wenzhou Med Univ, Affiliated Hosp 2, Dept Gen Surg, Wenzhou, Peoples R China
[4] Wenzhou Med Univ, Yuying Childrens Hosp, Wenzhou, Peoples R China
[5] Wenzhou Med Univ, Affiliated Hosp 2, Dept Emergency, Wenzhou, Peoples R China
[6] AC Camargo Canc Ctr, Lab Med Genom, Sao Paulo, SP, Brazil
[7] Rutgers New Jersey Med Sch, Dept Radiat Oncol, Div Canc Biol, Newark, NJ USA
[8] European Inst Oncol IRCCS, Dept Digest Surg, Milan, Italy
[9] Wenzhou Med Univ, Affiliated Hosp 1, Dept Gen Surg, Wenzhou 325015, Peoples R China
[10] Wenzhou Med Univ, Affiliated Hosp 1, Dept Radiol, Wenzhou 325015, Peoples R China
关键词
Gastric cancer (GC); computed tomography (CT); radiomics risk score (RRS); machine learning algorithms; postoperative chemotherapy; NODE-METASTASIS; IMAGES; IMPACT; TUMOR;
D O I
10.21037/jgo-23-627
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Background: Traditional clinical characteristics have certain limitations in evaluating cancer prognosis. The radiomics features provide information on tumor morphology, tissue texture, and hemodynamics, which can accurately reflect personalized predictions. This study investigated the clinical value of radiomics features on contrast-enhanced computed tomography (CT) images in predicting prognosis and postoperative chemotherapy benefits for patients with gastric cancer (GC).Methods: For this study, 171 GC patients who underwent radical gastrectomy and pathology confirmation of the malignancy at the First Affiliated Hospital of Wenzhou Medical University were retrospectively enrolled. The general information, pathological characteristics, and postoperative chemotherapy information were collected. Patients were also monitored through telephone interviews or outpatient treatment. GC patients were randomly divided into the developing cohort (n=120) and validation cohort (n=51). The intratumor areas of interest inside the tumors were delineated, and 1,218 radiomics features were extracted. The optimal radiomics risk score (RRS) was constructed using 8 machine learning algorithms and 29 algorithm combinations. Furthermore, a radiomics nomogram that included clinicopathological characteristics was constructed and validated through univariate and multivariate Cox analyses.Results: Eleven prognosis-related features were selected, and an RRS was constructed. Kaplan-Meier curve analysis showed that the RRS had a high prognostic ability in the developing and validation cohorts (log-rank P<0.01). The RRS was higher in patients with a larger tumor size (>= 3 cm), higher Charlson score (>= 2), and higher clinical stage (Stages III and IV) (all P<0.001). Furthermore, GC patients with a higher RRS significantly benefited from postoperative chemotherapy. The results of univariate and multivariate Cox regression analyses demonstrated that the RRS was an independent risk factor for overall survival (OS) and disease-free survival (DFS) (P<0.001). A visual nomogram was established based on the significant factors in multivariate Cox analysis (P<0.05). The C-index was 0.835 (0.793-0.877) for OS and 0.733 (0.677-0.789) for DFS in the developing cohort. The calibration curve also showed that the nomogram had good agreement.Conclusions: A nomogram that combines the RRS and clinicopathological characteristics could serve as a novel noninvasive preoperative prediction model with the potential to accurately predict the prognosis and chemotherapy benefits of GC patients.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] CT-based radiomics scores predict response to neoadjuvant chemotherapy and survival in patients with gastric cancer
    Kai-Yu Sun
    Hang-Tong Hu
    Shu-Ling Chen
    Jin-Ning Ye
    Guang-Hua Li
    Li-Da Chen
    Jian-Jun Peng
    Shi-Ting Feng
    Yu-Jie Yuan
    Xun Hou
    Hui Wu
    Xin Li
    Ting-Fan Wu
    Wei Wang
    Jian-Bo Xu
    BMC Cancer, 20
  • [22] Comparative Analysis Between Machine Learning Algorithms and Conventional Regression in Predicting the Prognosis of Patients with Basilar Invagination: A Retrospective Cohort Study
    Peng, Liwei
    Peng, Chi
    Yang, Fan
    Zuo, Wei
    Cheng, Chao
    Wang, Peng
    Zhang, Jin'an
    LI, Weixin
    TURKISH NEUROSURGERY, 2023, 33 (04) : 665 - 675
  • [23] Machine Learning for Prognosis Prediction in Japanese Breast Cancer Patients: A Retrospective Study
    Shiino, Sho
    Kouno, Nobuji
    Takasawa, Ken
    Hamamoto, Ryuji
    CANCER SCIENCE, 2024, 115 : 1504 - 1504
  • [24] Machine Learning Algorithms to Predict Major Adverse Cardiovascular Events in Patients Undergoing Orthotopic Liver Transplantation: A Retrospective Cohort Study
    Jain, Vardhmaan
    Sharma, Vikram
    Bansal, Agam
    Kleb, Cerise
    Sheth, Chirag
    Quintini, Cristiano
    Cywinski, Jacek
    Fares, Maan
    CIRCULATION, 2020, 142
  • [25] A CT-based deep learning radiomics nomogram for predicting the response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer: A multicenter cohort study
    Cui, Yanfen
    Zhang, Jiayi
    Li, Zhenhui
    Wei, Kaikai
    Lei, Ye
    Ren, Jialiang
    Wu, Lei
    Shi, Zhenwei
    Meng, Xiaochun
    Yang, Xiaotang
    Gao, Xin
    ECLINICALMEDICINE, 2022, 46
  • [26] The Application and Comparison of Machine Learning Models for the Prediction of Breast Cancer Prognosis: Retrospective Cohort Study
    Xiao, Jialong
    Mo, Miao
    Wang, Zezhou
    Zhou, Changming
    Shen, Jie
    Yuan, Jing
    He, Yulian
    Zheng, Ying
    JMIR MEDICAL INFORMATICS, 2022, 10 (02)
  • [27] Machine learning algorithms that predict the risk of prostate cancer based on metabolic syndrome and sociodemographic characteristics: a prospective cohort study
    Tran, Tao Thi
    Lee, Jeonghee
    Kim, Junetae
    Kim, Sun-Young
    Cho, Hyunsoon
    Kim, Jeongseon
    BMC PUBLIC HEALTH, 2024, 24 (01)
  • [28] Postoperative complications and symptoms of anxiety and depression in patients with gastric and esophageal cancer: a retrospective cohort study
    Fournier, Valentyn
    Fontesse, Sullivan
    Christophe, Veronique
    Ramdane, Nassima
    Anota, Amelie
    Gauchet, Alice
    Lelorain, Sophie
    Baudry, Anne-Sophie
    Duprez, Christelle
    Devaux, Stephanie
    Bergeat, Damien
    D'Journo, Xavier Benoit
    Glehen, Olivier
    Piessen, Guillaume
    Grynberg, Delphine
    PSYCHOLOGY HEALTH & MEDICINE, 2025, 30 (02) : 282 - 296
  • [29] A Machine Learning Model Based on MRI Radiomics to Predict Response to Chemoradiation Among Patients with Rectal Cancer
    Crimi, Filippo
    D'Alessandro, Carlo
    Zanon, Chiara
    Celotto, Francesco
    Salvatore, Christian
    Interlenghi, Matteo
    Castiglioni, Isabella
    Quaia, Emilio
    Pucciarelli, Salvatore
    Spolverato, Gaya
    LIFE-BASEL, 2024, 14 (12):
  • [30] Preoperative Prediction of Perineural Invasion and Prognosis in Gastric Cancer Based on Machine Learning through a Radiomics-Clinicopathological Nomogram
    Jia, Heng
    Li, Ruzhi
    Liu, Yawei
    Zhan, Tian
    Li, Yuan
    Zhang, Jianping
    CANCERS, 2024, 16 (03)