1
|
Guo Z, Zhang Z, Liu L, Zhao Y, Liu Z, Zhang C, Qi H, Feng J, Yang C, Tai W, Banchini F, Inchingolo R. Machine learning for predicting liver and/or lung metastasis in colorectal cancer: A retrospective study based on the SEER database. EUROPEAN JOURNAL OF SURGICAL ONCOLOGY 2024; 50:108362. [PMID: 38704899 DOI: 10.1016/j.ejso.2024.108362] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2023] [Revised: 04/11/2024] [Accepted: 04/20/2024] [Indexed: 05/07/2024]
Abstract
OBJECTIVE This study aims to establish a machine learning (ML) model for predicting the risk of liver and/or lung metastasis in colorectal cancer (CRC). METHODS Using the National Institutes of Health (NIH)'s Surveillance, Epidemiology, and End Results (SEER) database, a total of 51265 patients with pathological diagnosis of colorectal cancer from 2010 to 2015 were extracted for model development. On this basis, We have established 7 machine learning algorithm models. Evaluate the model based on accuracy, and AUC of receiver operating characteristics (ROC) and explain the relationship between clinical pathological features and target variables based on the best model. We validated the model among 196 colorectal cancer patients in Beijing Electric Power Hospital of Capital Medical University of China to evaluate its performance and universality. Finally, we have developed a network-based calculator using the best model to predict the risk of liver and/or lung metastasis in colorectal cancer patients. RESULTS 51265 patients were enrolled in the study, of which 7864 (15.3 %) had distant liver and/or lung metastasis. RF had the best predictive ability, In the internal test set, with an accuracy of 0.895, AUC of 0.956, and AUPR of 0.896. In addition, the RF model was evaluated in the external validation set with an accuracy of 0.913, AUC of 0.912, and AUPR of 0.611. CONCLUSION In this study, we constructed an RF algorithm mode to predict the risk of colorectal liver and/or lung metastasis, to assist doctors in making clinical decisions.
Collapse
Affiliation(s)
- Zhentian Guo
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China
| | - Zongming Zhang
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China.
| | - Limin Liu
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China
| | - Yue Zhao
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China
| | - Zhuo Liu
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China
| | - Chong Zhang
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China
| | - Hui Qi
- Department of General Surgery, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China; Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China
| | - Jinqiu Feng
- Key Laboratory of Geriatrics (Hepatobiliary Diseases) of China General Technology Group, Beijing, 100073, China; Department of Immunology, Peking University School of Basic Medical Sciences, Peking University, Beijing, 100191, China
| | - Chunmin Yang
- Department of Gastroenterology, Beijing Electric Power Hospital, State Grid Corporation of China, Capital Medical University, Beijing, 100073, China
| | - Weiping Tai
- Department of Gastroenterology, Beijing Shijitan Hospital, Capital Medical University, Beijing, 100038, China
| | - Filippo Banchini
- General Surgery Unit, Guglielmo da Saliceto Hospital, Piacenza, Italy
| | - Riccardo Inchingolo
- Interventional Radiology Unit, "F. Miulli" Regional General Hospital, Acquaviva delle Fonti, 70021, Italy
| |
Collapse
|
2
|
Stefanou AJ. Surgical and Interventional Management of Lung Metastasis: Surgical Assessment, Resection, Ablation, Percutaneous Interventions. Clin Colon Rectal Surg 2024; 37:85-89. [PMID: 38322599 PMCID: PMC10843877 DOI: 10.1055/s-0042-1758823] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/03/2022]
Abstract
The lungs are the second most common site of metastases for colorectal cancer after the liver. Pulmonary metastases can be identified at the time of diagnosis of the primary tumor, or metachronously. About 20% of patients with colorectal cancer will develop pulmonary metastases. The best options for treatment include a multidisciplinary treatment approach consisting of surgical resection whenever possible, and chemotherapy. Surgical options most often include minimally invasive segmentectomy or wedge resection, while patients unable to have surgery may benefit from radio frequency ablation or radiation treatment. Prognosis is dependent on preoperative carcinoembryonic antigen level, number, and location of metastatic lesions, and resectability of primary tumor. Overall, pulmonary metastases are best treated by complete resection whenever possible.
Collapse
Affiliation(s)
- Amalia J. Stefanou
- Gastrointestinal Oncology, Surgical Oncology, Moffitt Cancer Center, Tampa, Florida
| |
Collapse
|
3
|
Luo J, He MW, Luo T, Lv GQ. Identification of multiple risk factors for colorectal cancer relapse after laparoscopic radical resection. World J Gastrointest Surg 2023; 15:2211-2221. [PMID: 37969700 PMCID: PMC10642461 DOI: 10.4240/wjgs.v15.i10.2211] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/18/2023] [Revised: 08/08/2023] [Accepted: 08/18/2023] [Indexed: 10/27/2023] Open
Abstract
BACKGROUND Colorectal cancer (CRC) is a common life-threatening disease that often requires surgical intervention, such as laparoscopic radical resection. However, despite successful surgeries, some patients experience disease relapse. Identifying the risk factors for CRC relapse can help guide clinical interventions and improve patient outcomes. AIM To determine the risk factors that may lead to CRC relapse after laparoscopic radical resection. METHODS We performed a retrospective analysis using the baseline data of 140 patients with CRC admitted to our hospital between January 2018 and January 2020. All included participants were followed up until death or for 3 years. The baseline data and laboratory indicators were compared between the patients who experienced relapse and those who did not experienced relapse. RESULTS Among the 140 patients with CRC, 30 experienced relapse within 3 years after laparoscopic radical resection and 110 did not experience relapse. The relapse group had a higher frequency of rectal tumors with low differentiation and lymphatic vessel invasion than that of the non-relapse group. The expression of serum markers and the prognostic nutritional index were lower, whereas the neutrophil-to-lymphocyte ratio, expression of cytokeratin 19 fragment antigen 21-1, vascular endothelial growth factor, and Chitinase-3-like protein 1 were significantly higher in the relapse group than those in the non-relapse group. The groups did not differ significantly based on other parameters. Logistic regression analysis revealed that all the above significantly altered factors were independent risk factors for CRC relapse. CONCLUSION We identified multiple risk factors for CRC relapse following surgery, which can be considered for the clinical monitoring of patients to reduce disease recurrence and improve patient survival.
Collapse
Affiliation(s)
- Jun Luo
- Department of Gastrointestinal Surgery, Peking University Shenzhen Hospital, Shenzhen 518036, Guangdong Province, China
| | - Mei-Wen He
- Department of Gastrointestinal Surgery, Peking University Shenzhen Hospital, Shenzhen 518036, Guangdong Province, China
| | - Ting Luo
- Department of Operating Room, Peking University Shenzhen Hospital, Shenzhen 518036, Guangdong Province, China
| | - Guo-Qing Lv
- Department of Gastrointestinal Surgery, Shenzhen Peking University-The Hong Kong University of Science and Technology Medical Center, Peking University Shenzhen Hospital, Shenzhen 518036, Guangdong Province, China
| |
Collapse
|
4
|
Li W, Zhou Q, Liu W, Xu C, Tang ZR, Dong S, Wang H, Li W, Zhang K, Li R, Zhang W, Hu Z, Shibin S, Liu Q, Kuang S, Yin C. A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing's Sarcoma. Front Med (Lausanne) 2022; 9:832108. [PMID: 35463005 PMCID: PMC9020377 DOI: 10.3389/fmed.2022.832108] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2021] [Accepted: 02/24/2022] [Indexed: 11/13/2022] Open
Abstract
Objective In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing’s sarcoma (ES) based on machine learning (ML) algorithms. Methods Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application. Results LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed (https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py). Conclusion With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.
Collapse
Affiliation(s)
- Wenle Li
- Department of Orthopedics, Xianyang Central Hospital, Xianyang, China.,Clinical Medical Research Center, Xianyang Central Hospital, Xianyang, China
| | - Qian Zhou
- Department of Respiratory and Critical Care Medicine, The First People's Hospital of Chongqing Liang Jiang New Area, Chongqing, China
| | - Wencai Liu
- Department of Orthopaedic Surgery, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Chan Xu
- Department of Respiratory and Critical Care Medicine, The First People's Hospital of Chongqing Liang Jiang New Area, Chongqing, China.,Department of Dermatology, Xianyang Central Hospital, Xianyang, China
| | - Zhi-Ri Tang
- School of Physics and Technology, Wuhan University, Wuhan, China
| | - Shengtao Dong
- Department of Spine Surgery, Second Affiliated Hospital of Dalian Medical University, Dalian, China
| | - Haosheng Wang
- Department of Orthopaedics, The Second Hospital of Jilin University, Changchun, China
| | - Wanying Li
- Clinical Medical Research Center, Xianyang Central Hospital, Xianyang, China
| | - Kai Zhang
- Department of Orthopedics, Xianyang Central Hospital, Xianyang, China.,Clinical Medical Research Center, Xianyang Central Hospital, Xianyang, China
| | - Rong Li
- The First Clinical Medical College, Shaanxi University of Traditional Chinese Medicine, Xianyang, China
| | - Wenshi Zhang
- The First Clinical Medical College, Shaanxi University of Traditional Chinese Medicine, Xianyang, China
| | - Zhaohui Hu
- Department of Spinal Surgery, Liuzhou People's Hospital, Liuzhou, China
| | - Su Shibin
- Department of Business Management, Xiamen Bank, Xiamen, China
| | - Qiang Liu
- Clinical Medical Research Center, Xianyang Central Hospital, Xianyang, China
| | - Sirui Kuang
- Faculty of Medicine, Macau University of Science and Technology, Macau, China
| | - Chengliang Yin
- Faculty of Medicine, Macau University of Science and Technology, Macau, China
| |
Collapse
|