1
|
Wang W, Sheng R, Liao S, Wu Z, Wang L, Liu C, Yang C, Jiang R. LightGBM is an Effective Predictive Model for Postoperative Complications in Gastric Cancer: A Study Integrating Radiomics with Ensemble Learning. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01172-0. [PMID: 38940888 DOI: 10.1007/s10278-024-01172-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/04/2024] [Revised: 05/08/2024] [Accepted: 05/09/2024] [Indexed: 06/29/2024]
Abstract
Postoperative complications of radical gastrectomy seriously affect postoperative recovery and require accurate risk prediction. Therefore, this study aimed to develop a prediction model specifically tailored to guide perioperative clinical decision-making for postoperative complications in patients with gastric cancer. A retrospective analysis was conducted on patients who underwent radical gastrectomy at the First Affiliated Hospital of Nanjing Medical University between April 2022 and June 2023. A total of 166 patients were enrolled. Patient demographic characteristics, laboratory examination results, and surgical pathological features were recorded. Preoperative abdominal CT scans were used to segment the visceral fat region of the patients through 3Dslicer, a 3D Convolutional Neural Network (3D-CNN) to extract image features and the LASSO regression model was employed for feature selection. Moreover, an ensemble learning strategy was adopted to train the features and predict postoperative complications of gastric cancer. The prediction performance of the LGBM (Light Gradient Boosting Machine), XGB (XGBoost), RF (Random Forest), and GBDT (Gradient Boosting Decision Tree) models was evaluated through fivefold cross-validation. This study successfully constructed a model for predicting early complications following radical gastrectomy based on the optimal algorithm, LGBM. The LGBM model yielded an AUC value of 0.9232 and an accuracy of 87.28% (95% CI, 75.61-98.95%), surpassing the performance of other models. Through ensemble learning and integration of perioperative clinical data and visceral fat radiomics, a predictive LGBM model was established. This model has the potential to facilitate individualized clinical decision-making and the early recovery of patients with gastric cancer post-surgery.
Collapse
Affiliation(s)
- Wenli Wang
- Department of Anesthesiology and Perioperative Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China
| | - Rongrong Sheng
- Information Center, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China
| | - Shumei Liao
- Information Center, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China
| | - Zifeng Wu
- Department of Anesthesiology and Perioperative Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China
| | - Linjun Wang
- Department of Gastric Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China
| | - Cunming Liu
- Department of Anesthesiology and Perioperative Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China
| | - Chun Yang
- Department of Anesthesiology and Perioperative Medicine, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China.
| | - Riyue Jiang
- Department of Radiation Oncology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China.
| |
Collapse
|
2
|
Dadgar N, Sherry C, Zimmerman J, Park H, Lewis C, Donnenberg A, Zaidi AH, Fan Y, Xiao K, Bartlett D, Donnenberg V, Wagner PL. Targeting interleukin-6 as a treatment approach for peritoneal carcinomatosis. J Transl Med 2024; 22:402. [PMID: 38689325 PMCID: PMC11061933 DOI: 10.1186/s12967-024-05205-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2024] [Accepted: 04/15/2024] [Indexed: 05/02/2024] Open
Abstract
Peritoneal carcinomatosis (PC) is a complex manifestation of abdominal cancers, with a poor prognosis and limited treatment options. Recent work identifying high concentrations of the cytokine interleukin-6 (IL-6) and its soluble receptor (sIL-6-Rα) in the peritoneal cavity of patients with PC has highlighted this pathway as an emerging potential therapeutic target. This review article provides a comprehensive overview of the current understanding of the potential role of IL-6 in the development and progression of PC. We discuss mechansims by which the IL-6 pathway may contribute to peritoneal tumor dissemination, mesothelial adhesion and invasion, stromal invasion and proliferation, and immune response modulation. Finally, we review the prospects for targeting the IL-6 pathway in the treatment of PC, focusing on common sites of origin, including ovarian, gastric, pancreatic, colorectal and appendiceal cancer, and mesothelioma.
Collapse
Affiliation(s)
- Neda Dadgar
- Translational Hematology & Oncology Research, Enterprise Cancer Institute, Cleveland Clinic, Cleveland, OH, 44106, USA
| | - Christopher Sherry
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Jenna Zimmerman
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Hyun Park
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Catherine Lewis
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Albert Donnenberg
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Ali H Zaidi
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Yong Fan
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Kunhong Xiao
- Center for Proteomics & Artificial Intelligence, Center for Clinical Mass Spectrometry, Allegheny Health Network Cancer Institute, Pittsburgh, PA, 15224, USA
| | - David Bartlett
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA
| | - Vera Donnenberg
- University of Pittsburgh School of MedicineDepartment of Cardiothoracic SurgeryUPMC Hillman Cancer Center Wagner, Patrick; Allegheny Health Network Cancer Institute, Pittsburgh, USA
| | - Patrick L Wagner
- Allegheny Health Network Cancer Institute, 314 E. North Ave, Pittsburgh, PA, 15212, USA.
| |
Collapse
|
3
|
Zhou L, Tang C, Li X, Feng F. IL-6/IL-10 mRNA expression ratio in tumor tissues predicts prognosis in gastric cancer patients without distant metastasis. Sci Rep 2022; 12:19427. [PMID: 36371539 PMCID: PMC9653417 DOI: 10.1038/s41598-022-24189-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2022] [Accepted: 11/11/2022] [Indexed: 11/13/2022] Open
Abstract
There was growing evidence that inflammatory responses played significant roles in malignancies. However, the impact of pro-inflammatory-to-anti-inflammatory factor ratio in tumor tissues has not been investigated in gastric cancer (GC) yet. We collected patient data from The Cancer Genome Atlas (TCGA) database. A total of 270 stomach adenocarcinoma (STAD) patients without distant metastasis were included in the study. After screening 12 candidate pro-inflammatory-to-anti-inflammatory pairs, only the IL-6/IL-10 mRNA expression ratio in tumor tissues had a significant effect on overall survival (OS) of STAD patients (P = 0.014). X-tile analysis showed that the greatest survival differences were obtained when the cutoff value of IL-6/IL-10 mRNA expression ratio was set at 1.3 and 5.5. With the low-ratio group (IL-6/IL-10 mRNA expression ratio: < 1.3) as reference, OS time for both the medium-ratio group (IL-6/IL-10 mRNA expression ratio: 1.3-5.5) and the high-ratio group (IL-6/IL-10 mRNA expression ratio: > 5.5) was significantly shorter (P < 0.05). Multivariate Cox regression analyses indicated that IL-6/IL-10 mRNA expression ratio was an independent prognostic factor for OS and disease-specific survival (DSS). These findings provided a novel and powerful tool for a more rational management of GC patients.
Collapse
Affiliation(s)
- Li Zhou
- grid.263761.70000 0001 0198 0694Department of Oncology, Suzhou Ninth People′s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, 215200 China
| | - Chuangang Tang
- grid.452207.60000 0004 1758 0558Department of General Surgery, Xuzhou Central Hospital, The Affiliated Xuzhou Hospital of Medical College of Southeast University, Xuzhou, 221009 China ,grid.452207.60000 0004 1758 0558Department of Breast Surgery, Xuzhou Central Hospital, The Affiliated Xuzhou Hospital of Medical College of Southeast University, Xuzhou, 221009 China
| | - Xiaoxin Li
- grid.452207.60000 0004 1758 0558Department of Pathology, Xuzhou Central Hospital, The Affiliated Xuzhou Hospital of Medical College of Southeast University, Xuzhou, 221009 China
| | - Fang Feng
- grid.263761.70000 0001 0198 0694Department of Oncology, Suzhou Ninth People′s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University, Suzhou, 215200 China
| |
Collapse
|
4
|
Tanshinone IIA May Inhibit Gastric Cancer via Affecting the Intestinal Microbiome. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:6960304. [PMID: 36199775 PMCID: PMC9529444 DOI: 10.1155/2022/6960304] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 09/05/2022] [Accepted: 09/09/2022] [Indexed: 12/30/2022]
Abstract
Background Gastric cancer (GC) belongs to a type of the most deadly cancer in the world, and the incidence rate of GC will increase in the coming decades. Tanshinone IIA (Tan IIA) is an active component that separated from Danshen. Tan IIA may also exert its therapeutic effects in disease with intestinal dysbacteriosis, at least partially, via regulating the intestinal microbiome. Nevertheless, it is obscure whether Tanshinone IIA affects the intestinal dysbacteriosis and plays antitumor roles. This research was designed to explore Tanshinone IIA potential on the intestinal dysbacteriosis of GC xenograft mice. Methods Mouse xenograft GC tumor models were built and treated by Tan IIA. The tumor growth as well as microbiome in the intestinal were compared. Western blot was used to detect the phosphorylation of the NF-κB and expressions of the downstream cytokines IL-6 and IL-1β. Results Microbiome in the intestinal was changed in xenograft tumor mice in comparison with the control mice. What is more, Tan IIA could influence the microbiome in the intestinal of the tumor mice. Tan IIA hinders the growth of xenograft tumor and change the microbiome in the intestinal, but intestinal dysbacteriosis condition partially blocked Tan IIA-stimulated antitumor effects. In addition, intestinal dysbacteriosis abrogated Tan IIA-stimulated decrease in the NF-κB signaling in xenograft tumor mice. Conclusions Tanshinone IIA may inhibit GC tumor growth via affecting the intestinal microbiome through regulating the NF-κB signaling.
Collapse
|