Multitask machine learning-based tumor-associated collagen signatures predict peritoneal recurrence and disease-free survival in gastric cancer.

Autor: Fu M; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China.; Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Guangzhou, 510515, People's Republic of China.; School of Science, Jimei University, Xiamen, 361021, People's Republic of China., Lin Y; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Yang J; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Cheng J; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Lin L; Department of Pathology, Fujian Key Laboratory of Translational Cancer Medicine, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, 350014, People's Republic of China., Wang G; School of Science, Jimei University, Xiamen, 361021, People's Republic of China., Long C; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Xu S; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Lu J; Department of Pathology, Fujian Key Laboratory of Translational Cancer Medicine, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, 350014, People's Republic of China., Li G; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Yan J; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China., Chen G; Department of Pathology, Fujian Key Laboratory of Translational Cancer Medicine, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, 350014, People's Republic of China., Zhuo S; School of Science, Jimei University, Xiamen, 361021, People's Republic of China.; Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, Fujian Normal University, Fuzhou, 350007, People's Republic of China., Chen D; Department of General Surgery, Guangdong Provincial Key Laboratory of Precision Medicine for Gastrointestinal Tumor, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, People's Republic of China. chendexinsmu@163.com.
Jazyk: angličtina
Zdroj: Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association [Gastric Cancer] 2024 Nov; Vol. 27 (6), pp. 1242-1257. Date of Electronic Publication: 2024 Sep 14.
DOI: 10.1007/s10120-024-01551-0
Abstrakt: Background: Accurate prediction of peritoneal recurrence for gastric cancer (GC) is crucial in clinic. The collagen alterations in tumor microenvironment affect the migration and treatment response of cancer cells. Herein, we proposed multitask machine learning-based tumor-associated collagen signatures (TACS), which are composed of quantitative collagen features derived from multiphoton imaging, to simultaneously predict peritoneal recurrence (TACS PR ) and disease-free survival (TACS DFS ).
Methods: Among 713 consecutive patients, with 275 in training cohort, 222 patients in internal validation cohort, and 216 patients in external validation cohort, we developed and validated a multitask machine learning model for simultaneously predicting peritoneal recurrence (TACS PR ) and disease-free survival (TACS DFS ). The accuracy of the model for prediction of peritoneal recurrence and prognosis as well as its association with adjuvant chemotherapy were evaluated.
Results: The TACS PR and TACS DFS were independently associated with peritoneal recurrence and disease-free survival in three cohorts, respectively (all P < 0.001). The TACS PR demonstrated a favorable performance for peritoneal recurrence in all three cohorts. In addition, the TACS DFS also showed a satisfactory accuracy for disease-free survival among included patients. For stage II and III diseases, adjuvant chemotherapy improved the survival of patients with low TACS PR and low TACS DFS , or high TACS PR and low TACS DFS , or low TACS PR and high TACS DFS , but had no impact on patients with high TACS PR and high TACS DFS .
Conclusions: The multitask machine learning model allows accurate prediction of peritoneal recurrence and survival for GC and could distinguish patients who might benefit from adjuvant chemotherapy.
(© 2024. The Author(s) under exclusive licence to The International Gastric Cancer Association and The Japanese Gastric Cancer Association.)
Databáze: MEDLINE
Externí odkaz: