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

Abstract

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.