Multitask Machine Learning-based Tumor-associated Collagen Signatures Predict Peritoneal Recurrence and Disease-free Survival in Gastric Cancer

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) and disease-free survival (TACS).

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) and disease-free survival (TACS). 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 and TACS were independently associated with peritoneal recurrence and disease-free survival in three cohorts, respectively (all P < 0.001). The TACS demonstrated a favorable performance for peritoneal recurrence in all three cohorts. In addition, the TACS 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 and low TACS, or high TACS and low TACS, or low TACS and high TACS, but had no impact on patients with high TACS and high TACS.

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.