Five-year survival post hepatectomy for colorectal liver metastases in a real-world Chinese cohort: Recurrence patterns and prediction for potential cure

Abstract

Background: Patients with a 5-year recurrence-free survival post liver resection for colorectal cancer liver metastases (CRLM) are considered to be potentially cured. However, there is a deficit of data on long-term follow-up and the recurrence status among these patients in the Chinese population. We analyzed real-world follow-up data of patients with CRLM who underwent hepatectomy, explored the recurrence patterns, and established a prediction model for a potential cure scenario.

Methods: Patients who underwent radical hepatic resection for CRLM during 2000-2016, with actual follow-up data for at least 5 years, were enrolled. The observed survival rate was calculated and compared among the groups with different recurrence patterns. The predictive factors for 5-year non-recurrence were determined using logistic regression analysis; a recurrence-free survival model was developed to predict long-term survival.

Results: A total of 433 patients were included, of whom 113 patients were found non-recurrence after 5 years follow-up, with a potential cure rate of 26.1%. Patients with late recurrence (>5 months) and lung relapse showed significantly superior survival. Repeated localized treatment significantly improved the long-term survival of patients with intrahepatic or extrahepatic recurrences. Multivariate analysis showed that RAS wild-type CRC, preoperative CEA <10 ng/ml, and liver metastases ≤3 were independent factors for a 5-year disease-free recurrence. A cure model was developed based on the above factors, achieving good performance in predicting long-term survival.

Conclusions: About one quarter patients with CRLM could achieve potential cure with non-recurrence at 5-year after surgery. The recurrence-free cure model could well distinguish the long-term survival, which would aid clinicians in determining the treatment strategy.

Keywords: colorectal cancer; hepatectomy; liver metastasis; survival.

FIGURE 1

Flow diagram of patients with colorectal liver metastases who underwent liver resection.

FIGURE 2

(A) Overall survival and (B) recurrence‐free survival of patients with actual 5‐years follow‐up post hepatectomy. When relapse occurred within 5 years, the impact of time of recurrence on overall survival was plotted using the log‐rank test (C) Recurrence within 5 months showed greatest impact in distinguishing the prognosis and was defined as the best cutoff for early recurrence (p = 6.13*10⁻⁷) (D).

FIGURE 3

Overall survival of patients with (A) different first recurrence sites (lung vs liver, p < 0.001; lung vs. bone/brain, p < 0.001; lung versus other sites, p = 0.010; liver vs. bone/brain, p = 0.535; liver vs. other sites, p = 0.682) and (B) different number of organs involved in recurrence (p = 0.346). The impact of treatment strategy after recurrence between local therapy and palliative systemic therapy was compared in patients with intrahepatic recurrence (p < 0.001) (C) and intra‐ or extrahepatic recurrence (p < 0.001) (D).

FIGURE 4

(A) Receiver operating characteristic (ROC) curve of the recurrence‐free cure model. Overall survival (B) and recurrence‐free survival (C) after hepatectomy for patients with different groups of prediction model (all p < 0.001).