The study, published in Annals of Gastroenterological Surgery, assembled clinical data from 18 Japanese medical institutions, most of them high-volume board-certified training centers, covering patients who underwent initial curative-intent liver resection between January 2006 and December 2016. Of 1251 patients initially screened, 584 met the strict inclusion criteria, which required a known KRAS mutation profile, complete follow-up data, and exclusion of palliative R2 resections and BRAF-mutant tumors. The cohort was predominantly male with a median age of 66 years, and about a quarter of patients had right-sided primary colorectal tumors. Nearly two-thirds had nodal metastases from the primary tumor, almost 70 percent presented with synchronous liver metastases, and during a median follow-up of 44.1 months, a striking 79.1 percent of patients developed tumor recurrence—figures that underscore the aggressive nature of this disease even after apparently curative surgery.

At the heart of the investigation lies the KRAS oncogene, whose mutational status has become indispensable for designing treatment strategies in the era of targeted molecular therapy. Using Sanger sequencing of codons 12 and 13 on formalin-fixed paraffin-embedded tissue, the researchers detected KRAS mutations in 36.8 percent of patients. Mutant tumors were significantly more common in right-sided colon cancers, echoing the well-established embryological and molecular divide between the midgut-derived right colon and the hindgut-derived left colon and rectum. Critically, the survival analysis revealed that KRAS mutation was associated with both shorter recurrence-free survival and shorter overall survival across the entire cohort: median overall survival was 47.3 months for mutant carriers versus 70.6 months for wild-type patients, with five-year survival of 36.8 percent versus 55.6 percent respectively.

Yet the most provocative finding concerned geography within the colon itself. When the analysis was stratified by primary tumor sidedness, the prognostic power of KRAS mutation vanished on the right side and intensified on the left. Among patients with left-sided primaries, KRAS mutation conferred significantly worse overall and recurrence-free survival, with median overall survival of 44.2 months versus 69.4 months for wild-type disease. Among right-sided patients, by contrast, survival curves for mutant and wild-type tumors were statistically indistinguishable. This asymmetry suggests that the biological pathways driving metastatic behavior differ fundamentally according to embryological origin, and it cautions against treating KRAS as a universal prognostic marker. It also raises the possibility that right-sided disease harbors other, still unidentified molecular determinants—such as BRAF mutations or microsatellite instability—that may dominate its clinical course.

The second pillar of the study is the tumor burden score, or TBS, an elegant geometric construct that captures the cumulative impact of tumor size and number on a single continuous scale. Each patient is assigned coordinates on a Cartesian plane according to maximum tumor diameter and lesion count, and the Pythagorean distance from the origin yields the score. In this cohort, TBS grading stratified overall survival more powerfully than tumor size or number alone. But here, too, the interplay with genetics proved decisive: among KRAS wild-type patients, TBS grades separated median survival from 87.1 months in the low-burden group down to 43.8 months in the high-burden group, whereas among KRAS-mutant patients the survival curves collapsed into statistical sameness. In other words, a KRAS mutation appeared to define prognosis entirely independently of the anatomical burden of liver disease—a finding with profound implications for how tumor biology and tumor morphology should be weighed against each other.

Multivariate Cox regression distilled five independent preoperative predictors of survival: primary tumor nodal metastasis, KRAS mutation, extrahepatic disease, high tumor burden score, and elevated CA19-9 above 40 units per milliliter. Notably, CEA—the traditional tumor marker of colorectal cancer—did not survive multivariate adjustment, whereas CA19-9 did, a choice consistent with recent CRLM-specific studies that have demonstrated the prognostic relevance of CA19-9 even in patients receiving preoperative chemotherapy. These five variables were then integrated into a graphical nomogram that assigns weighted points to each factor and converts the summed total into predicted three- and five-year survival probabilities. Unlike categorical scoring systems, the nomogram preserves the relative weighting of individual risk factors and yields a continuous estimate of biological risk at the moment of diagnosis.

The performance data are compelling. When the cohort was divided into low-, medium-, and high-risk groups by total nomogram points, median overall survival separated cleanly into 95.6, 66.0, and 40.4 months respectively, with five-year survival spanning from 73.1 percent in the low-risk group to just 27.9 percent in the high-risk group. The same framework stratified recurrence-free survival with equal consistency, and—crucially—it predicted the pattern of relapse. Higher biological risk was associated with a growing proportion of extrahepatic recurrence involving lung, lymph nodes, and peritoneum, a signature of systemic metastatic propensity rather than merely local liver disease. Measured by Harrell’s C-index, the new model outperformed both the classic Fong clinical risk score of 1999 (0.627 versus 0.553) and the MD Anderson modified clinical risk score (0.627 versus 0.581), with lower Akaike information criterion values confirming superior fit. Internal validation through 1000 bootstrap resamples demonstrated an optimism-corrected C-index of 0.636 and a calibration slope of 0.931, indicating minimal overfitting and good agreement between predicted and observed survival.

It is this recurrence-pattern insight that breathes life into the concept of biological resectability. Even when a tumor is technically resectable by radiological criteria, a high nomogram score signals a hidden risk of systemic spread that surgery alone cannot address. In the high-risk group, roughly 90 percent of patients relapsed after hepatectomy, and in the low- and medium-risk groups recurrence was comparable, suggesting these groups differ qualitatively from high-risk disease in the degree of systemic cancer dissemination. The authors therefore propose distinguishing patients who technically qualify for resection but carry high biological risk as biologically borderline resectable—a category in which hepatic resection may be only one component of multimodal therapy rather than an optimally curative option. Importantly, the framework is presented as hypothesis-generating and complementary to anatomical assessment, not as a validated treatment algorithm, and it requires prospective validation in predominantly technically resectable cohorts.

The study is not without limitations, which the authors address with candor. The nomogram was developed and evaluated within the same multicenter Japanese cohort, so external validation in international populations remains essential. Because KRAS testing was not routine early in the study period, 649 patients with unknown mutation status were excluded, potentially introducing selection bias toward a more contemporary molecularly characterized population. Paired molecular analyses of primary tumors and metastases were unavailable, leaving open the question of KRAS discordance, and extended RAS and co-alteration analyses involving TP53, SMAD4, and other genes were not systematically performed. Dynamic changes in tumor morphology and marker levels during preoperative chemotherapy were likewise not incorporated. The risk-group cutoffs are explicitly exploratory, intended to facilitate interpretation rather than to define fixed biological categories.

Nevertheless, the implications for clinical practice are substantial. The nomogram demonstrates that resectability should be conceived along a continuous biological spectrum rather than as a binary yes-or-no verdict, and it provides an objective, readily computable instrument to locate any individual patient on that spectrum. By fusing molecular information—KRAS status—with geometric tumor burden, nodal status, extrahepatic disease, and CA19-9, the model captures dimensions of metastatic behavior that traditional scores built in the chemotherapy era of the 1990s cannot. Preclinical evidence suggesting that oncogenic Ras signaling cooperates with TP53 loss to promote invasion and systemic spread lends mechanistic plausibility to the observed link between high biological risk and extrahepatic recurrence. As molecular profiling becomes universal in colorectal cancer care, tools of this kind could reshape multidisciplinary decision-making, ensuring that the question asked before liver surgery is no longer only whether the tumor can be removed, but whether removing it will truly serve the patient.

Subject of Research: A nomogram-based continuous biological risk model for defining biologically borderline resectable colorectal liver metastases based on KRAS status and tumor burden.

Article Title: Biological Resectability in Colorectal Liver Metastases: A Nomogram‐Based Continuous Risk Model to Define Borderline Disease

Article References: Umeda, Y., Mitsuhashi, T., Fuji, T., Kojima, T., Koujima, T., Matsuda, T., Satoh, D., Inagaki, M., Takagi, K., & Fujiwara, T. (2026). Biological Resectability in Colorectal Liver Metastases: A Nomogram‐Based Continuous Risk Model to Define Borderline Disease. Annals of Gastroenterological Surgery, Article ags3.70278. https://doi.org/10.1002/ags3.70278

Image Credits: AI Generated

DOI: 10.1002/ags3.70278

Keywords: colorectal liver metastases, KRAS mutation, nomogram, tumor burden score, biological resectability, hepatectomy, CA19-9, overall survival, recurrence-free survival, borderline resectable, prognostic model, colorectal cancer