Tailored treatments for metastatic colorectal cancer (mCRC) have not yet completely evolved due to the variety in response to drugs. Therefore, artificial intelligence has been recently used to develop prognostic and predictive models of treatment response (either activity/efficacy or toxicity) to aid in clinical decision making. In this systematic review, we have examined the ability of learning methods to predict response to chemotherapy alone or combined with targeted therapy in mCRC patients by targeting specific narrative publications in Medline up to April 2022 to identify appropriate original scientific articles. After the literature search, 26 original articles met inclusion and exclusion criteria and were included in the study. Our results show that all investigations conducted on this field have provided generally promising results in predicting the response to therapy or toxic side-effects. By a meta-analytic approach we found that the overall weighted means of the area under the receiver operating characteristic (ROC) curve (AUC) were 0.90, 95% C.I. 0.80–0.95 and 0.83, 95% C.I. 0.74–0.89 in training and validation sets, respectively, indicating a good classification performance in discriminating response vs. non-response. The calculation of overall HR indicates that learning models have strong ability to predict improved survival. Lastly, the delta-radiomics and the 74 gene signatures were able to discriminate response vs. non-response by correctly identifying up to 99% of mCRC patients who were responders and up to 100% of patients who were non-responders. Specifically, when we evaluated the predictive models with tests reaching 80% sensitivity (SE) and 90% specificity (SP), the delta radiomics showed an SE of 99% and an SP of 94% in the training set and an SE of 85% and SP of 92 in the test set, whereas for the 74 gene signatures the SE was 97.6% and the SP 100% in the training set.

Some recent studies have suggested that laparoscopic surgery for colorectal cancer may provide a potential survival advantage when compared with open surgery. This study aimed to compare cancer-related survivals of patients who underwent laparoscopic or open resection of colon cancer in the same, high volume tertiary center. Patients who had undergone elective open or laparoscopic surgery for colon cancer between January 2002 and December 2010 were analyzed. A clinical database was prospectively compiled. Survival analysis was calculated by using the Kaplan-Meier method. A total of 460 resections were performed. There were no significant differences between the laparoscopic (n = 227) and the open group (n = 233) apart from tumor stage: stage I tumors were more frequent in the laparoscopic group whereas stage II tumors were more frequent in the open group. The mean number of harvested lymph nodes was significantly higher in the laparoscopic than in the open group (20.0 ± 0.7 vs 14.2 ± 0.5, P < 0.01). The 5-year cancer-related survival for patients undergoing laparoscopic resection was significantly higher than that following open resections (83.1% vs 68.5%, P = 0.01). By performing a stage-to-stage comparison, we found that the improvement in survival in the laparoscopic group occurred mainly in patients with stage II tumors. Our study shows a survival advantage for patients who had undergone laparoscopic surgery for stage II colon cancer. This may be correlated with a higher number of harvested lymph nodes and thus a better stage stratification of these patients.

Voltage-gated Na⁺ channels (VGSCs) are expressed widely in human carcinomas and play a significant role in promoting cellular invasiveness and metastasis. However, human tissue-based studies and clinical characterization are lacking. In several carcinomas, including colorectal cancer (CRCa), the predominant VGSC is the neonatal splice variant of Nav1.5 (nNav1.5). The present study was designed to determine the expression patterns and clinical relevance of nNav1.5 protein in human CRCa tissues from patients with available clinicopathological history. The immunohistochemistry was made possible by the use of a polyclonal antibody (NESOpAb) specific for nNav1.5. The analysis showed that, compared with normal mucosa, nNav1.5 expression occurred in CRCa samples (i) at levels that were significantly higher and (ii) with a pattern that was more delineated (i.e., apical/basal or mixed). A surprisingly high level of nNav1.5 protein expression also occurred in adenomas, but this was mainly intracellular and diffuse. nNav1.5 showed a statistically significant association with TNM stage, highest expression being associated with TNM IV and metastatic status. Interestingly, nNav1.5 expression co-occurred with other biomarkers associated with metastasis, including hERG1, KCa3.1, VEGF-A, Glut1, and EGFR. Finally, univariate analysis showed that nNav1.5 expression had an impact on progression-free survival. We conclude (i) that nNav1.5 could represent a novel clinical biomarker (‘companion diagnostic’) useful to better stratify CRCa patients and (ii) that since nNav1.5 expression is functional, it could form the basis of anti-metastatic therapies including in combination with standard treatments.