High-Risk Clinicopathological and Genetic Features and Outcomes in Patients Receiving Neoadjuvant Radiochemotherapy for Locally Advanced Rectal Cancer

Deep Learning Techniques with Genomic Data in Cancer Prognosis: A Comprehensive Review of the 2021-2023 Literature

Deep learning has brought about a significant transformation in machine learning, leading to an array of novel methodologies and consequently broadening its influence. The application of deep learning in various sectors, especially biomedical data analysis, has initiated a period filled with noteworthy scientific developments. This trend has majorly influenced cancer prognosis, where the interpretation of genomic data for survival analysis has become a central research focus. The capacity of deep learning to decode intricate patterns embedded within high-dimensional genomic data has provoked a paradigm shift in our understanding of cancer survival. Given the swift progression in this field, there is an urgent need for a comprehensive review that focuses on the most influential studies from 2021 to 2023. This review, through its careful selection and thorough exploration of dominant trends and methodologies, strives to fulfill this need. The paper aims to enhance our existing understanding of applications of deep learning in cancer survival analysis, while also highlighting promising directions for future research. This paper undertakes aims to enrich our existing grasp of the application of deep learning in cancer survival analysis, while concurrently shedding light on promising directions for future research in this vibrant and rapidly proliferating field.

Development and validation of neoadjuvant rectal score-based signature nomograms to predict overall survival and disease-free survival in locally advanced rectal cancer: a retrospective, double center, cohort study

AIM

To evaluate the prognostic significance of the NAR score and develop nomograms for locally advanced rectal cancer (LARC) treated after neoadjuvant chemo-radiotherapy (nCRT) combined with total meso-rectal excision (TME) surgery to predict prognostic.

METHODS

Retrospective collection among LARC patients treated at Fujian Medical University Union Hospital (training cohort) and Fujian Medical University Affiliated Zhangzhou Hospital (external validation cohort) between Jan 10, 2011 and Dec 28, 2021. The NAR score was calculated by formula: [5pN-3(cT-pT) + 12]^2/9.61. NAR score low (< 8), intermediate (8-16), and high (> 16).

RESULTS

1665 patients in the training cohort and 256 patients in the external validation cohorts were enrolled. Lower NAR score was significantly associated with better cumulative incidence of OS, DFS, local recurrence (LR), and distant metastasis (DM) (all P < 0.001). Multivariate Cox regression analysis indicates that NAR score, distance to the anal verge, no.253 LN metastasis, post-CRT carbohydrate antigen 19-9, tumor regression grade, and surgery method are independent predictors of OS and DFS (all P < 0.001). Among these independent factors, the NAR score had the highest area under the curve (AUC) and the nomograms to predict OS and DFS were generated. The AUCs for the accuracy of the prediction OS were 1 year = 0.742, 3 years = 0.749, 5 years = 0.713; prediction DFS were 1 year = 0.727, 3 years = 0.739, 5 years = 0.718, the models have good accuracy.

CONCLUSIONS

The NAR score can effectively classify patients with LARC into groups with varying outcomes of OS, DFS, LR, and DM. Moreover, the novel nomograms comprising the NAR score were developed and validated to help predict OS and DFS.

A nomogram for predicting good response after neoadjuvant chemoradiotherapy for locally advanced rectal cancer: a retrospective, double-center, cohort study

AIM

The purpose of this study was to explore the clinical factors associated with achieving good response after neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC) and to develop and validate a nomogram.

METHODS

A total of 1724 consecutive LARC patients treated at Fujian Medical University Union Hospital from January 2010 to December 2021 were retrospectively evaluated as the training cohort; 267 consecutive LARC patients treated at Zhangzhou Affiliated Hospital of Fujian Medical University during the same period were evaluated as the external 2 cohorts. Based on the pathological results after radical surgery, treatment response was defined as follows: good response, stage ypT0∼2N0M0 and poor response, ypT3∼4N0M0 and/or N positive. Independent influencing factors were analyzed by logistic regression, a nomogram was developed and validated, and the model was evaluated using internal and external data cohorts for validation.

RESULTS

In the training cohort, 46.6% of patients achieved good response after nCRT combined with radical surgery. The rate of the retained anus was higher in the good response group (93.5% vs. 90.7%, P < 0.001). Cox regression analysis showed that the risk of overall survival and disease-free survival was significantly lower among good response patients than poor response patients, HR = 0.204 (95%CI: 0.146-0.287). Multivariate logistic regression analysis showed an independent association with 9 clinical factors, including histopathology, and a nomogram with an excellent predictive response was developed accordingly. The C-index of the predictive accuracy of the nomogram was 0.764 (95%CI: 0.742-0.786), the internal validation of the 200 bootstrap replication mean C-index was 0.764, and the external validation cohort showed an accuracy C-index of 0.789 (95%CI: 0.734-0.844), with good accuracy of the model.

CONCLUSION

We identified factors associated with achieving good response in LARC after treatment with nCRT and developed a nomogram to contribute to clinical decision-making.