Do Second Primary Cancers Affect the Risk of Biochemical Recurrence in Prostate Cancer Patients Undergoing Radical Prostatectomy? A Propensity Score-Matched Analysis

Second Primary Cancers following Colorectal Cancer in Sicily, Italy

Simple Summary

This study addressed the under-investigated issue of second primary cancer occurring in colorectal cancer survivors. Our aim was to explore whether patients recovered from a first colorectal cancer were at higher risk of developing a subsequent primary cancer. The hypothesis was that exposure to cancer treatment, enhanced health surveillance and shared risk factors may lead to an excess risk of second primary cancer in this population. The number of cases of second primary cancer exceeded the expected in this population, mainly driven by female genital cancers, and especially observed in the first years after colorectal cancer diagnosis. Our findings are overall consistent with previous studies, providing valuable information to better characterize and predict mortality from second primary cancer in subjects who suffered from first colorectal cancer.

Abstract

Background: Cancer survivors are at risk of developing second primary cancers (SPC). We investigated the risk of SPC in colorectal cancer (CRC) survivors in Sicily, Southern Italy. Methods: We analyzed data from the Eastern Sicily cancer registry covering 2.5 million people diagnosed and followed up between 2003 and 2017. We calculated the standardized incidence ratio (SIR) and 95% confidence interval (CI) of SPC overall and by cancer type, using the general Sicily population rates as reference. Results: A total of 19,040 cases of CRC and 1453 cases of SPC were included in the analysis. Mean age of occurrence of SPC was 68.1. The SIR for any SPC was 1.11 (95% CI 1.05–1.17); it was higher in women (1.18; 95% CI 1.08–1.29) than in men (1.07; 95% CI 0.97–1.14, p-value of difference 0.07). The SIR was increased for SPC from the ovary (SIR 2.01; 95% CI 1.33–2.95), kidney (SIR 2.00; 95% CI 1.54–2.56), endometrium (SIR 1.94; 95% CI 1.45–2.54), bladder (SIR 1.22, 95% CI 1.04–1.43) and stomach (1.29; 95% CI 0.98–1.66). The SIR for CRC as SPC was 0.84 (95% CI 0.70–1.01). No increased incidence was found for lung, prostate, breast, thyroid and liver cancer. The SIR for SPC overall and several cancers decreased with time of follow-up. Conclusions: In this population, CRC survivors have an 11% higher risk of developing a SPC than the general population, particularly cancers of the ovary, kidney, endometrium, bladder and stomach. Follow-up for SPC is required, especially during the first 5 years from CRC diagnosis.

Machine Learning in Prediction of Second Primary Cancer and Recurrence in Colorectal Cancer

BACKGROUND

Colorectal cancer (CRC) is the third commonly diagnosed cancer worldwide. Recurrence of CRC (Re) and onset of a second primary malignancy (SPM) are important indicators in treating CRC, but it is often difficult to predict the onset of a SPM. Therefore, we used mechanical learning to identify risk factors that affect Re and SPM.

PATIENT AND METHODS

CRC patients with cancer registry database at three medical centers were identified. All patients were classified based on Re or no recurrence (NRe) as well as SPM or no SPM (NSPM). Two classifiers, namely A Library for Support Vector Machines (LIBSVM) and Reduced Error Pruning Tree (REPTree), were applied to analyze the relationship between clinical features and Re and/or SPM category by constructing optimized models.

RESULTS

When Re and SPM were evaluated separately, the accuracy of LIBSVM was 0.878 and that of REPTree was 0.622. When Re and SPM were evaluated in combination, the precision of models for SPM+Re, NSPM+Re, SPM+NRe, and NSPM+NRe was 0.878, 0.662, 0.774, and 0.778, respectively.

CONCLUSIONS

Machine learning can be used to rank factors affecting tumor Re and SPM. In clinical practice, routine checkups are necessary to ensure early detection of new tumors. The success of prediction and early detection may be enhanced in the future by applying "big data" analysis methods such as machine learning.