Binary genetic algorithm for optimal joinpoint detection: Application to cancer trend analysis

Abstract

The joinpoint regression model (JRM) is used to describe trend changes in many applications and relies on the detection of joinpoints (changepoints). However, the existing joinpoint detection methods, namely, the grid search (GS)‐based methods, are computationally demanding, and hence, the maximum number of computable joinpoints is limited. Herein, we developed a genetic algorithm‐based joinpoint (GAJP) model in which an explicitly decoupled computing procedure for optimization and regression is used to embed a binary genetic algorithm into the JRM for optimal joinpoint detection. The combinations of joinpoints were represented as binary chromosomes, and genetic operations were performed to determine the optimum solution by minimizing the fitness function, the Bayesian information criterion (BIC) and BIC3. The accuracy and computational performance of the GAJP model were evaluated via intensive simulation studies and compared with those of the GS‐based methods using BIC, BIC3, and permutation test. The proposed method showed an outstanding computational efficiency in detecting multiple joinpoints. Finally, the suitability of the GAJP model for the analysis of cancer incidence trends was demonstrated by applying this model to data on the incidence of colorectal cancer in the United States from 1975 to 2016 from the National Cancer Institute's Surveillance, Epidemiology, and End Results program. Thus, the GAJP model was concluded to be practically feasible to detect multiple joinpoints up to the number of grids without requirement to preassign the number of joinpoints and be easily extendable to cancer trend analysis utilizing large datasets.

Cancer Detection and Prediction Using Genetic Algorithms

“…Kim et al [ 45 ] applied a binary GA with a Joinpoint Regression Model (JRM) in order to study trends in colorectal cancer. The GA worked towards optimizing both the number and the location of the joinpoints.…”

Significance of histology and nodal status on the survival of women with early-stage cervical cancer: validation of the 2018 FIGO cervical cancer staging system

“…This analysis was based on the rationale that high-risk patients exhibiting nodal metastasis are recommended to receive postoperative CCRT, as per the current guidelines [ 19 20 ], while the actual benefits of the other postoperative adjuvant treatments remain understudied for women with nodal metastasis. Additionally, temporal trends, analyzed using linear segmented regression, were assessed using The Joinpoint Regression Program (version 4.7.0.0), which was provided by the National Cancer Institute (Bethesda, MD, USA) [ 21 ]. A log transformation was subsequently performed to determine the annual percent change (APC) in the slope with a 95% CI.…”

Association between hospital treatment volume and survival of women with gynecologic malignancy in Japan: a JSOG tumor registry-based data extraction study

“…Additional analysis was performed to examine the robustness of the model using the Joinpoint Regression Program (National Institute of Health, Bethesda, MD, USA) [ 16 ]. Potential changes were found in the HR based on the annual hospital treatment volume.…”

“…Ordinal and categorical variables were analyzed using χ 2 test. The Joinpoint Regression Program 4.8.0.1 was used to determine potential changes in temporal trends in the proportion of each group for every calendar year [ 16 ]. Additionally, a binary logistic regression model was fitted to identify independent clinicopathological factors associated with high-volume centers.…”