Abstract
An essential criterion for the proper implementation of case-control studies is selecting appropriate case and control groups. In this article, a new simulated annealing-based control group selection method is proposed, which solves the problem of selecting individuals in the control group as a distance optimization task. The proposed algorithm pairs the individuals in the n-dimensional feature space by minimizing the weighted distances between them. The weights of the dimensions are based on the odds ratios calculated from the logistic regression model fitted on the variables describing the probability of membership of the treated group. For finding the optimal pairing of the individuals, simulated annealing is utilized. The effectiveness of the newly proposed Weighted Nearest Neighbours Control Group Selection with Simulated Annealing (WNNSA) algorithm is presented by two Monte Carlo studies. Results show that the WNNSA method can outperform the widely applied greedy propensity score matching method in feature spaces where only a few covariates characterize individuals and the covariates can only take a few values.
Highlights
Observational studies are widely applied data analysis methods mainly used in healthcare [1,2,3,4,5]
We found that k = bk min ∗ 1.15c was the right choice in all cases, and the algorithm quickly found the right pairings of elements
The standardized mean difference (SMD) values for all matching and covariates were less than 0.1, which confirms that according to the general evaluation principles, all results on all covariates can be seen as well-balanced
Summary
Observational studies are widely applied data analysis methods mainly used in healthcare [1,2,3,4,5] In these studies, the effect of a treatment, a risk factor, or other intervention is evaluated by performing a comparative analysis. The comparison is based on the analysis of the results of two groups, the treated and the untreated (control) groups, and the investigator has no control over the assignment of the subjects into the groups. Such analyses are carried out, for example, when the effectiveness of a drug for a particular disease is to be assessed (e.g., how effective a drug is at treating heart failure). The simplest solution is based on stratified matching, but balancing score-based methods can be used, and pairing of the treated and untreated individuals can be performed in the n-dimensional space of the covariates
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
