TY  - EJOU
AU  - Afzal, Uzma 
AU  - Mahmood, Tariq 
AU  - Qamar, Ali Mustafa 
AU  - Khan, Ayaz H. 

TI  - Managing Health Treatment by Optimizing Complex Lab-Developed Test Configurations: A Health Informatics Perspective
T2  - Computers, Materials \& Continua

PY  - 2023
VL  - 75
IS  - 3
SN  - 1546-2226

AB  - A complex Laboratory Developed Test (LDT) is a clinical test developed within a single laboratory. It is typically configured from many feature constraints from clinical repositories, which are part of the existing Laboratory Information Management System (LIMS). Although these clinical repositories are automated, support for managing patient information with test results of an LDT is also integrated within the existing LIMS. Still, the support to configure LDTs design needs to be made available even in standard LIMS packages. The manual configuration of LDTs is a complex process and can generate configuration inconsistencies because many constraints between features can remain unsatisfied. It is a risky process and can lead patients to undergo unnecessary treatments. We proposed an optimized solution (opt-LDT) based on Genetic Algorithms to automate the configuration and resolve the inconsistencies in LDTs. Opt-LDT encodes LDT configuration as an optimization problem and generates a consistent configuration that satisfies the constraints of the features. We tested and validated opt-LDT for a local secondary care hospital in a real healthcare environment. Our results, averaged over ten runs, show that opt-LDT resolves 90% of inconsistencies while taking between 6 and 6.5 s for each configuration. Moreover, positive feedback based on a subjective questionnaire from clinicians regarding the performance, acceptability, and efficiency of opt-LDT motivates us to present our results for regulatory approval.
KW  - Artificial intelligence; health informatics; evolutionary algorithms; genetic algorithms; feature selection; laboratory developed test

DO  - 10.32604/cmc.2023.037653