Genetic algorithm for scheduling of laboratory personnel

Background: Staffing core laboratories with appropriate skilled workers req uires a process to schedule these individuals so that all workstations are appropriately filled and all the skills of each worker are exercised period ically to maintain competence. Methods: We applied a genetic algorithm to scheduling laboratory personnel. Our program, developed in Visual Basic 4.0, maximizes the value of a fitne ss function that measures how well a given scheduling of individuals and th eir skills matches a set of work tasks for a given work shift. The user pro vides in an Excel spreadsheet the work tasks, individuals available to work on any given date, and skills each individual possesses. The user also spe cifies the work shift to be scheduled, the range of dates to be scheduled, the number of days that an individual stays on a given workstation before r otating, and various parameters for the genetic algorithm if they differ fr om the default values. Results: For >22 months, the program matched individuals to those tasks for which they were qualified and maintained personnel skills by rotating job duties. The schedules generated by the program allowed supervisory personne l to anticipate dates far in advance of when worker availability would be l imited, so staffing could be adjusted. In addition, the program helped to i dentify skills for which too few individuals had been trained. This program has been well accepted by the staff in the clinical laboratories of a 670- bed university medical center, saving 37 h of labor per month, or approxima tely $11 000 per year, in time that supervisory personnel have spent develo ping work schedules. Conclusions: The genetic algorithm approach appears to be useful for schedu ling in highly technical work environments that employ multiskilled workers . (C) 2001 American Association for Clinical Chemistry.