Читать книгу Healthcare Systems - Группа авторов - Страница 35

In order to ensure better patient care, we develop a platform that optimizes routes by taking into account the constraints related to patients and caregivers. The medical and coordination staff can thus communicate with each other and receive information on the patients treated and those still waiting for treatment. The platform is developed used for both offline planning and online rescheduling. It also allows the HHC schedule coordinator to record and consult the information needed. The main component of this platform is the genetic clustering algorithm. This algorithm communicates with Google Maps API to display the routes of caregivers as well as the geographical location of patients.

The algorithm assigns caregivers to patients based on availability, qualification and preference constraints. Patients are automatically identified on the map via their address, which is used for the calculation of the distances traveled. The routes are then determined according to the constraints. If a caregiver is absent or late, their status is updated and the routes are recalculated in order to take this information into account.

The results obtained from the route planning and calculation experiments are presented in Table 2.1. We tested the algorithm on examples ranging from 2 to 16 careworkers with 2 to 64 patients. The computation times remained quite fast; however, we noticed that as the number of patients and caregivers increases, the computation time becomes longer.

Table 2.1. Results and experiments

Number of caregivers	Number of patients	Computation time (s)
2	2 4 8	1.58 3.27 5.09
4	4 8 16	7.43 10.60 12.44
8	8 16 32	13.80 14.38 16.73
16	16 32 64	18.62 20.01 22.69

Table 2.2. Case of rescheduling with disruptions

Number of disturbances	Number of reassigned visits per caregiver	Computation time (s)
1	1 2 3	4.66-5.09 4.66-5.09 4.66-5.09
2	1 2 3	4.66-5.09 4.66-5.09 4.66-5.09
2	1 2 3	4.66-5.09 4.66-5.09 4.70-5.36

We also tested the rescheduling algorithm by adding disruptions represented by staff absences. The rescheduling phase can occur after the first route is calculated. Table 2.2 presents the results obtained when we have one to four disruptions. These visits are reassigned to other caregivers, and we find that each caregiver has one to three visits added to their initial schedule. Rescheduling is achieved in seconds. It is very efficient for the coordinator who needs a reactive system.