Computer simulation of diabetic retinopathy screening adherence : Agent based model with fuzzy logic

摘要

Diabetic retinopathy is a major cause of blindness in developed countries. Since this disease remains asymptomatic in the early stages, periodic screening is of utmost importance. However, the success of screening programmes depends largely on the adherence of the target population. Thus, the development of computer simulations that make it possible to understand the factors correlated with the individual decision to adhere to the screening or not, to predict low adherence rates and to define strategies that promote its increase, is very useful. The aim of the present research is to demonstrate that it is possible to simulate the behavior of adherence to screening, using a model with a high degree of abstraction and scalability. To this end, a model based on agents with fuzzy logic was developed, calibrated, and validated using real data from 271,867 calls for screening in the Northern Regional Health Administration. The results obtained are very close to the real ones, both in the training and in the test sets, which attests to the validity of the model for the study of this problem and use as a predictive tool for public health planning.