The concern about the diagnosis of problems affecting citrus led to an accumulation of knowledge over the years. However, such accumulated knowledge needed to be organized and efficiently disseminated. Thus, the aims of this work were to build a knowledge basis for the diagnosis of abiotic and biotic citrus diseases to develop and implement a Decision Support System (DSS) and to test and evaluate this system. DSS was built by using the tool 'Borland Delphi' version 5. A total of 562 questions were formulated, including 322 rules, besides photographs to help in the diagnosis of 34 diseases, 40 pests and 34 abiotics disturbances in citrus. DSS evolution was divided into verification and validation. In the verification phase, DSS was analyzed by means of a questionnaire applied to citrus specialists. The program validation phase inclued four groups of people, with different knowledge levels (10 people/group), trying to provide the correct diagnosis. Results indicated correct diagnosis by 45.6% of correctness of the interviewed people and a 93.6% when using the DSS was used. The system was nomed Dr. Citrus (prototype registered at INPI # 014070009188).
diagnostic; citrus; decision support
