Fig 1.
A perspective of system development steps.
Table 1.
Format of the records to show the relationship.
Table 2.
An example of observed information from a patient.
Table 3.
Format of the probability table for retinopathy.
Table 4.
A dataset showing the relation between HbA1c and NPDR.
Fig 2.
The models made by the neural network (HbA1c-all).
Table 5.
The statistical indices of ANN patterns.
Fig 3.
A scatter graph between HbA1c level and risk of PDR.
Fig 4.
The best fitted function (quadratic) to the HbA1c-Micro set of data.
Table 6.
Statistical indices of selected seven patterns for HbA1c-Micro data table.
Fig 5.
Bayesian network created by factors and complications.
Fig 6.
A piece of probability table for DR.
Fig 7.
A piece of probability table for macroalbuminuria.
Fig 8.
A Bayesian network calculates the probability of complications for a patient.
Table 7.
Statistical details of ANN and the best fitted regression models.
Table 8.
Sensitivity, specificity and precision rate of the model for all five complications.