Skip to main content

Table 1 The different virtual subjects have been generated by varying the parameters in this table and corresponding to 46,170 different initial conditions

From: Potential predictors of type-2 diabetes risk: machine learning, synthetic data and wearable health devices

Anthropometric measures

 Sex \(S\in \{female, male\}\)

 Age \(A\in \{28, 38, 48, 58, 68\}\)

 Weight \(W\in \{ underweight, normal, overweight \}\)

 Height \(H\in \{ short, average, tall \}\)

Physical activity

 Number of sessions per week \(N_{\mathrm{PA}} \in \{ 0, 1, 2, 3\}\)

 Duration (mins) \( D_{\mathrm{PA}} \in \{ low=30, medium=60, high=90 \}\)

 Intensity (% of \(\hbox {VO}_{\mathrm{2max}}\)) \(I_{\mathrm{PA}} \in \{ low = 40, high = 60 \}\)

Food intake (3 meals per day, breakfast, lunch, dinner)

 Carbohydrates (grams) \(C_{\mathrm{ME}} \in \{ low, med, high \}\)

 Proteins (grams) \(P_{\mathrm{ME}} \in \{ low, med, high \}\)

 Fats (grams) \(F_{\mathrm{ME}} \in \{ low, med, high \}\)