Feed-forward neural network model for hunger and satiety related VAS score prediction

Table 2 Description of datasets: Oral intake and gastric infusion, Dataset C, and the test set: Dataset D. Dataset C used meals and gastric infusions, whereas dataset D only used meals

Data Source	Data Name	G	C	P	H	S	F	D	Sub	T _s	T _e	Ml/If	NPS
Dataset C	ho	✓	✓	✓	✓	✓	✓	✓	15	–10	180	30	9
	hs	✓	✓	✓	✓	✓	✓	✓	15	–10	180	30	9
	uhs	✓	✓	✓	✓	✓	✓	✓	15	–10	180	30	9
Dataset D	d3	✓	✗	✗	✓	✓	✓	✓	15	0	270	0	10
	d4	✓	✗	✗	✓	✓	✓	✓	15	0	270	0	10

The letters or abbreviation in the headers are as follows: DataName = macro-nutrient type or intake form; G = GLP-1 (pmol/l); C = CCK (pmol/l); P = PYY (pg/ml); H = VAS for Hunger; S = VAS for Satiety; F = VAS for Fullness; D = VAS for Desire to eat; Sub = Number of subjects; Ts = Tstart (min); Te = Tend (min); Ml/If = time point/range for Meal/Infusion; NPS = Number of Plasma Samples. A check mark (✓) indicates that the corresponding satiety hormone measurements and/or VAS scores were available, while a cross mark (✗) indicates non-availability of the measurements

ISSN: 1742-4682