Table 2. Descriptive analysis (median and range) and results of the significance testing comparing different training plans generated by ChatGPT. Likert-Scale Ratings were from 1 (“bad”) to 5 (“good”) with 0 indicating “not applicable”.

		Median (Range)			Significance Testing
		TP 1	TP 2	TP 3	TP 1 vs TP 2	TP 1 vs TP 3	TP 2 vs TP 3
Primary Aspects	Overall training plan	2(2)	3(3)	4(2)	0.005	0.003	1.0
	Health Screening	2(3)	2(3)	3(3)	1.0	0.312	0.952
	Defined goal	0(3)	4(2)	4(3)	0.022	0.002	1.0
	Overall testing procedure	0 (0)	0 (0)	4(3)	1.0	0.004	0.004
	Testing procedure regarding initial performance status	0 (0)	0 (0)	4(4)	1.00	0.004	0.004
	Testing procedure regarding assessment of individual training variables	0 (0)	0 (0)	3(3)	1.00	0.004	0.004
	Testing procedure regarding assessment of training effects	0 (0)	0 (0)	3(3)	1.00	0.004	0.004
	Overall monitoring procedure	0(1)	1(3)	4(3)	1.00	0.002	0.03
	Monitoring procedure regarding assessment of internal load	0 (0)	3(4)	4(2)	0.135	0.00	0.135
	Monitoring procedure regarding assessment of external load	0(2)	3(4)	4(2)	0.101	0.00	0.221
	Monitoring procedure regarding assessment of contextual factors	0 (0)	0 (0)	3(4)	1.00	0.004	0.004
	Training type	3(4)	3(3)	5(3)	1.00	0.297	0.377
	Training volume	3(3)	4(1)	4(3)	0.656	0.101	1.00
	Training intensity	1(5)	4(2)	4(3)	0.076	0.042	1.00
	Training frequency	3(3)	4(2)	3(4)	1.00	0.055	0.377
	Progression of training volume	3(4)	4(2)	2(3)	1.00	0.101	0.656
	Progression of training intensity	1(3)	3(4)	4(2)	0.042	0.004	1.00
	Progression of training frequency	3(2)	4(5)	3(3)	1.00	0.791	1.00
Summary Median Rating	< 3	n = 15	n = 7	n = 1
	3	n = 3	n = 5	n = 6
	> 3	n = 0	n = 6	n = 11
Secondary Aspects	Nutritional aspects	0 (0)	1(4)	4(2)	0.438	0.00	0.042
	Recovery aspects	2(3)	3(3)	4(4)	0.281	0.057	1.00
	Psychological skills	0 (0)	0 (0)	3(4)	1.00	0.004	0.004
	Skill Acquisition	0 (0)	0 (0)	3(4)	1.00	0.008	0.008
Summary Median Rating	> 3	n = 4	n = 4	n = 0
	3	n = 0	n = 0	n = 2
	> 3	n = 0	n = 0	n = 2

Bold numbers comparing different training plans indicate significant differences (p < 0.05).