The validity of synthetic clinical data: a validation study of a leading synthetic data generator (Synthea) using clinical quality measures

Table 2 Comparison of Demographics between SyntheticMass and Real World Populations [27,28,29]

	SyntheticMass	Reference Population Estimates
Total Population	1,193,439	6,547,629
Age
< 18	19.2%	21.7%
18–64	64.5%	64.5%
≥ 65	16.3%	13.8%
Average	40	39.1
Female	51%	51.6%
BMI (Adult)
< 18.5	2%	N/A^b
18.5–24.99	15.4%	N/A^b
25–29.99	20%	35.6%
≥ 30	62.6%	23.3%
Male Average	31	28.7
Female Average	32	29.2
Average Height (cm)
Male	176.77	175.77^a
Female	163.33	161.80^a
Average Weight (kg)
Male	97.98	88.77^a
Female	86.04	76.43^a
Adults ≥20 years old with High Blood Pressure	30.92%	33.4%

^aNationally Reported Rate, all other rates shown reflect Massachusetts population
^bNo publically reported data found for reference

ISSN: 1472-6947