Table 1.

Characteristics of the dataset and the features used by the model in this study.

(#) Feature	Total n = 99,232		COVID-19 negative n = 90,839		COVID-19 positive n = 8393
	n	%	n	%	n	%
(1) Sex
Male	50,350	50.74	45,545	50.1	4805	57.2
Female	48,882	49.26	45,294	49.8	3588	42.7
(2) Age 60+
True	15,279	15.4	13,619	14.9	1660	19.7
False	83,953	84.6	77,220	85	6733	80.2
(3) Cough
True	14,768	14.88	10,715	11.8	4053	48.2
False	84,223	84.87	79,909	87.9	4314	51.4
(4) Fever
True	8122	8.18	4387	4.83	3735	44.5
False	90,868	91.5	86,237	94.9	4631	55.1
(5) Sore throat
True	1273	1.28	96	0.11	1177	14
False	95,062	95.8	88,059	96.9	7003	83.4
(6) Shortness of breath
True	930	0.94	71	0.08	859	10.2
False	95,405	96.14	88,084	96.9	7321	87.2
(7) Headache
True	1799	1.81	68	0.07	1731	20.6
False	94,536	95.27	88,087	96.9	6449	76.8
(8) Known contact with an individual confirmed to have COVID-19
True	5507	5.55	1455	1.6	4052	48.2
False	93,725	94.45	89,384	98.4	4341	51.8