Table 5 Baseline characteristics between the train and test dataset for the categorical variables
From: Predicting high blood pressure using machine learning models in low- and middle-income countries
Variable | Total population | Train dataset | Test dataset |
|---|---|---|---|
Sex, \(n(\%)\) | |||
     female | 98902.0 (53.55) | 79050.0 (53.51) | 19852.0 (53.75) |
     male | 68096.0 (36.87) | 54565.0 (36.93) | 13531.0 (36.63) |
     no response | 17676.0 (9.57) | 14124.0 (9.56) | 3552.0 (9.62) |
level of education, \(n(\%)\) | |||
     elementary school | 67226.0 (36.40) | 53810.0 (36.42) | 13416.0 (36.32) |
     high school | 52337.0 (28.34) | 41891.0 (28.35) | 10446.0 (28.28) |
     no formal schooling | 32767.0 (17.74) | 26269.0 (17.78) | 6498.0 (17.59) |
     tertiary | 19993.0 (10.83) | 15959.0 (10.80) | 4034.0 (10.92) |
     no response | 12351.0 (6.69) | 9810.0 (6.64) | 2541.0 (6.88) |
marital status, \(n(\%)\) | |||
     married | 108653.0 (58.84) | 86865.0 (58.80) | 21788.0 (58.99) |
     not married | 29446.0 (15.94) | 23569.0 (15.95) | 5877.0 (15.91) |
     no response | 21506.0 (11.65) | 17250.0 (11.68) | 4256.0 (11.52) |
     widowed | 9677.0 (5.24) | 7814.0 (5.29) | 1863.0 (5.04) |
     cohabitating | 6291.0 (3.41) | 4984.0 (3.37) | 1307.0 (3.54) |
     divorced | 4977.0 (2.70) | 3976.0 (2.69) | 1001.0 (2.71) |
     separated | 4124.0 (2.23) | 3281.0 (2.22) | 843.0 (2.28) |
work status, \(n(\%)\) | |||
     employed | 83332.0 (45.12) | 66711.0 (45.15) | 16621.0 (45.00) |
     homemaker | 32866.0 (17.80) | 26435.0 (17.89) | 6431.0 (17.41) |
     unemployed | 29313.0 (15.87) | 23502.0 (15.91) | 5811.0 (15.73) |
     no response | 15891.0 (8.60) | 12613.0 (8.54) | 3278.0 (8.88) |
     student | 13117.0 (7.10) | 10396.0 (7.04) | 2721.0 (7.37) |
     retired | 10155.0 (5.50) | 8082.0 (5.47) | 2073.0 (5.61) |
currently smoke tobacco, \(n(\%)\) | |||
     no | 147737.0 (80.00) | 118191.0 (80.00) | 29546.0 (79.99) |
     yes | 29116.0 (15.77) | 23295.0 (15.77) | 5821.0 (15.76) |
     no response | 7821.0 (4.24) | 6253.0 (4.23) | 1568.0 (4.25) |
type tobacco, \(n(\%)\) | |||
     no response | 184414.0 (99.86) | 147529.0 (99.86) | 36885.0 (99.86) |
     cigarettes | 238.0 (0.13) | 192.0 (0.13) | 46.0 (0.12) |
     shisha | 19.0 (0.01) | 16.0 (0.01) | 3.0 (0.01) |
     cigars | 3.0 (0.00) | 2.0 (0.00) | 1.0 (0.00) |
smoke home workplace, \(n(\%)\) | |||
     no | 111323.0 (60.28) | 89033.0 (60.26) | 22290.0 (60.35) |
     no response | 37313.0 (20.20) | 29897.0 (20.24) | 7416.0 (20.08) |
     yes | 36038.0 (19.51) | 28809.0 (19.50) | 7229.0 (19.57) |
consumed alcohol, \(n(\%)\) | |||
     no | 101138.0 (54.77) | 80934.0 (54.78) | 20204.0 (54.70) |
     yes | 68693.0 (37.20) | 54961.0 (37.20) | 13732.0 (37.18) |
     no response | 14843.0 (8.04) | 11844.0 (8.02) | 2999.0 (8.12) |
quit drinking for health, \(n(\%)\) | |||
     no response | 171569.0 (92.90) | 137285.0 (92.92) | 34284.0 (92.82) |
     no | 7643.0 (4.14) | 6068.0 (4.11) | 1575.0 (4.26) |
     yes | 5462.0 (2.96) | 4386.0 (2.97) | 1076.0 (2.91) |
salt consumption, \(n(\%)\) | |||
     no response | 99523.0 (53.89) | 79551.0 (53.85) | 19972.0 (54.07) |
     normal | 53766.0 (29.11) | 43082.0 (29.16) | 10684.0 (28.93) |
     low | 16413.0 (8.89) | 13091.0 (8.86) | 3322.0 (8.99) |
     high | 14972.0 (8.11) | 12015.0 (8.13) | 2957.0 (8.01) |
work intensity, \(n(\%)\) | |||
     no response | 65581.0 (35.51) | 52339.0 (35.43) | 13242.0 (35.85) |
     moderate-intensity | 64134.0 (34.73) | 51384.0 (34.78) | 12750.0 (34.52) |
     vigorous-intensity | 54959.0 (29.76) | 44016.0 (29.79) | 10943.0 (29.63) |
had blood pressure measurement, \(n(\%)\) | |||
     yes | 97983.0 (53.06) | 78419.0 (53.08) | 19564.0 (52.97) |
     no | 67811.0 (36.72) | 54229.0 (36.71) | 13582.0 (36.77) |
     no response | 18880.0 (10.22) | 15091.0 (10.21) | 3789.0 (10.26) |
taken drugs for raised bp, \(n(\%)\) | |||
     no response | 148841.0 (80.60) | 119021.0 (80.56) | 29820.0 (80.74) |
     no | 22428.0 (12.14) | 17921.0 (12.13) | 4507.0 (12.20) |
     yes | 13405.0 (7.26) | 10797.0 (7.31) | 2608.0 (7.06) |
had blood sugar measurement, \(n(\%)\) | |||
     no | 126432.0 (68.46) | 101154.0 (68.47) | 25278.0 (68.44) |
     yes | 54113.0 (29.30) | 43272.0 (29.29) | 10841.0 (29.35) |
     no response | 4129.0 (2.24) | 3313.0 (2.24) | 816.0 (2.21) |
taken diabetes drugs, \(n(\%)\) | |||
     no response | 165765.0 (89.76) | 132600.0 (89.75) | 33165.0 (89.79) |
     yes | 17022.0 (9.22) | 13607.0 (9.21) | 3415.0 (9.25) |
     no | 1887.0 (1.02) | 1532.0 (1.04) | 355.0 (0.96) |
had cholesterol measurement, \(n(\%)\) | |||
     no | 87445.0 (47.35) | 69866.0 (47.29) | 17579.0 (47.59) |
     no response | 77040.0 (41.72) | 61670.0 (41.74) | 15370.0 (41.61) |
     yes | 20189.0 (10.93) | 16203.0 (10.97) | 3986.0 (10.79) |
taken cholesterol oral treatment, \(n(\%)\) | |||
     no response | 179155.0 (97.01) | 143288.0 (96.99) | 35867.0 (97.11) |
     no | 3835.0 (2.08) | 3095.0 (2.09) | 740.0 (2.00) |
     yes | 1684.0 (0.91) | 1356.0 (0.92) | 328.0 (0.89) |
had heart attack, \(n(\%)\) | |||
     no | 98979.0 (53.60) | 79176.0 (53.59) | 19803.0 (53.62) |
     no response | 76528.0 (41.44) | 61254.0 (41.46) | 15274.0 (41.35) |
     yes | 9167.0 (4.96) | 7309.0 (4.95) | 1858.0 (5.03) |
taking heart disease medication, \(n(\%)\) | |||
     no | 96645.0 (52.33) | 77291.0 (52.32) | 19354.0 (52.40) |
     no response | 83737.0 (45.34) | 66963.0 (45.33) | 16774.0 (45.41) |
     yes | 4292.0 (2.32) | 3485.0 (2.36) | 807.0 (2.18) |
treated for raised bp, \(n(\%)\) | |||
     no | 160181.0 (86.74) | 128063.0 (86.68) | 32118.0 (86.96) |
     no response | 12560.0 (6.80) | 10068.0 (6.81) | 2492.0 (6.75) |
     yes | 11933.0 (6.46) | 9608.0 (6.50) | 2325.0 (6.29) |
are you pregnant, \(n(\%)\) | |||
     no | 105556.0 (57.16) | 84437.0 (57.15) | 21119.0 (57.18) |
     no response | 74248.0 (40.20) | 59427.0 (40.22) | 14821.0 (40.13) |
     yes | 4870.0 (2.64) | 3875.0 (2.62) | 995.0 (2.69) |
blood pressure, \(n(\%)\) | |||
     high | 105677.0 (57.22) | 84523.0 (57.21) | 21154.0 (57.27) |
     normal | 78997.0 (42.78) | 63216.0 (42.79) | 15781.0 (42.73) |