Skip to main content

Table 1 List of risk factors (features) used in the study and the survey results

From: Helicobacter pylori (H. pylori) risk factor analysis and prevalence prediction: a machine learning-based approach

Feature

Response

H. pylori ( +)

H. pylori (−)

Residence

Urban

293 (54.3%)

247 (45.7%)

Rural

50 (12.1%)

364 (87.9%)

Allergies

Any allergic disease

70 (31%)

156 (69%)

No allergies

273 (37.5%)

455 (62.5%)

Parasites

Any parasites found

110 (37.2%)

186 (62.8%)

No parasites

233 (35.4%)

425 (64.6%)

Cooking area

Inside house

276 (33.5%)

547 (66.5%)

Outside house

67 (51.1%)

64 (48.9%)

Dewormed status

Dewormed

247 (33.7%)

487 (66.3%)

Not dewormed

96 (43.6%)

124 (56.4%)

Cow

Family owns cow(s)

47 (23.4%)

154 (76.6%)

No cow(s)

296 (39.3%)

457 (60.7%)

Smoking

Smoker in household

10 (16.4%)

51 (83.6%)

No smokers

333 (37.3%)

560 (62.7%)

Cat

No cat

257 (38.6%)

408 (61.4%)

Cat lives inside

53 (25.4%)

156 (74.6%)

Cat lives outside

33 (41.3%)

47 (58.7%)

Dog

No dog

228 (40.1%)

341 (59.9%)

Dog lives inside

0 (0%)

4 (100%)

Dog lives outside

115 (30.2%)

266 (69.8%)

Electricity use

Every day

273 (55.2%)

222 (44.8%)

Sometimes

11 (12.8%)

75 (87.2%)

Never

59 (15.8%)

314 (84.2%)

Floor in Home

Cement

150 (36.8%)

258 (63.2%)

Wood

4 (20%)

16 (80%)

Mud

186 (35.9%)

332 (64.1%)

Other

3 (37.5%)

5(62.5%)

Waste disposal

Garbage bin

80 (44.2%)

101 (55.8%)

Pit

56 (36.6%)

97 (63.4%)

Open field

26 (12.6%)

181 (87.4%)

Burn

181 (43.8%)

232 (56.2%)

Age

0–5 years

43 (47.3%)

48 (52.7%)

6–10 years

167 (39.3%)

258 (60.7%)

11–15 years

133 (30.4%)

305 (69.6%)

Family size

0–3 people

55 (34.6%)

104 (65.4%)

4–5 people

165 (35.6%)

299 (64.4%)

 > 5 people

123 (37.2%)

208 (62.8%)

Toilet

Flush toilet

10 (25%)

30 (75%)

Pit toilet

325 (38.7%)

514 (61.3%)

Open field

8 (10.7%)

67 (89.3%)

Water source

Piped

327 (38.3%)

526 (61.7%)

Well

12 (15.4%)

66 (84.6%)

River or rain water

4 (17.4%)

19 (82.6%)

  1. The reference group is the one that is bolded in the response column