Application of data mining methods to improve screening for the risk of early gastric cancer

Table 7 Important independent variables for the risk of EGC

Variables	C5.0 DT	TAN	MLP	LR	Total
Occupations	0.03	0.10	0.04	0.04	0.21
HP infection	0.03	0.05	0.04	0.09	0.21
HP antibody	0.03	0.02	0.04	0.11	0.20
Weight	0.03	0.08	0.07	0.02	0.20
Drinking-water source	0.03	0.04	0.03	0.06	0.16
Age	0.03	0.03	0.06	0.03	0.15
Pepsinogen I	0.03	0.02	0.08	0.02	0.15
Gastrin 17	0.04	0.02	0.07	0.02	0.15
Education levels	0.03	0.02	0.03	0.05	0.13
Residences	0.03	0.04	0.02	0.04	0.13
BMI	0.03	0.03	0.04	0.02	0.12
PepsinogenI/II	0.03	0.02	0.05	0.02	0.12
Languages	0.03	0.02	0.03	0.04	0.12
Tea	0.03	0.06	0.01	0.02	0.12
Drinking hot water	0.03	0.03	0.02	0.04	0.12
Gastroscopy	0.03	0.03	0.03	0.03	0.12
High salt intake	0.03	0.05	0.01	0.02	0.11
Abdominal pain	0.03	0.03	0.02	0.03	0.11
Hypertension	0.03	0.03	0.03	0.02	0.11
Hyperlipidemia	0.03	0.03	0.03	0.02	0.11
Smoking	0.03	0.03	0.02	0.02	0.10
Heartburn	0.03	0.02	0.03	0.02	0.10
Pepsinogen II	0.03	0.02	0.03	0.02	0.10
Fruit	0.03	0.02	0.02	0.02	0.09
Acid reflux	0.03	0.02	0.02	0.02	0.09
Postprandial distress	0.02	0.02	0.03	0.02	0.09
Speed of eating	0.03	0.03	0.02	0.01	0.09
Abdominal distension	0.03	0.01	0.02	0.03	0.09
Drinking	0.03	0.02	0.01	0.02	0.08
Sex	0.03	0.02	0.01	0.01	0.07
Pickled foods	0.03	0.01	0.01	0.02	0.07
Early satiety	0.03	0.01	0.01	0.02	0.07
Belching	0.03	0.01	0.01	0.01	0.06
No obvious symptom	0.01	0.01	0.01	0.02	0.05

The sum of the 34 independent variables’ importance calculated by each model is equal to one. The sum of the 34 independent variables’ total importance is 4

ISSN: 1472-6947