A revelation about frequent itemset of stroke by using Apriori algorithm
10.3969/J.ISSN.1672-8270.2018.03.009
- VernacularTitle:使用Apriori算法揭示脑卒中的频繁集
- Author:
Wen-Qiao SUN
1
;
Lei SHI
;
Jian HE
Author Information
1. 解放军第210医院信息科 辽宁 大连 116021
- Keywords:
Stroke;
Rule pattern of risk factor;
Association rule mining;
Apriori algorithm
- From:
China Medical Equipment
2018;15(3):32-35
- CountryChina
- Language:Chinese
-
Abstract:
Objective: To study the rule pattern of risk factor of stroke through data analysis of preliminary screening of large-scale stroke. Methods: The preliminary screening data of risk factors in stroke were gathered from the National Center for Stroke Screening and Prevention and Control. And the association rules mining was adopted in the research. The relevant risk factors of stroke in large-scale crowd were researched, and 0.1% was chose as minimum support and 10% were used as minimum confidence coefficient. The rule mode of stroke was mined by using above conditions. Results: In the nine risk factors of the table of preliminary screening, there was a weak correlation between "transient ischemic attack (TIA) in past", "hypertension", "family history of stroke" and stroke, respectively. And TIA, atrial fibrillation or valvular heart disease, family history of stroke, hypertension and diabetes were the most important risk factors. At the same time, the study found that age would become an important risk factor for stroke when patient was older than 60. Conclusions: In the 21 presumptive rule patterns with big probability, some of them has not received sufficient attention in past. And the rule pattern of risk factor of stroke provides a new diagnostic basis with value.
