Association analysis of factors influencing high hospitalization costs for cancer patients based on FP-Growth and Apriori algorithm
10.3760/cma.j.cn111325-20240418-00297
- VernacularTitle:基于FP-Growth与Apriori算法的肿瘤患者高额住院费用影响因素的关联分析
- Author:
Jingjing YE
1
;
Dian ZHOU
;
Di TIAN
;
Yuan ZHOU
;
Yu ZHANG
;
Manchen LYU
;
Tongbin XUE
;
Huan BAI
;
Cheng GUO
;
Ye WU
Author Information
1. 安徽医科大学第一附属医院医患关系办公室，合肥 230022
- Publication Type:Journal Article
- Keywords:
Diagnosis related groups;
High hospitalisation costs;
Association rules;
FP-Growth algorithm;
Apriori algorithm
- From:
Chinese Journal of Hospital Administration
2025;41(3):216-222
- CountryChina
- Language:Chinese
-
Abstract:
Objective:Exploring the association rules of factors influencing high hospitalization costs for cancer patients, providing references for hospitals to optimize medical cost management measures.Methods:In the inpatient case information system of a tertiary general hospital, the medical record homepages of inpatients in the DRG groups of the oncology department in 2022 were obtained. The upper four scores of hospitalization costs was used as the threshold for patient grouping. Patients with hospitalization costs≥this threshold were the high-cost group, while other patients were control group; 12 factors, including age, gender, and admission condition, etc, were considered as potential influencing factors of high hospitalization costs. FP-Growth and Apriori algorithms were used to excavate the potential association rules between the influencing factors of high hospitalization costs. Logistic regression was used to analyze the independent influencing factors of high hospitalization costs.Results:A total of 5 512 hospitalized patients were included, including 1 378 patients in the high-cost group. Thirteen validated strong association rules for factors influencing high hospitalization costs were obtained, of which the rule antecedents included age (≥70 years), number of days in hospital (≥7 days), other diagnoses (≥5), surgery, planned readmission, use of antibiotics, admission (general/critical), living admission score (61~99), level of care (level 1/level 2), non-day ward, criticality during hospitalisation. Logistic regression results showed that all nine influencing factors except gender, use of antibiotics, and readmission plans were independent influences on high hospitalization costs ( P<0.05). Conclusions:The joint application of FP-Growth and Apriori algorithm could effectively explore the association rules of high hospitalization costs for oncology patients. The early warning information mainly included the number of hospitalization days, the number of other diagnoses, surgeries, and so on. It was suggested that medical institutions can reasonably control the high hospitalization costs through clinical pathway management, diagnosis and treatment process reengineering, admission risk assessment, and multidisciplinary collaborative diagnosis and treatment strategies.
