• 沒有找到結果。

A data-mining technique-association rule mining-was applied to identify the comorbidity of acne patients.

N/A
N/A
Protected

Academic year: 2021

Share "A data-mining technique-association rule mining-was applied to identify the comorbidity of acne patients. "

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

利用資料探勘方法探討痤瘡患者共患疾病 以全民健康保險— 學術研究資料庫為例

痤瘡為皮膚科非常常見而且重要的疾病。本研究以資料探勘方法探討痤瘡患者共患疾病,闡釋其臨床 意義,並經由焦點團體座談驗證資料探勘的結果及臨床實務的影響。

共患疾病的研究對於醫務管理臨床實務有重要影響,對共患疾病組合的了解,有助於設計醫療行銷的 方案、提升就醫方便性及可近性的貼心安排、預防醫學的發展以及加強醫療院所申報資料的偵錯等。

本研究擷取 2002 年四月至九月全民健康保險學術研究資料庫的門診資料,進行資料探勘中關聯法則 的分析,以探討痤瘡患者的共患疾病。研究期間內痤瘡患者的人數為 541,255 人,關聯法則探勘的條 件設定為最小支持度為 1.0% ,最小信賴度為 60% ,共得到 30 條有關其他疾病和痤瘡共病的規則。

本研究的結論為 :

1. 資料探勘中的關聯法則能應用於共患疾病的分析。

2. 急性呼吸道感染、皮膚科的常見疾病、腸胃炎及近視為痤瘡患者重要的常見疾病。

3. 痤瘡患者的共患疾病確實影響痤瘡患者的治療計畫及醫療資源耗用。

根據本研究的研究結果提出以下建議:

(1) 建議衛生主管機關建立制度以提升健保資料庫的完整性與可信度,期能增加研究分析的正確性與 應用性。(2) 建議醫學教育單位於實習課程中,加入國際疾病分類號編碼的相關課程,以提升臨床醫師正確輸 入國際疾病分類號的能力。

(3) 建議醫院可針對痤瘡患者共患疾病的相關科別,改善就診動線與門診時間,以增加病人就醫的方 便性。(4) 建議未來的研究可以在國際疾病分類號之外,增加費用、處置、藥品等欄位串檔分析,以提昇研 究的正確性與應用範圍,並考慮將多達 12,000 的國際疾病分類號加以分群,以減少資料過於分散的 影響,能更確切的了解共患疾病和痤瘡之間的關聯。

關鍵字:痤瘡、關聯法則、資料探勘、共患疾病、健保資料庫。

(2)

Application of Data Mining for Comorbidity of Acne Patients- An Example of National Health Insurance Research Database

Acne vulgaris is a very common and important disease in dermatology outpatients. The purposes of this stu dy were to clarify the comorbidity of acne patients in Taiwan for outpatient services and their related factor s using modern data-mining techniques.

The combination of comorbidity is very important for health care administration. They can be applied to de sign medical marketing and increase the accessibility.

A data-mining technique-association rule mining-was applied to identify the comorbidity of acne patients.

Data from April, 2002 to September, 2002 of National Health Insurance Research Database were studied.

Among a total of 541,255 acne patients were analysed, nearly 90% of their age are between 10 to 39 years old. Using association rule mining with a 1.0% minimum support factor and 60% minimum confidence fac tor, there were 30 association rules between other diseases and acne.

The major findings were:

1. Association rule mining techniques can identify the comorbidity of acne patients.

2. Upper respiratoy tract infections, common skin diseases, gastroenteritis and myopia were dominant com orbidities of acne patients.

3. These comorbidities truly affect the therapeutic plans and medical expenditure of acne patients.

Based on the findings, there are four suggestions: (1) The Department of Health can set up the system to str engthen the completeness and reliability of insurance claims database. (2) Medical schools can add coding courses in the internship of medical students for increase the coding ability of physicians. (3) Hospitals can arrange the outpatient clinics of associated specialists to improve the medical accessibility. (4) Further stud ies can add other variables and icd grouping method to clarify the relevance between comorbidity and acne .

Keywords: acne, association rule, data mining, comorbidity, insurance claims database.

參考文獻

相關文件

• Information retrieval : Implementing and Evaluating Search Engines, by Stefan Büttcher, Charles L.A.

Since the FP-tree reduces the number of database scans and uses less memory to represent the necessary information, many frequent pattern mining algorithms are based on its

This bioinformatic machine is a PC cluster structure using special hardware to accelerate dynamic programming, genetic algorithm and data mining algorithm.. In this machine,

We try to explore category and association rules of customer questions by applying customer analysis and the combination of data mining and rough set theory.. We use customer

Furthermore, in order to achieve the best utilization of the budget of individual department/institute, this study also performs data mining on the book borrowing data

Step 5: Receive the mining item list from control processor, then according to the mining item list and PFP-Tree’s method to exchange data to each CPs. Step 6: According the

(1999), "Mining Association Rules with Multiple Minimum Supports," Proceedings of ACMSIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego,

Since Dolby AC-3(abbreviated as AC-3) is the main technology of the surrounding sound format, in this thesis, we proposes a data model for mining the relationship between