發(fā)布時(shí)間：2018-04-28 10:15

  本文選題：臨床行為序列 + 序列聚類　； 參考：《江蘇大學(xué)》2017年碩士論文

【摘要】：目前,醫(yī)療保險(xiǎn)的服務(wù)范圍和面對(duì)的人群不斷擴(kuò)大,伴隨而生的醫(yī)療欺詐及違規(guī)行為屢見(jiàn)不鮮。由于醫(yī)療領(lǐng)域高度的專業(yè)性以及醫(yī)保交易的三方(醫(yī)保機(jī)構(gòu)、醫(yī)療單位、患者)存在著信息不對(duì)稱,醫(yī)療異常行為對(duì)醫(yī)保機(jī)構(gòu)而言具有相當(dāng)?shù)碾[蔽性。為此,研究臨床異常行為的發(fā)現(xiàn)方法,對(duì)規(guī)范醫(yī)療秩序、預(yù)防醫(yī)療欺詐行為的發(fā)生具有重要的理論研究和實(shí)際應(yīng)用價(jià)值。結(jié)合國(guó)內(nèi)外的研究成果,本文分析了臨床行為序列的時(shí)序性和自然凝聚性的特點(diǎn),利用二分K均值算法對(duì)正常臨床行為序列數(shù)據(jù)集進(jìn)行聚類,將得到的簇作為正常輪廓,針對(duì)臨床醫(yī)療事件異常行為的特征,研究了基于距離的異常檢測(cè)技術(shù),實(shí)現(xiàn)了臨床異常檢測(cè)原型系統(tǒng),用以發(fā)現(xiàn)臨床醫(yī)療數(shù)據(jù)中潛藏的異常行為。本文的主要工作如下:(1)提出基于整體相似度匹配的二分K均值序列聚類算法(PSClu)。PSClu對(duì)二分K均值算法的距離計(jì)算方式進(jìn)行優(yōu)化,采用編輯距離作為簇間序列相似性度量的函數(shù),結(jié)合編輯距離的上下界、等長(zhǎng)前綴子序列的編輯距離計(jì)算以及簇的質(zhì)心近似求解方法,過(guò)濾部分編輯距離的計(jì)算,降低二分K均值算法的時(shí)間復(fù)雜度,最終快速聚類生成正常臨床行為序列的簇。(2)提出待檢序列到簇質(zhì)心的相似度計(jì)算方法。為更有效的發(fā)現(xiàn)異常的臨床行為序列,在比較用藥事件相似度時(shí),研究了在藥效相似性的基礎(chǔ)上加入了藥物用量和價(jià)格相似性的比較,并根據(jù)醫(yī)療行為重要性的差異,采用了加權(quán)編輯距離算法(WED)計(jì)算待檢序列與簇質(zhì)心的相似度。(3)構(gòu)建異常檢測(cè)模型。利用PSClu算法對(duì)序列聚類生成正常簇,并以這些簇作為正常輪廓;引入WED算法計(jì)算待檢序列與簇質(zhì)心的相似度,以待檢序列與正常序列簇質(zhì)心的差異程度作為判斷是否存在異常的依據(jù),構(gòu)建包含數(shù)據(jù)預(yù)處理、聚類生成、相似性判斷等機(jī)制的異常檢測(cè)模型。(4)設(shè)計(jì)并實(shí)現(xiàn)了原型系統(tǒng),基于異常檢測(cè)模型,對(duì)原型系統(tǒng)的頁(yè)面、服務(wù)層、持久層等進(jìn)行了實(shí)現(xiàn)。通過(guò)某醫(yī)療機(jī)構(gòu)的臨床行為數(shù)據(jù),對(duì)該異常檢測(cè)系統(tǒng)的性能進(jìn)行分析和評(píng)價(jià)。
[Abstract]:At present, the scope of medical insurance services and the face of the continuous expansion of the population, accompanied by medical fraud and irregularities are common. Due to the highly professional nature of medical field and the existence of information asymmetry in medical insurance institutions, medical units and patients, the abnormal behavior of medical care is quite hidden to medical insurance institutions. Therefore, it is of great theoretical and practical value to study the discovery methods of clinical abnormal behavior in order to standardize medical order and to prevent the occurrence of medical fraud. Combined with the domestic and foreign research results, this paper analyzes the characteristics of sequence timing and natural cohesion of clinical behavior sequence, using binary K-means algorithm to cluster the data set of normal clinical behavior sequence, and taking the cluster as the normal contour. According to the characteristics of abnormal behavior of clinical medical events, the distance based anomaly detection technology is studied, and a prototype system of clinical abnormal detection is implemented, which can be used to detect the hidden abnormal behavior in clinical medical data. The main work of this paper is as follows: (1) A binary K-means clustering algorithm based on global similarity matching is proposed. PSClu.PSClu optimizes the distance calculation method of the binary K-means algorithm, and uses the edit distance as the function of similarity measurement between clusters. Combined with the upper and lower bounds of editing distance, the calculation of editing distance of equal length prefix sub-sequence and the approximate solution of cluster centroid, the computation of partial editing distance is filtered to reduce the time complexity of binary K-means algorithm. Finally, a fast clustering method is proposed to calculate the similarity between the test sequence and the cluster centroid. In order to find the sequence of abnormal clinical behaviors more effectively, when comparing the similarity of drug use events, the comparison of drug dosage and price was added on the basis of drug efficacy similarity, and according to the difference of importance of medical behavior, The weighted Editing distance algorithm (WED) is used to calculate the similarity between the detection sequence and the cluster centroid. PSClu algorithm is used to generate normal clusters for sequence clustering, and these clusters are used as normal contours. WED algorithm is introduced to calculate the similarity between sequences and cluster centroids. Based on the difference between the centroid of the cluster to be detected and the normal sequence as the basis for judging the existence of anomalies, a prototype system is designed and implemented, which includes data preprocessing, clustering generation, similarity judgment and other mechanisms. Based on the anomaly detection model, the page, service layer and persistence layer of the prototype system are implemented. Based on the clinical behavior data of a medical institution, the performance of the anomaly detection system is analyzed and evaluated.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R197.3;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳興蜀;吳小松;王文賢;王海舟;;基于特征關(guān)聯(lián)度的K-means初始聚類中心優(yōu)化算法[J];四川大學(xué)學(xué)報(bào)(工程科學(xué)版);2015年01期

2 姜華;韓安琪;王美佳;王崢;吳栻玲;;基于改進(jìn)編輯距離的字符串相似度求解算法[J];計(jì)算機(jī)工程;2014年01期

3 肖強(qiáng);;移動(dòng)醫(yī)生工作站的功能和類型探討[J];中國(guó)數(shù)字醫(yī)學(xué);2013年02期

4 謝晴宇;孟慶剛;王永炎;;中醫(yī)臨床路徑實(shí)踐模式的思考[J];北京中醫(yī)藥大學(xué)學(xué)報(bào);2013年01期

5 郭艷平;顏文俊;;基于EMD和優(yōu)化K-均值聚類算法診斷滾動(dòng)軸承故障[J];計(jì)算機(jī)應(yīng)用研究;2012年07期

6 彭明強(qiáng);;臨床路徑的國(guó)內(nèi)外研究進(jìn)展[J];中國(guó)循證醫(yī)學(xué)雜志;2012年06期

7 錢(qián)鵬江;王士同;鄧趙紅;;基于稀疏Parzen窗密度估計(jì)的快速自適應(yīng)相似度聚類方法[J];自動(dòng)化學(xué)報(bào);2011年02期

8 徐琴珍;楊綠溪;;一種優(yōu)化的神經(jīng)網(wǎng)絡(luò)樹(shù)異常入侵檢測(cè)方法[J];信號(hào)處理;2010年11期

9 李亞楠;許晟;王斌;;基于加權(quán)SimRank的中文查詢推薦研究[J];中文信息學(xué)報(bào);2010年03期

10 賀玲;蔡益朝;楊征;;高維數(shù)據(jù)聚類方法綜述[J];計(jì)算機(jī)應(yīng)用研究;2010年01期

相關(guān)博士學(xué)位論文 前1條

1 郁繼鋒;基于數(shù)據(jù)挖掘的Web應(yīng)用入侵異常檢測(cè)研究[D];華中科技大學(xué);2011年

相關(guān)碩士學(xué)位論文 前4條

1 張傳玉;基于序列模式挖掘的臨床異常行為檢測(cè)[D];江蘇大學(xué);2016年

2 劉瑩霞;鏈碼技術(shù)和聚類分析在基因序列中的應(yīng)用[D];華南理工大學(xué);2012年

3 王玨;序列挖掘在臨床行為模式發(fā)現(xiàn)中的應(yīng)用研究[D];江蘇大學(xué);2008年

4 莊軍;基于臨床合理用藥的數(shù)據(jù)挖掘技術(shù)和應(yīng)用研究[D];重慶大學(xué);2006年

，

本文編號(hào)：1814840