本文關(guān)鍵詞： 醫(yī)保欺詐 醫(yī)療濫用 醫(yī)生信任度 內(nèi)部特征和網(wǎng)絡(luò)圖探索 非凸標(biāo)簽傳播算法　出處：《山東大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來,健康中國逐步上升為國家戰(zhàn)略,醫(yī)保建設(shè)在經(jīng)濟(jì)社會發(fā)展中占據(jù)著重要的地位。隨著醫(yī)療信息化的不斷普及和推進(jìn),醫(yī)保欺詐也越來越被確認(rèn)為一種嚴(yán)重的社會問題。醫(yī)療濫用是醫(yī)保欺詐中一種主要的欺詐方式,這種欺詐方式主要是指醫(yī)療機(jī)構(gòu)或醫(yī)生提供的藥品或者醫(yī)療用品與實際治療所用的不一致或者違背醫(yī)療用藥標(biāo)準(zhǔn),從而增加醫(yī)療保健支出。各種醫(yī)療保險欺詐案件屢見不鮮,大大損害了被保險人的利益,對醫(yī)�；鸬陌踩斐闪酥卮蟮膿p害,嚴(yán)重阻礙了醫(yī)保政策的實施和推廣。盡管,醫(yī)療欺詐不是最近發(fā)生的一種問題,并且各種欺詐檢測方法被提出來解決這個問題,但是醫(yī)療欺詐問題仍然沒有得到很好的解決。首先,一些基于檢測規(guī)則的傳統(tǒng)檢測方法通過專家定義的欺詐和非欺詐規(guī)則來找出違規(guī)的行為。這些方法往往受限于專家的知識水平。其次,雖然有許多文獻(xiàn)提出了各種不同的方法來解決欺詐問題,這些文獻(xiàn)中的監(jiān)督方法專注于將欺詐問題定義為一種二分類問題。醫(yī)保數(shù)據(jù)是一種分布很不均衡的數(shù)據(jù)集,其中包含大量的正常記錄以及較少量的欺詐記錄,這種偏斜的類分布性使得從大量正常數(shù)據(jù)中區(qū)分出極少量的欺詐數(shù)據(jù)比較困難。隨著時間的推移,醫(yī)保數(shù)據(jù)集也根據(jù)內(nèi)部或外部的因素動態(tài)變化,從而醫(yī)保欺詐檢測結(jié)果不是很理想。最后,監(jiān)督學(xué)習(xí)方法為了產(chǎn)生一個更準(zhǔn)確欺詐檢測結(jié)果,需要對訓(xùn)練數(shù)據(jù)中涉及的大量實體的屬性進(jìn)行分析。這項工作花費(fèi)了大量的精力和精力,甚者有些屬性違反了在醫(yī)療領(lǐng)域隱私政策。而基于聚類的離群檢測和聚類分析等無監(jiān)督方法由于輸入的參數(shù)較少,只需要了解少量的信息,所以獲得的結(jié)果的準(zhǔn)確性往往達(dá)不到欺詐檢測的要求。因此需要一種涉及較少量非隱私屬性、較高準(zhǔn)確度的醫(yī)保欺詐檢測方法。本文的具體工作和貢獻(xiàn)概括如下:1.提出了一個基于醫(yī)生信任度的醫(yī)保欺詐檢測方法GM-FP。這個方法通過醫(yī)生信任度這個關(guān)鍵特征將圖挖掘和頻繁模式挖掘結(jié)合起來,僅僅使用醫(yī)療記錄來訓(xùn)練一個關(guān)于某種疾病的合理治療模型(藥品和醫(yī)療設(shè)施的種類、數(shù)量及之間的關(guān)系),并基于未知記錄與合理模型的相似程度來判斷記錄是否存在欺詐。2.提出一種基于醫(yī)療記錄數(shù)據(jù)集內(nèi)部特征和網(wǎng)絡(luò)圖探索的異常檢測方法—IF-NE。對于每個醫(yī)保記錄,IF-NE通過分析該記錄的內(nèi)部特征和基于網(wǎng)絡(luò)的特征,并根據(jù)特征選擇合適的分類器來對正常記錄和異常記錄進(jìn)行分類,從而決定該醫(yī)保記錄是否是欺詐記錄。內(nèi)部特征是基于RMF(新進(jìn)度、頻率和花費(fèi)金額)來獲取的。基于網(wǎng)絡(luò)的特征提取豐富了醫(yī)生—病人二分圖網(wǎng)絡(luò)模型,將醫(yī)療記錄加入形成醫(yī)生—病人—醫(yī)保記錄三分圖模型;同時,利用了一種用于通過網(wǎng)絡(luò)從有限集合的標(biāo)記邊(即欺詐醫(yī)保記錄)推斷所有網(wǎng)絡(luò)組件(即醫(yī)生、病人和醫(yī)保記錄)的分?jǐn)?shù)的新算法來獲得基于網(wǎng)絡(luò)特征。最后,利用隨機(jī)森林基于數(shù)據(jù)特征對記錄進(jìn)行欺詐檢測,結(jié)果表明該方法比基準(zhǔn)方法效果更好。3.提出一種基于稀有標(biāo)簽傳播的欺詐檢測方法。該方法改進(jìn)了傳統(tǒng)的基于凸標(biāo)簽傳播的標(biāo)簽傳播方法,通過凸凹變換,將凸標(biāo)簽傳播算法轉(zhuǎn)變?yōu)橄∮袠?biāo)簽傳播的非凸標(biāo)簽傳播算法,從而解決了標(biāo)簽傳播算法在集監(jiān)督程度低、類不平衡性高的醫(yī)保數(shù)據(jù)集上性能降低的問題。
[Abstract]:In recent years, the health China gradually rising to a national strategy, the construction of medical insurance plays an important role in the economic and social development. With the popularization and promotion of medical information, medical insurance fraud is increasingly being recognized as a serious social problem. Medical abuse is a major fraud in Medicare fraud, the fraud mainly refers to the medical institutions or doctors to provide medicines or medical supplies and the actual treatment with inconsistent or contrary to medical standards, thereby increasing medical expenditure. Various medical insurance fraud cases are commonplace, and greatly damage the interests of the insured, caused significant damage to the health insurance fund safety seriously hinder the implementation and promotion of medical insurance policy. However, a problem of medical fraud are not recent, and all kinds of fraud detection method is proposed to solve this problem, But the medical fraud problem is still not solved very well. First of all, some of the traditional detection method based on the detection rules defined by expert fraud and non fraud rules to identify illegal behavior. These methods are often limited by the knowledge of the expert level. Secondly, although there are many literatures put forward various methods to solve the problem of fraud. These monitoring methods in the literature focus on the definition of fraud as a classification problem. Two Medicare data is an uneven distribution of the data set, which contains a large number of normal records and less fraud records, this class makes the distribution of deviation from a large number of normal data to distinguish very small amounts of data fraud difficult. With the passage of time, the health insurance data set according to the dynamic changes of internal and external factors, and medical insurance fraud detection result is not very ideal. At last, Supervised learning methods in order to produce a more accurate result of fraud detection, a large number of attribute entities involved in the training data were analyzed. This work has spent a lot of energy and energy, even some property in violation of privacy in the medical field. While the policy of clustering based outlier detection and clustering analysis method for unsupervised the input parameters are less, only need to know a small amount of information, so the accuracy of the results obtained are often not up to the fraud detection requirements. So we need a less involved non private property, insurance fraud detection method of high accuracy. The main work and contributions are summarized as follows: 1. a medical insurance fraud detection the doctor method based on trust degree by the method of GM-FP. doctors trust this key feature of graph mining and mining frequent patterns together, only the use of medical records Book to train a reasonable treatment of a disease model (the relationship between species, and the number of drugs and medical facilities, and the degree of similarity between) unknown record and reasonable model based on the record to judge the existence of fraud.2. proposed a medical record data set based on the internal characteristics and explore the network anomaly detection method IF-NE. for each medical record, IF-NE through the internal characteristic analysis of the record and based on the characteristics of the network, and according to the characteristics of choosing appropriate classifier to classify the normal and abnormal records records, so as to determine the medical insurance fraud records are recorded. The internal characteristics is based on the RMF (new schedule, frequency and amount spent) to get the network based feature extraction. The doctor - patient rich two networks, will join the doctor - patient medical records form - health records of three figure model; at the same time, The use of a mark used by network from a finite set of edges (i.e. health records fraud) concluded that all of the network components (i.e. doctors, patients and medical records) of the new algorithm to obtain scores based on network characteristics. Finally, using the random forest based on data characteristics on the record of fraud detection, the results show that the method is higher than the standard method better.3. presents a rare fraud detection method based on label propagation. This method improved label propagation method based on the traditional convex label propagation, through the convex concave convex transform, label propagation algorithm transformation of non convex label propagation algorithm for rare label propagation, thus solving the label propagation algorithm in the low level of supervision, problems the performance of the high class imbalance reduce Medicare data set.

【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R197.1;TP311.13

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張德蓮;;護(hù)理與醫(yī)療記錄的沖突諧調(diào)[J];全科護(hù)理;2011年19期

2 鹿內(nèi)清三 ,王群;醫(yī)療記錄的證據(jù)價值[J];國外醫(yī)學(xué)(醫(yī)院管理分冊);1992年01期

3 張文燕;;英國醫(yī)療記錄共享項目引爭議[J];中國醫(yī)院院長;2014年05期

4 Woods D.;Thomas E.;Holl J.;王一飛;;兒童中不良事件和可預(yù)防的不良事件[J];世界核心醫(yī)學(xué)期刊文摘(兒科學(xué)分冊);2006年Z1期

5 王娟;誰保護(hù)患者的權(quán)利?[J];國外醫(yī)學(xué)(醫(yī)院管理分冊);1990年04期

6 陳淑芬,楊小敏;全科醫(yī)學(xué)的醫(yī)療記錄模式——以問題為導(dǎo)向的醫(yī)療記錄[J];中國全科醫(yī)學(xué);2001年01期

7 陳淑芬,楊小敏;全科醫(yī)學(xué)的醫(yī)療記錄模式——以問題為導(dǎo)向的醫(yī)療記錄(續(xù)上期)[J];中國全科醫(yī)學(xué);2001年02期

8 林竟成;醫(yī)院發(fā)展概況[J];醫(yī)院管理;1984年01期

9 葉梅艷;使用“IMR”優(yōu)化護(hù)理工作的體會[J];護(hù)士進(jìn)修雜志;2002年02期

10 Lima M.A;Drislane F.W;Koralnik I.J;郭俊;;進(jìn)行性多灶性腦白質(zhì)病患者的癲癇發(fā)作及其預(yù)后[J];世界核心醫(yī)學(xué)期刊文摘(神經(jīng)病學(xué)分冊);2006年11期

相關(guān)會議論文 前2條

1 孫迎;葉英;;醫(yī)院管理信息系統(tǒng)的內(nèi)涵[A];中國生物醫(yī)學(xué)工程學(xué)會第六次會員代表大會暨學(xué)術(shù)會議論文摘要匯編[C];2004年

2 劉曉軍;;營養(yǎng)篩查和評價方法介紹及應(yīng)用[A];臨床營養(yǎng)師實踐技能培訓(xùn)班匯編[C];2012年

相關(guān)重要報紙文章 前6條

1 ;無線讓你更健康[N];網(wǎng)絡(luò)世界;2003年

2 徐丹　郭易楠;發(fā)布檢驗信息 查閱電子病歷[N];上海科技報;2009年

3 編譯 胡德良;醫(yī)療行業(yè)能和iPad一起走多遠(yuǎn)[N];醫(yī)藥經(jīng)濟(jì)報;2014年

4 張小明;都市健身涌新潮[N];人民政協(xié)報;2001年

5 黃夢/編譯;VAR積極參與IT技術(shù)推動醫(yī)療行業(yè)應(yīng)用發(fā)展　[N];電腦商報;2004年

6 ;HIPAA深刻影響醫(yī)療行業(yè)[N];計算機(jī)世界;2005年

相關(guān)碩士學(xué)位論文 前2條

1 齊珂;基于移動終端的醫(yī)療記錄遠(yuǎn)程訪問軟件設(shè)計[D];電子科技大學(xué);2015年

2 崔豪驛;基于圖挖掘的醫(yī)療濫用欺詐檢測分析[D];山東大學(xué);2017年

，

本文編號：1446557