本文選題：集成學(xué)習(xí)　切入點：甲狀腺結(jié)節(jié)　出處：《東華大學(xué)》2017年碩士論文

【摘要】：甲狀腺疾病是內(nèi)分泌科中一類常見的疾病,主要表現(xiàn)為甲亢、甲減、甲狀腺炎、甲狀腺結(jié)節(jié)等。其中甲狀腺結(jié)節(jié)是對人體健康危害較為嚴重的一種,并且發(fā)病率有逐年上升的趨勢。甲狀腺結(jié)節(jié)患者在就診過程中留下了大量的電子病歷數(shù)據(jù),要想改善甲狀腺結(jié)節(jié)臨床診斷的現(xiàn)狀,需要我們高效、準確地挖掘出這些數(shù)據(jù)中隱含的信息。在傳統(tǒng)的甲狀腺結(jié)節(jié)臨床診斷過程中,醫(yī)生需要對患者進行超聲、血檢、細針穿刺等檢查,才能初步判斷患者的良惡性屬性,但即使這樣,診斷結(jié)果的準確率依然不盡人意。另一方面,傳統(tǒng)的機器學(xué)習(xí)算法在對真實醫(yī)療數(shù)據(jù)集進行模型訓(xùn)練及預(yù)測時,均體現(xiàn)出較高的誤差。究其原因,在于其沒有考慮到醫(yī)療數(shù)據(jù)集的特殊性——稀疏性和不平衡性,因此使結(jié)果產(chǎn)生較大的偏差。在此背景下,為了減少患者不必要的檢查流程,提高甲狀腺結(jié)節(jié)的鑒別準確率與效率,本文提出了一種基于超聲檢查特征的甲狀腺結(jié)節(jié)鑒別方法,并在已有集成學(xué)習(xí)的基礎(chǔ)模型上做出改進,建立了一個自定義的甲狀腺結(jié)節(jié)鑒別模型,最后設(shè)計并實現(xiàn)了一個基于超聲檢查數(shù)據(jù)的甲狀腺結(jié)節(jié)輔助鑒別系統(tǒng)。本文首先針對甲狀腺結(jié)節(jié)的臨床數(shù)據(jù)集,從患者基本信息、生化指標和臨床診斷等方面進行分析,研究指標之間以及臨床診斷之間的相互關(guān)系,為甲狀腺結(jié)節(jié)的臨床治療過程提供重要依據(jù)。然后對文本形式的甲狀腺超聲電子病理記錄進行結(jié)構(gòu)化處理,提取出有效的、結(jié)構(gòu)化的特征屬性,并對其進行平衡化、數(shù)值化等必要的預(yù)處理,轉(zhuǎn)化為機器學(xué)習(xí)分類算法所能識別的形式,方便實驗過程中的數(shù)據(jù)分析與建模。最后在已有集成學(xué)習(xí)的基礎(chǔ)模型上,通過在其目標函數(shù)中加入自定義項的方式做出適合醫(yī)療數(shù)據(jù)集的改進,構(gòu)建一個新的鑒別模型,有效解決由于數(shù)據(jù)集的稀疏性與不平衡性所造成的實驗結(jié)果的誤差,提高預(yù)測結(jié)果的準確性。同時建立一個基于超聲檢查數(shù)據(jù)的甲狀腺結(jié)節(jié)輔助鑒別系統(tǒng),患者和醫(yī)生通過輸入相應(yīng)的超聲檢查特征就能實時預(yù)測鑒別結(jié)果,實現(xiàn)甲狀腺結(jié)節(jié)的自動化鑒別功能,提高檢查的效率。為了驗證本文所提出鑒別方法的優(yōu)越性,實驗在真實醫(yī)療數(shù)據(jù)集和UCI標準數(shù)據(jù)集上分別對比了本算法與隨機森林、支持向量機、神經(jīng)網(wǎng)絡(luò)算法,結(jié)果表明該方法具有最高的準確率,分別達到92.43%和94%。
[Abstract]:Thyroid disease is a common disease in Endocrinology, which is characterized by hyperthyroidism, hypothyroidism, thyroiditis, thyroid nodule and so on.Thyroid nodule is one of the most serious health hazards, and the incidence of thyroid nodule is increasing year by year.Patients with thyroid nodules have left a large number of electronic medical records in the process of treatment. In order to improve the present situation of clinical diagnosis of thyroid nodules, we need to extract the hidden information from these data efficiently and accurately.In the traditional clinical diagnosis of thyroid nodule, doctors need ultrasound, blood examination, fine needle puncture and other examinations to preliminarily judge the benign and malignant properties of patients, but even so, the accuracy of diagnosis is still unsatisfactory.On the other hand, the traditional machine learning algorithms have higher errors in model training and prediction of real medical data sets.The reason is that it does not take into account the particularity of medical data set-sparsity and unbalance, so the result is deviated greatly.In this context, in order to reduce the unnecessary examination process and improve the accuracy and efficiency of thyroid nodule differentiation, this paper proposes a method based on ultrasonic features to distinguish thyroid nodules.Based on the existing integrated learning model, a self-defined thyroid nodule identification model is established. Finally, a thyroid nodule identification system based on ultrasonic data is designed and implemented.Based on the clinical data set of thyroid nodules, this paper analyzes the basic information, biochemical indicators and clinical diagnosis of thyroid nodules, and studies the relationship between the indicators and the clinical diagnosis.To provide an important basis for the clinical treatment of thyroid nodules.Then, the electronic pathological records of thyroid ultrasound in the form of text are processed structurally, and the effective and structured characteristic attributes are extracted, and the necessary preprocessing, such as balancing and numerical processing, is carried out.It can be transformed into a form that can be recognized by machine learning classification algorithm, which is convenient for data analysis and modeling in the process of experiment.Finally, based on the existing integrated learning model, a new discriminant model is constructed by adding a custom item to the objective function to improve the medical data set.The errors of experimental results caused by the sparsity and unbalance of data sets are solved effectively, and the accuracy of prediction results is improved.At the same time, a thyroid nodule identification system based on ultrasonic examination data is established. Patients and doctors can predict the results of thyroid nodules by input the corresponding ultrasonic features in real time, and realize the automatic identification function of thyroid nodules.Improve the efficiency of inspection.In order to verify the superiority of the method proposed in this paper, we compare the proposed algorithm with random forest, support vector machine and neural network algorithm on the real medical data set and UCI standard data set, respectively.The results show that this method has the highest accuracy, reaching 92.43% and 94% respectively.
【學(xué)位授予單位】：東華大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R581;TP311.52

【參考文獻】

相關(guān)期刊論文 前10條

1 陳德華;馮潔瑩;樂嘉錦;潘喬;;中文病理文本的結(jié)構(gòu)化處理方法研究[J];計算機科學(xué);2016年10期

2 鄒博偉;錢忠;陳站成;朱巧明;周國棟;;面向自然語言文本的否定性與不確定性信息抽取[J];軟件學(xué)報;2016年02期

3 Wang Longkang;Ren Tingxiang;Nie Baisheng;Chen Yang;Lv Changqing;Tang Haoyang;Zhang Jufeng;;Development of a spontaneous combustion TARPs system based on BP neural network[J];International Journal of Mining Science and Technology;2015年05期

4 李前程;孫麗娜;吳雙;隋國慶;王輝;;高頻超聲及彈性成像對甲狀腺結(jié)節(jié)性質(zhì)鑒別診斷的logistic回歸分析[J];中國地方病防治雜志;2015年04期

5 熊偉;龔勛;羅俊;李天瑞;;基于局部紋理特征的超聲甲狀腺結(jié)節(jié)良惡性識別[J];數(shù)據(jù)采集與處理;2015年01期

6 張振;周毅;杜守洪;羅雪瓊;梅甜;;醫(yī)療大數(shù)據(jù)及其面臨的機遇與挑戰(zhàn)[J];醫(yī)學(xué)信息學(xué)雜志;2014年06期

7 趙杰;祁永梅;;一種新的甲狀腺腫瘤超聲圖像特征提取算法[J];光電工程;2013年09期

8 吳偉成;周俊生;曲維光;;基于統(tǒng)計學(xué)習(xí)模型的句法分析方法綜述[J];中文信息學(xué)報;2013年03期

9 付忠良;;通用集成學(xué)習(xí)算法的構(gòu)造[J];計算機研究與發(fā)展;2013年04期

10 馮時;付永陳;陽鋒;王大玲;張一飛;;基于依存句法的博文情感傾向分析研究[J];計算機研究與發(fā)展;2012年11期

，

本文編號：1725108