發(fā)布時間：2018-03-29 08:45

  本文選題：輸尿管結(jié)石　切入點：神經(jīng)網(wǎng)絡(luò)　出處：《石河子大學(xué)》2017年碩士論文

【摘要】：目的輸尿管結(jié)石是泌尿外科常見疾病,保守藥物排石作為傳統(tǒng)的非侵入治療方案廣泛被患者所接受,但是目前尚無一種可靠的預(yù)測輸尿管結(jié)石自發(fā)排出的方法。為此,本研究擬運用人工神經(jīng)網(wǎng)絡(luò)技術(shù)建立輸尿管結(jié)石自發(fā)排出的預(yù)測模型,并轉(zhuǎn)化成臨床應(yīng)用。方法選取2013年1月至2013年8月間前來我院就診的225例輸尿管結(jié)石患者作為研究對象,所有患者須符合納入及排除標準。收集患者的臨床資料包括一般情況,實驗室檢查指標及影像學(xué)檢查資料。通過保守排石治療4周后復(fù)查泌尿系超聲或CT判斷結(jié)石是否排出,將所有患者分為結(jié)石排出組和未排出組。通過單因素分析篩選出影響結(jié)石排出的因素,將這些因素作為預(yù)測參數(shù)建立人工神經(jīng)網(wǎng)絡(luò)預(yù)測模型,并應(yīng)用該模型對測試集樣本進行預(yù)測。繪制預(yù)測擬概率的ROC曲線,并計算曲線下面積評價預(yù)測效能。為進一步評價該模型的泛化能力,再次隨機選取44例選擇保守排石治療的輸尿管結(jié)石患者,運用計算神經(jīng)網(wǎng)絡(luò)模型預(yù)測結(jié)石自排結(jié)局,再次評價該模型的預(yù)測效能。結(jié)果排石組141例,未排石組84例。通過單因素分析結(jié)果顯示兩組患者性別、體質(zhì)指數(shù)、膀胱刺激征、側(cè)別、腎盂積水、尿pH值、血尿、淋巴細胞計數(shù)比較,差異均無統(tǒng)計學(xué)意義(P0.05);兩組患者年齡、疼痛程度評分、血白細胞計數(shù)、中性粒細胞百分比、淋巴細胞百分比、中性粒細胞計數(shù)、C反應(yīng)蛋白值、結(jié)石大小及位置在排石組與未排石組間比較差異有統(tǒng)計學(xué)意義(P0.05)。系統(tǒng)將225例樣本按照7:3的的比例隨機分成訓(xùn)練集157例(70%)和測試集68例(30%)分別用于模型的建立及測試。運行人工神經(jīng)網(wǎng)絡(luò),輸入層共建立9個神經(jīng)元。系統(tǒng)自動體系構(gòu)建兩個隱含層,輸出層有1個神經(jīng)元。預(yù)測變量重要性位于前三位的是結(jié)石直徑(0.20)、C反應(yīng)蛋白值(0.18)及患者年齡(0.12),應(yīng)用該模型對68名測試集樣本進行預(yù)測,結(jié)果顯示測試集樣本的敏感度、特異度和總準確率分別為93.33%,60.87%和82.35%。ROC曲線下面積為0.868,[95%CI(0.774,0.962)]。對隨機選取的44名患者輸尿管結(jié)石自排結(jié)局進行了預(yù)測,根據(jù)隨訪結(jié)果,計算出人工神經(jīng)網(wǎng)絡(luò)模型預(yù)測的敏感度、特異度和總準確率為100.00%,64.29%和88.64%。結(jié)論人工神經(jīng)網(wǎng)絡(luò)模型能準確預(yù)測輸尿管結(jié)石能否排出,可輔助臨床醫(yī)師為患者制定安全、合理的治療方案。
[Abstract]:Objective Ureterolithiasis is a common disease in urology, conservative drug lithotomy is widely accepted by patients as a traditional non-invasive treatment, but there is no reliable method to predict the spontaneous discharge of ureteral calculi. In this study, artificial neural network (Ann) technique was used to establish a predictive model of spontaneous ureteral calculi excretion, which was transformed into clinical application. Methods 225 patients with ureteral calculi who came to our hospital from January 2013 to August 2013 were selected as the study objects. All patients should meet the criteria of inclusion and exclusion. The clinical data including general information, laboratory examination indexes and imaging examination data were collected. After 4 weeks of conservative lithotomy treatment, urinary tract ultrasound or CT was rechecked to determine whether or not the stones were excreted. All patients were divided into stone excretion group and non-excretion group. Factors affecting stone excretion were screened by single factor analysis, and these factors were used as predictive parameters to establish artificial neural network prediction model. The model is used to predict the sample of the test set, the ROC curve of the forecast quasi probability is drawn, and the area under the curve is calculated to evaluate the prediction efficiency. In order to further evaluate the generalization ability of the model, Forty-four patients with ureteral calculi who were treated with conservative lithotomy were randomly selected to predict the outcome of calculi self-drainage by using the computational neural network model and to evaluate the prediction effectiveness of the model again. The results of single factor analysis showed that there was no significant difference in sex, BMI, bladder irritation, side, hydronephrosis, urine pH value, hematuria and lymphocyte count between the two groups (P 0.05). Pain score, white blood cell count, neutrophil percentage, lymphocyte percentage, neutrophil count and C-reactive protein, The difference of stone size and location between the two groups was statistically significant (P 0.05). 225 samples were randomly divided into training set (157 cases) and test set (68 cases) to set up the model according to the proportion of 7:3. Try. Run the artificial neural network, Nine neurons were created in the input layer, and two hidden layers were constructed by the automatic system. There was one neuron in the output layer. The prediction variables in the first three places were stone diameter 0.20 C reactive protein (0.18) and patient age 0.12. The model was used to predict 68 test set samples, and the results showed the sensitivity of the test set samples. The specificity and the total accuracy were 93.330.87% and 0.868 under the 82.35%.ROC curve, respectively. The self-discharging outcome of 44 patients with ureteral calculi selected randomly was predicted. The sensitivity of artificial neural network model was calculated according to the follow-up results. Conclusion the artificial neural network model can accurately predict whether ureteral calculi can be excreted, and can assist clinicians to formulate safe and reasonable treatment schemes for patients with ureteral calculi. The specificity and total accuracy are 100.00,64.29% and 88.64.Conclusion the artificial neural network model can accurately predict whether ureteral stones can be discharged.
【學(xué)位授予單位】：石河子大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R693.4

【參考文獻】

相關(guān)期刊論文 前10條

1 沈悅凡;李輝;鐘歡;陳煜;王榮江;王偉高;;輸尿管結(jié)石患者腎積水程度的影響因素分析[J];浙江臨床醫(yī)學(xué);2016年09期

2 曾凱;李應(yīng)龍;錢彪;倪釗;王新敏;李強;王文曉;王勤章;;糖尿病對輸尿管結(jié)石患者自發(fā)排石的影響[J];現(xiàn)代泌尿外科雜志;2016年05期

3 邱志磊;徐立柱;賈魁;梁鑫;胡偉;鄭帥帥;;前列腺癌人工神經(jīng)網(wǎng)絡(luò)診斷模型的應(yīng)用研究[J];臨床泌尿外科雜志;2015年10期

4 屈健;劉衛(wèi)洪;王江平;丁國富;王勤章;;血白細胞與C反應(yīng)蛋白及疼痛分級對輸尿管結(jié)石自排的影響研究[J];中國全科醫(yī)學(xué);2014年32期

5 臧桐;孫鳳嶺;楊同君;廖秀梅;高峰;;輸尿管下段結(jié)石1235例診治分析[J];臨床軍醫(yī)雜志;2014年08期

6 張鵬;吳們;張輝見;陳壯飛;鄭少斌;劉成山;;應(yīng)用人工神經(jīng)網(wǎng)絡(luò)預(yù)測ESWL單次治療腎結(jié)石的成功率[J];臨床泌尿外科雜志;2012年11期

7 劉綠;梁慶模;;人工神經(jīng)網(wǎng)絡(luò)在乳腺癌影像診斷中的應(yīng)用[J];山東醫(yī)藥;2012年37期

8 張小馬;方軍;龔強;;輸尿管鏡術(shù)后24h內(nèi)疼痛的量化分析與處理[J];中國內(nèi)鏡雜志;2012年02期

9 毛健;趙紅東;姚婧婧;;人工神經(jīng)網(wǎng)絡(luò)的發(fā)展及應(yīng)用[J];電子設(shè)計工程;2011年24期

10 李文峰;潘惟昕;厲建;陸超;顧豫飛;顧欣;;腎絞痛后輸尿管結(jié)石自行排出的預(yù)測性研究[J];臨床泌尿外科雜志;2011年11期

相關(guān)博士學(xué)位論文 前1條

1 鄧偉;BP神經(jīng)網(wǎng)絡(luò)構(gòu)建與優(yōu)化的研究及其在醫(yī)學(xué)統(tǒng)計中的應(yīng)用[D];復(fù)旦大學(xué);2002年

相關(guān)碩士學(xué)位論文 前1條

1 屈健;腎絞痛后輸尿管結(jié)石自排患者臨床特點研究[D];石河子大學(xué);2014年

，

本文編號：1680394