本文選題：輸尿管結(jié)石 + 神經(jīng)網(wǎng)絡(luò)(計(jì)算機(jī))��； 參考：《中國全科醫(yī)學(xué)》2016年20期

【摘要】：目的運(yùn)用人工神經(jīng)網(wǎng)絡(luò)建立輸尿管結(jié)石自行排出的預(yù)測模型,并轉(zhuǎn)化成臨床應(yīng)用。方法選取2013年1—8月在石河子大學(xué)醫(yī)學(xué)院第一附屬醫(yī)院泌尿外科門診就診的輸尿管結(jié)石患者225例。經(jīng)保守排石治療4周后,復(fù)查泌尿系B超或CT判斷結(jié)石是否排出,并將患者分為排石組和未排石組。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),并對(duì)68例測試集樣本進(jìn)行預(yù)測。繪制預(yù)測擬概率的ROC曲線,并計(jì)算ROC曲線下面積評(píng)價(jià)預(yù)測效能。結(jié)果排石組141例,未排石組84例。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p H值、血尿、淋巴細(xì)胞計(jì)數(shù)比較,差異均無統(tǒng)計(jì)學(xué)意義(P0.05);兩組患者年齡、疼痛程度、結(jié)石直徑、結(jié)石位置、血白細(xì)胞計(jì)數(shù)、中性粒細(xì)胞計(jì)數(shù)、中性粒細(xì)胞分?jǐn)?shù)、淋巴細(xì)胞分?jǐn)?shù)、C反應(yīng)蛋白水平比較,差異均有統(tǒng)計(jì)學(xué)意義(P0.05)。運(yùn)行人工神經(jīng)網(wǎng)絡(luò),輸入層共建立9個(gè)神經(jīng)元。系統(tǒng)自動(dòng)體系構(gòu)建兩個(gè)隱含層,輸出層有1個(gè)神經(jīng)元。預(yù)測變量重要性前3位分別是:結(jié)石直徑(0.20)、C反應(yīng)蛋白(0.18)、年齡(0.12)。運(yùn)用建立成功的人工神經(jīng)網(wǎng)絡(luò)對(duì)68例測試集樣本進(jìn)行預(yù)測,結(jié)果顯示,測試集樣本的靈敏度、特異度和總準(zhǔn)確率分別為93.3%、60.9%和82.4%,ROC曲線下面積為0.868〔95%CI(0.774,0.962)〕。結(jié)論人工神經(jīng)網(wǎng)絡(luò)預(yù)測輸尿管結(jié)石能否排出有較高的準(zhǔn)確率,可輔助臨床醫(yī)師為患者制定安全、合理的治療方案。
[Abstract]:Objective to establish a prediction model of ureteral calculi excretion by artificial neural network (Ann) and transform it into clinical application. Methods 225 patients with ureteral calculi were selected from January to August 2013 in Urology Department of the first affiliated Hospital of Shihezi University Medical College. After 4 weeks of conservative lithotomy treatment, the patients were divided into two groups: lithotomy group and non-lithotomy group. Factors affecting stone excretion were screened by single factor analysis. Artificial neural network was established by using these factors as predictive parameters and 68 test samples were predicted. The ROC curve of the prediction quasi probability is drawn and the area under the ROC curve is calculated to evaluate the prediction efficiency. Results there were 141 cases in the lithotomy group and 84 cases in the non-lithotomy group. Univariate analysis showed that there were no significant differences in sex, BMI, bladder irritation, side, hydronephrosis, urine pH, hematuria and lymphocyte count between the two groups. There were significant differences in stone diameter, stone location, leukocyte count, neutrophil fraction, lymphocyte fraction and C-reactive protein level (P 0.05). An artificial neural network was run and nine neurons were established in the input layer. The system automatically constructs two hidden layers with one neuron in the output layer. The first three positions of predictive variable importance were: stone diameter 0.20 C reactive protein 0.18, age 0.12. A successful artificial neural network was used to predict 68 test samples. The results showed that the sensitivity, specificity and total accuracy of the test samples were 93.30.9% and 82.4%, respectively. The area under the ROC curve was 0.86895%. Conclusion artificial neural network can predict whether ureteral calculi can be excreted with high accuracy and can assist clinicians to make safe and reasonable treatment plan for patients with ureteral calculi.
【作者單位】： 石河子大學(xué)醫(yī)學(xué)院第一附屬醫(yī)院泌尿外科;
【基金】：國家科技支撐計(jì)劃子課題(2013BAI05B05) 新疆生產(chǎn)建設(shè)兵團(tuán)醫(yī)藥衛(wèi)生重點(diǎn)項(xiàng)目科技援疆專項(xiàng)(2014AB052)
【分類號(hào)】：R693.4

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 冉金生,臧美孚,崔書錦;經(jīng)輸尿管鏡氣壓彈道碎石治療輸尿管結(jié)石[J];北京醫(yī)學(xué);2001年02期

2 陸曙炎,周忠興,莫偉高,陳靜,陳建國,鄒建鋼,張煥興,吳小鵬,陳仰之,劉偉民,蘇彤,蔣曉東,高谷深;輸尿管結(jié)石治療方案的改進(jìn)[J];中華外科雜志;2001年01期

3 張?jiān)?“舒”、“利”“震”三法結(jié)合治療輸尿管結(jié)石的臨床觀察[J];中國鄉(xiāng)村醫(yī)藥;2001年04期

4 王建新,劉乃波,鮑鎮(zhèn)美;螺旋CT診斷輸尿管結(jié)石的應(yīng)用價(jià)值(附25例報(bào)告)[J];中華泌尿外科雜志;2002年06期

5 何銀志 ,馬雁斌;巨大輸尿管結(jié)石一例[J];貴州醫(yī)藥;2002年02期

6 胡石騰,陳華平,胡濤,湯加泉,劉楚芝,羅學(xué)軍,張新保;動(dòng)態(tài)靜脈尿路造影對(duì)輸尿管結(jié)石的診斷價(jià)值[J];南華大學(xué)學(xué)報(bào)(醫(yī)學(xué)版);2002年02期

7 羅玉萍,王學(xué)閩,陳海鳴;體外震波碎石治療輸尿管結(jié)石317例體會(huì)[J];江西醫(yī)學(xué)院學(xué)報(bào);2002年04期

8 武秀平,邢繼平;電腦多功能電療儀治療輸尿管結(jié)石絞痛18例療效觀察[J];中國自然醫(yī)學(xué)雜志;2002年03期

9 孫中義,江軍,王洛夫,姜慶,朱方強(qiáng),張克勤;螺旋CT對(duì)輸尿管結(jié)石診斷價(jià)值[J];臨床泌尿外科雜志;2003年12期

10 李斌,王安勇,杜勇,張戎;輸尿管結(jié)石致絞痛急診體外沖擊波碎石術(shù)的療效觀察[J];臨床泌尿外科雜志;2004年03期

相關(guān)會(huì)議論文 前10條

1 李立宇;;輸尿管結(jié)石并絞痛的急診處理[A];第十五屆全國泌尿外科學(xué)術(shù)會(huì)議論文集[C];2008年

2 印正國;李進(jìn);程庭利;趙文博;;體外震波碎石治療328例急診輸尿管結(jié)石療效分析[A];第七次中國中西醫(yī)結(jié)合泌尿外科學(xué)術(shù)年會(huì)暨第二次廣東省中西醫(yī)結(jié)合泌尿外科學(xué)術(shù)年會(huì)論文集[C];2009年

3 薛來平;高嵐;林恩平;李曉斌;;輸尿管結(jié)石的超聲檢查[A];慶祝中國超聲醫(yī)學(xué)工程學(xué)會(huì)成立20周年——第八屆全國超聲醫(yī)學(xué)學(xué)術(shù)會(huì)議論文匯編[C];2004年

4 熊維江;張英;衛(wèi)勤;胡輝瑩;;654-2、黃體酮、速尿聯(lián)合治療輸尿管結(jié)石療效觀察[A];《中華急診醫(yī)學(xué)雜志社》第三屆組稿會(huì)暨急診醫(yī)學(xué)學(xué)術(shù)研討會(huì)論文匯編[C];2004年

5 肖青;邵淑芹;柳曉明;袁紅英;郭振濤;李春龍;;輸尿管結(jié)石的內(nèi)科治療探索[A];中華醫(yī)學(xué)會(huì)腎臟病學(xué)分會(huì)2006年學(xué)術(shù)年會(huì)論文集[C];2006年

6 周攀;;中西醫(yī)結(jié)合治療輸尿管結(jié)石80例[A];中華醫(yī)學(xué)會(huì)第11屆全國內(nèi)科學(xué)術(shù)會(huì)議論文匯編[C];2007年

7 庹必燦;陳勁梅;楊嬡;;體外沖擊波碎石300例輸尿管結(jié)石體會(huì)[A];第二十一屆航天醫(yī)學(xué)年會(huì)暨第四屆航天護(hù)理年會(huì)論文匯編（上冊(cè)）[C];2005年

8 蔡運(yùn)林;譚光林;王安果;楊岳;;輸尿管結(jié)石發(fā)病相關(guān)因素分析[A];第十五屆全國泌尿外科學(xué)術(shù)會(huì)議論文集[C];2008年

9 陳楚紅;龔e，

本文編號(hào)：1980412