本文選題：原發(fā)性卵巢功能不全 + 卵巢功能早衰��； 參考：《中國(guó)全科醫(yī)學(xué)》2017年27期

【摘要】：目的建立基于人工神經(jīng)網(wǎng)絡(luò)(ANN)的卵巢早衰(POF)預(yù)測(cè)模型——多層向前神經(jīng)網(wǎng)絡(luò)模型,以期提高POF臨床診斷總符合率。方法 2011年1—3月選取武漢市白玉山街所管轄的6個(gè)社區(qū)內(nèi)符合納入標(biāo)準(zhǔn)的婦女341例為研究對(duì)象。2011年5月—2016年6月,每隔4個(gè)月對(duì)研究對(duì)象進(jìn)行1次來(lái)院隨訪,隨訪至其40歲。隨訪過(guò)程中2例研究對(duì)象行子宮切除術(shù),2例服用性激素治療,失訪21例,均予以剔除,最終共納入316例研究對(duì)象。采用無(wú)偏隨機(jī)化分配法將316例研究對(duì)象分為訓(xùn)練樣本(177例)、檢驗(yàn)樣本(44例)和堅(jiān)持樣本(95例)。設(shè)置輸入?yún)?shù)為A型行為、腮腺炎病史、婦科手術(shù)史、使用促排卵藥物史、婚育史、卵泡刺激素(FSH)、FSH/黃體生成素(LH)、抗苗勒管激素(AMH)、抑制素B(INHB)、竇狀卵泡數(shù)(AFC)、收縮期峰流速(PSV)、阻力指數(shù)(RI);輸出參數(shù)為"是否發(fā)生POF"。通過(guò)訓(xùn)練樣本進(jìn)行模型構(gòu)建,檢驗(yàn)樣本對(duì)模型進(jìn)行校正,堅(jiān)持樣本對(duì)模型進(jìn)行穩(wěn)定性檢測(cè)。結(jié)果ANN經(jīng)過(guò)剔除"冗余"后,自動(dòng)構(gòu)建出輸入單元(12個(gè))、單隱層(6個(gè)節(jié)點(diǎn))和激活函數(shù)(hyperbolic tangent)、輸出單元(2個(gè))和激活函數(shù)(softmax)的模型。訓(xùn)練樣本的交叉熵誤差值為53.236,在預(yù)測(cè)誤差未減少時(shí)終止測(cè)試,訓(xùn)練時(shí)間為0.42 s。影響權(quán)重在前5位的輸入?yún)?shù)分別為AMH(26.3%)、INHB(24.1%)、AFC(21.7%)、A型行為(7.2%)、婦科手術(shù)史(6.5%)。多層向前神經(jīng)網(wǎng)絡(luò)模型預(yù)測(cè)訓(xùn)練樣本、檢驗(yàn)樣本、堅(jiān)持樣本發(fā)生POF的靈敏度分別為97.8%、91.7%和92.0%,特異度分別為92.4%、84.4%和80.0%,總符合率分別為93.8%、86.4%和83.2%。在訓(xùn)練樣本和檢驗(yàn)樣本的基礎(chǔ)上,得到多層向前神經(jīng)網(wǎng)絡(luò)模型預(yù)測(cè)POF的受試者工作特征曲線下面積(AUC)為0.972。結(jié)論基于ANN構(gòu)建的POF預(yù)測(cè)模型——多層向前神經(jīng)網(wǎng)絡(luò)模型具有較高臨床診斷總符合率,不僅為臨床高效診斷及優(yōu)化檢查提供理論基礎(chǔ)和方法支持,而且為實(shí)現(xiàn)早防早治提供機(jī)會(huì),值得臨床推廣。
[Abstract]:Objective to establish a multilayer forward neural network model for predicting premature ovarian failure (POF) based on artificial neural network (Ann) in order to improve the total diagnostic coincidence rate of POF. Methods from January to January 2011, 341 women who met the inclusion criteria were selected from 6 communities in Baayushan Street, Wuhan City. The subjects were followed up every 4 months from May 2011 to June 2016. They were followed up to 40 years old. During the follow-up, 2 cases were treated with sex hormone after hysterectomy, 21 cases were excluded, and 316 cases were included in the study. 316 cases were divided into training samples (177 cases), test samples (44 cases) and persistent samples (95 cases) by unbiased randomization method. The input parameters were: type A behavior, history of mumps, history of gynecological surgery, history of using ovulation promoting drugs, history of marriage and childbearing. Follicle stimulating hormone (FSH) / luteinizing hormone (LH), anti-mullerian hormone (AMH), inhibin (BINHBB), antral follicle number (POF), peak systolic velocity (PSV), resistance index (RI), and the output parameters were "whether POF occurred or not". The model is constructed by training samples, calibrated by test samples, and the stability of the model is detected by persisting samples. Results after eliminating "redundancy" in ANN, the models of input unit (12), single hidden layer (6 nodes) and activation function (hyperbolic tangent, output unit (2) and activation function) were automatically constructed. The cross-entropy error of the training sample is 53.236, and the test is terminated when the prediction error is not reduced, and the training time is 0.42 s. The input parameters in the first five positions of influence weight were AMH26.3 and INHB24.1, respectively. The AFCJ 21.7A behavior was 7.2cm, and the gynecologic operation history was 6.5cm. The sensitivity of POF was 91.7% and 92.0%, the specificity was 92.44.4% and 80.0%, respectively. The total coincidence rates were 93.864% and 83.2%, respectively. On the basis of training samples and test samples, a multilayer forward neural network model was obtained to predict the area under the operating characteristic curve of POF was 0.972. Conclusion the POF predictive model based on ANN, a multilayer forward neural network model, has a high total coincidence rate of clinical diagnosis, which not only provides theoretical basis and method support for clinical high efficiency diagnosis and optimization examination. And for early prevention and treatment to provide opportunities, worthy of clinical promotion.
【作者單位】： 武漢鋼鐵(集團(tuán))公司第二職工醫(yī)院婦產(chǎn)科;
【基金】：武漢市臨床醫(yī)學(xué)科研項(xiàng)目(WX15D15) 第四批武漢中青年醫(yī)學(xué)骨干人才資助項(xiàng)目
【分類(lèi)號(hào)】：R711.75;TP183

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 郭奕瑞;李玉倩;王高帥;劉曉田;張路寧;張紅艷;王炳源;王重建;;人工神經(jīng)網(wǎng)絡(luò)模型在2型糖尿病患病風(fēng)險(xiǎn)預(yù)測(cè)中的應(yīng)用[J];鄭州大學(xué)學(xué)報(bào)(醫(yī)學(xué)版);2014年02期

相關(guān)重要報(bào)紙文章 前1條

1 記者 周前進(jìn);人工神經(jīng)網(wǎng)絡(luò)可篩查糖尿病[N];健康報(bào);2000年

相關(guān)碩士學(xué)位論文 前1條

1 洪燁;基于機(jī)器學(xué)習(xí)算法的糖尿病預(yù)測(cè)模型研究[D];哈爾濱工業(yè)大學(xué);2016年

，

本文編號(hào)：1965341