ICU急性低血壓預(yù)測方法研究
發(fā)布時間：2018-07-25 20:09
【摘要】：急性低血壓是重癥監(jiān)護室(Intensive Care Unit, ICU)病人經(jīng)常出現(xiàn)的突發(fā)急癥之一,如果不采取及時有效的干預(yù)措施會嚴重威脅病人的生命安全。由于目前ICU普遍面臨醫(yī)療資源緊張、人手嚴重短缺的問題,并且急性低血壓發(fā)作前缺少可以直接觀察到的征兆,醫(yī)護人員可能無法及時發(fā)現(xiàn)急性低血壓發(fā)作的病人,導(dǎo)致病人存活率下降。因此預(yù)測急性低血壓的發(fā)生或者甄選急性低血壓發(fā)作高風(fēng)險病人是ICU監(jiān)護迫切需要解決的臨床問題之一。利用ICU監(jiān)護產(chǎn)生的海量臨床數(shù)據(jù),借助計算機自動分析、挖掘這些臨床數(shù)據(jù)蘊含的急性低血壓發(fā)作特征模式,實現(xiàn)急性低血壓發(fā)作的智能預(yù)測,是解決這個問題的思路之一�；诖�,本文開展了以下研究工作： 1、研究了急性低血壓發(fā)作前后心率、動脈收縮壓、動脈舒張壓、動脈平均壓、脈搏、血氧多個生理參數(shù)的變化規(guī)律,采用相關(guān)性分析方法確定了預(yù)測急性低血壓發(fā)作的特征向量； 2、設(shè)計了基于LM算法的人工神經(jīng)網(wǎng)絡(luò)和多輸出切比雪夫神經(jīng)網(wǎng)絡(luò)兩種模型實現(xiàn)了急性低血壓發(fā)作的預(yù)測。并將兩種模型與經(jīng)典BP神經(jīng)網(wǎng)絡(luò)的性能指標進行對比分析； 3、根據(jù)脈搏波傳導(dǎo)時間與動脈血壓具有相關(guān)性的特點提出了基于脈搏波傳導(dǎo)時間的特征提取方法。分析了急性低血壓發(fā)作前后脈搏波傳導(dǎo)時間的統(tǒng)計特征和能量特征,采用相關(guān)性分析和主成份分析方法構(gòu)建了特征向量,并采用基于LM算法的神經(jīng)網(wǎng)絡(luò)實現(xiàn)急性低血壓發(fā)作的預(yù)測。 本文研究旨在研究基于ICU臨床監(jiān)護數(shù)據(jù)、模式識別和人工智能技術(shù)的急性低血壓發(fā)作預(yù)測方法,研究結(jié)果表明論文提出的方法取得較好的預(yù)測結(jié)果,可以為急性低血壓發(fā)作預(yù)測的臨床應(yīng)用提供理論參考。
[Abstract]:Acute hypotension is one of the emergent emergencies frequently occurring in (Intensive Care Unit, ICU) patients in intensive care unit (ICU). If no timely and effective intervention is taken, the life safety of patients will be seriously threatened. At present, ICU is generally faced with the problems of shortage of medical resources, severe shortage of manpower, and the lack of directly observed signs before acute hypotension, so health care workers may not be able to detect patients with acute hypotension in time. This leads to a decline in patient survival. Therefore, predicting the occurrence of acute hypotension or selecting patients at high risk of acute hypotension is one of the urgent clinical problems in ICU monitoring. It is one of the ways to solve this problem to mine the characteristic pattern of acute hypotension by using the massive clinical data generated by ICU monitoring and with the help of computer automatic analysis to realize the intelligent prediction of acute hypotension. Based on this, the following research work was carried out: 1. The changes of heart rate, arterial systolic pressure, arterial diastolic pressure, mean arterial pressure, pulse and blood oxygen were studied before and after acute hypotension. The characteristic vectors for predicting acute hypotension were determined by correlation analysis. 2. Two models of artificial neural network based on LM algorithm and multiple output Chebyshev neural network are designed to predict acute hypotension. The two models are compared with the classical BP neural network. 3. According to the correlation between pulse wave conduction time and arterial blood pressure, a feature extraction method based on pulse wave conduction time is proposed. The statistical and energy characteristics of pulse wave conduction time before and after acute hypotension were analyzed. The characteristic vectors were constructed by correlation analysis and principal component analysis. A neural network based on LM algorithm is used to predict acute hypotension. The purpose of this study is to study the prediction method of acute hypotension based on ICU clinical monitoring data, pattern recognition and artificial intelligence. The results show that the proposed method has good prediction results. It can provide theoretical reference for clinical application of predicting acute hypotension.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：R459.7;TP183
本文編號：2144939
[Abstract]:Acute hypotension is one of the emergent emergencies frequently occurring in (Intensive Care Unit, ICU) patients in intensive care unit (ICU). If no timely and effective intervention is taken, the life safety of patients will be seriously threatened. At present, ICU is generally faced with the problems of shortage of medical resources, severe shortage of manpower, and the lack of directly observed signs before acute hypotension, so health care workers may not be able to detect patients with acute hypotension in time. This leads to a decline in patient survival. Therefore, predicting the occurrence of acute hypotension or selecting patients at high risk of acute hypotension is one of the urgent clinical problems in ICU monitoring. It is one of the ways to solve this problem to mine the characteristic pattern of acute hypotension by using the massive clinical data generated by ICU monitoring and with the help of computer automatic analysis to realize the intelligent prediction of acute hypotension. Based on this, the following research work was carried out: 1. The changes of heart rate, arterial systolic pressure, arterial diastolic pressure, mean arterial pressure, pulse and blood oxygen were studied before and after acute hypotension. The characteristic vectors for predicting acute hypotension were determined by correlation analysis. 2. Two models of artificial neural network based on LM algorithm and multiple output Chebyshev neural network are designed to predict acute hypotension. The two models are compared with the classical BP neural network. 3. According to the correlation between pulse wave conduction time and arterial blood pressure, a feature extraction method based on pulse wave conduction time is proposed. The statistical and energy characteristics of pulse wave conduction time before and after acute hypotension were analyzed. The characteristic vectors were constructed by correlation analysis and principal component analysis. A neural network based on LM algorithm is used to predict acute hypotension. The purpose of this study is to study the prediction method of acute hypotension based on ICU clinical monitoring data, pattern recognition and artificial intelligence. The results show that the proposed method has good prediction results. It can provide theoretical reference for clinical application of predicting acute hypotension.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：R459.7;TP183
【參考文獻】
相關(guān)期刊論文 前10條
1 羅志昌，張松，，楊文鳴，楊子彬;脈搏波波形特征信息的研究[J];北京工業(yè)大學(xué)學(xué)報;1996年01期
2 王一飛;;21世紀的4P醫(yī)學(xué)與生殖健康[J];國際生殖健康/計劃生育雜志;2010年01期
3 李艷文,姜印平,鄭彤,閆宗魁;基于小波變換的脈搏波信號去噪[J];河北工業(yè)大學(xué)學(xué)報;2005年04期
4 焦學(xué)軍,房興業(yè);連續(xù)每搏血壓測量方法的研究進展[J];航天醫(yī)學(xué)與醫(yī)學(xué)工程;2000年02期
5 張雨濃,徐小文,毛宗源;Java語言與人工神經(jīng)網(wǎng)絡(luò)應(yīng)用[J];暨南大學(xué)學(xué)報(自然科學(xué)與醫(yī)學(xué)版);1998年01期
6 耿小慶;和金生;于寶琴;;幾種改進BP算法及其在應(yīng)用中的比較分析[J];計算機工程與應(yīng)用;2007年33期
7 蒲春;孫政順;趙世敏;;Matlab神經(jīng)網(wǎng)絡(luò)工具箱BP算法比較[J];計算機仿真;2006年05期
8 張雨濃;李巍;蔡炳煌;李克訥;;切比雪夫正交基神經(jīng)網(wǎng)絡(luò)的權(quán)值直接確定法[J];計算機仿真;2009年01期
9 蔡滿軍;程曉燕;喬剛;;一種改進BP網(wǎng)絡(luò)學(xué)習(xí)算法[J];計算機仿真;2009年07期
10 高雪鵬,叢爽;BP網(wǎng)絡(luò)改進算法的性能對比研究[J];控制與決策;2001年02期
本文編號：2144939
本文鏈接：http://www.sikaile.net/yixuelunwen/jjyx/2144939.html
最近更新
教材專著
