CN1477581A - Predictive modelling method application to computer-aided medical diagnosis - Google Patents

Predictive modelling method application to computer-aided medical diagnosis Download PDF

Info

Publication number
CN1477581A
CN1477581A CN 03132141 CN03132141A CN1477581A CN 1477581 A CN1477581 A CN 1477581A CN 03132141 CN03132141 CN 03132141 CN 03132141 A CN03132141 A CN 03132141A CN 1477581 A CN1477581 A CN 1477581A
Authority
CN
Grant status
Application
Patent type
Prior art keywords
prediction
method
model
medical
symptom
Prior art date
Application number
CN 03132141
Other languages
Chinese (zh)
Other versions
CN1234092C (en )
Inventor
周志华
Original Assignee
南京大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Abstract

The present invention discloses a prediction model-building method for computer-aided medical diagnosis. It utilizes the medical symptom detection equipment to obtain the symptom of object to be diagnosed to form symptomatic vector, then utilizes the prediction model to make treatment so as to can obtain prediction result. It also provides its concrete steps for implementing said invented prediction model-building method.

Description

一种适用于计算机辅助医疗诊断的预测建模方法 Suitable for computer-aided medical diagnosis predictive modeling methods

一、技术领域本发明涉及一种计算机辅助医疗诊断装置,特别涉及一种利用神经网络集成技术和规则学习技术的高精度、高可理解性预测建模方法。 I. Technical Field The present invention relates to a computer-aided medical diagnosis, and particularly to high precision, high intelligibility prediction modeling method using neural networks and rule learning integration technology techniques.

二、背景技术 Second, the technical background

随着计算机技术的发展,计算机辅助医疗诊断装置由于不受疲劳、情绪等因素的影响,已成为重要的辅助诊断手段。 With the development of computer technology, computer-aided medical diagnostic device due to the impact from fatigue, mood and other factors, it has become an important means of diagnosis. 计算机辅助医疗诊断装置通常是利用一些预测建模方法对历史病例进行分析,从而建立预测模型,然后再用该预测模型来对新病例进行诊断,其结果提交给医学专家进行进一步的分析确诊,从而在一定程度上减轻医学专家的工作负担。 Computer-aided medical diagnostic devices usually use some predictive modeling of historical cases were analyzed to build predictive models, and then use the predictive model to diagnose new cases, and the results submitted for further analysis to diagnose medical experts, in order to reduce the workload of medical experts to some extent. 因此,预测建模方法是计算机辅助医疗诊断装置的关键。 Therefore, predictive modeling method is the key computer-aided medical diagnostic device. 一方面,由于医疗诊断务求精确,因此适用的预测建模方法必须具有很高的精度;另一方面,由于医疗诊断事关被诊者的身体健康和生命安全,因此适用的预测建模方法必须具有很高的可理解性,即在作出诊断结论之后还需要能提供对诊断的解释,这不仅是被诊者及其家属的需要,还是医学专家检查诊断过程的需要。 On the one hand, due to the precise medical diagnosis of a view, therefore applicable predictive modeling method must have a high accuracy; on the other hand, due to the medical diagnosis is related to the health and safety of those attending, and therefore must apply predictive modeling methods with high intelligibility, that diagnosis is made after the conclusion also need to be able to provide an explanation of the diagnosis, which is not only the patient who needs and their families, still need to check the diagnosis of medical experts. 然而,现有技术如神经网络等虽然具有高精度,但不具有高可理解性;而规则学习等虽然具有高可理解性,但却不具有高精度,这就对计算机辅助医疗诊断装置的性能造成了不利影响。 However, the prior art such as neural networks and the like, while having high accuracy, but does not have high intelligibility; learning rule and, while having a high intelligibility, but do not have high precision, the performance of this computer-aided medical diagnosis apparatus It had a negative impact.

三、发明内容 III. SUMMARY OF THE INVENTION

本发明的目的是针对现有技术难以产生适用于计算机辅助医疗诊断装置的高精度、高可理解性预测模型的问题,提供一种高精度、高可理解性的预测建模方法,以辅助提高计算机辅助医疗诊断装置的性能。 Object of the present invention is suitable for computer aided difficult problem medical diagnostic apparatus precision, high intelligibility prediction model for the prior art, provides a high precision, high intelligibility prediction methods to assist in improving Computer-aided medical diagnostic device performance.

为实现本发明所述目的,本发明提供一种利用机器学习中的神经网络集成技术和规则学习技术进行预测建模的方法,该方法包括以下步骤:(1)若预测模型未训练好,则执行步骤2,否则转到步骤6;(2)利用历史病例产生初始训练数据集;(3)利用初始训练数据集训练出一个神经网络集成;(4)利用神经网络集成对初始训练数据集进行处理以产生规则训练数据集;(5)利用规则学习技术从规则训练数据集中产生规则模型;(6)利用规则模型进行预测并给出结果及解释;(7)结束。 In order to achieve the object of the present invention, the present invention provides a method for predictive modeling of machine learning in neural networks and rule learning integration technology techniques, the method comprising the steps of: (1) If the prediction is not good training model, the step 2, otherwise, go to step 6; (2) generating an initial set of training data using historical cases; (3) with the initial set of training data to train a neural network ensemble; (4) integrated using a neural network training data set initial processed training data set generation rule; (5) rule learning using techniques rule rule model from the training data set; (6) using a reference model to predict results and interpretation given; (7) ends.

本发明的优点是为计算机辅助医疗诊断装置提供了一种高精度、高可理解性的预测建模方法,以辅助提高计算机辅助医疗诊断装置的性能。 Advantage of the invention is to provide a high-precision computer-aided medical diagnosis apparatus, high intelligibility prediction methods to improve the performance of computer-assisted medical diagnostic aid device.

下面将结合附图对最佳实施例进行详细说明。 Following with reference to the preferred embodiments described in detail.

四、附图说明 IV BRIEF DESCRIPTION

图1是计算机辅助医疗诊断装置的工作流程图。 FIG 1 is a flowchart of a computer-aided medical diagnosis apparatus.

图2是本发明方法的流程图。 FIG 2 is a flowchart of a method of the present invention.

图3是用神经网络集成产生规则训练数据集的流程图。 FIG 3 is a flowchart of the rule sets of training data generated by the neural network ensemble.

五、具体实施方式 V. DETAILED DESCRIPTION

如图1所示,计算机辅助医疗诊断装置利用医学症状检测设备例如体温、血压测量设备等获取待诊对象的症状例如体温、血压等,然后将症状进行量化以得到症状向量,例如[t1,t2,…,tn],其中t1表示第一个症状值,t2表示第二个症状值,依此类推。 1, using a computer-aided medical diagnosis apparatus acquires medical condition detecting apparatus e.g. temperature, blood pressure measurement device and other symptoms to be diagnosed, for example, an object body temperature, blood pressure, and the symptoms to obtain a quantized vector symptoms, e.g. [t1, t2 , ..., TN], where t1 represents the first symptom value, t2 represents the second value symptoms, and so on. 症状向量交给预测模型处理,即可得到预测结果及解释的数字化表示形式,经过文字化处理后,就产生了最后提交给用户的诊断结论及解释。 Symptoms vector prediction model to deal with, you can get the predicted results and interpretation of digital representation, after word processing, produces a diagnostic conclusion and interpretation of the final submission to the user.

本发明的方法如图2所示。 The method of the present invention shown in FIG. 步骤10是初始动作。 Step 10 is the initial operation. 步骤11判断预测模型是否已经训练好,若已训练好则可处理诊断任务,执行步骤16;否则需进行训练,执行步骤12。 Step 11 determines whether the prediction model has been training well, you can deal with good training Ruoyi diagnostic tasks, perform step 16; otherwise, the need for training, step 12. 步骤12利用历史病例产生初始训练数据集,为叙述方便,称初始训练数据集为L0。 Step 12 uses historical cases to generate the initial training data set for narrative convenience, said the initial training data set to L0. L0中包含了每一历史病例所对应的症状向量及其类别,即诊断出的具体疾病类别(“没有疾病”也作为一种类别)。 L0 vector contains the history of symptoms and each category corresponding to the cases, i.e., diagnosis of the particular disease category ( "no disease" also as a category). 步骤13利用统计学中常用的可重复取样技术从L0中产生N个数据集,并用这N个数据集中的每一个训练出一个神经网络,这些神经网络就组成了神经网络集成。 Step 13 using a commonly used statistical sampling techniques may be repeated N data sets from L0, the concentration and the N data with each of a trained neural network, the neural network on the formation of neural network ensembles. N是一个用户预设的整数值例如9,它确定了神经网络集成所包含的神经网络个数。 N is a predetermined integer value, for example, the user 9, the neural network that determines the number of neural network ensemble included. 这里使用的神经网络可以是任何类型的神经网络,只要可以执行预测任务即可,例如可以使用神经网络教科书中介绍的多层前馈BP网络。 As used herein, the neural network can be any type of neural network, as long as you can perform the task can be predicted, for example, can be used in the textbooks multilayer neural network BP network before introduction of the feed. 步骤14利用神经网络集成产生用于建立规则模型的规则训练数据集L1,该步骤将在后面的部分结合图3进行具体介绍。 Integration step 14 using a neural network training data set generation rule to create a rule for L1 model, in conjunction with the step of FIG. 3 in the following section will be specifically described.

图2的步骤15利用L1训练出规则模型。 Step 15 of FIG. 2 L1 trained using rule model. 规则模型是一个由很多条IF-Then或类似形式的规则组成的预测模型,它由某种规则学习方法从某个训练数据集(这里就是L1)中训练出来。 Rule model is a predictive model of many items IF-Then rules or similar type of composition, which consists of a certain rule learning from training data set (this is L1) is trained. 这里可以使用任何类型的规则学习方法,只要其产生的模型可以执行预测任务即可,例如可以使用机器学习教科书中介绍的RIPPER、C4.5 Rule等。 Here you can use any type of rule learning method, which produces a model as long as the prediction task can be performed, for example, can be used RIPPER machine learning textbooks introduced, C4.5 Rule and so on. 步骤16接收待诊断的症状向量。 Step 16 receives symptom vector to be diagnosed. 步骤17将症状向量提交给训练好的规则模型进行预测。 Step 17 will be submitted to predict symptom vector to the trained model rules. 步骤18给出规则模型产生的预测结果及预测过程中使用的规则,这些规则就组成了对该预测结果的解释。 Rule used during the prediction results and the prediction model generation rule given in step 18, which make up the rules for the interpretation of the results of the prediction. 步骤19是结束状态。 Step 19 is the end state.

由于本发明的方法建立的预测模型是规则模型,因此其具有高理解性;又由于该方法利用了具有高精度的神经网络集成来产生建立规则模型的训练数据集,这可以视为对初始数据集进行了去噪、增强等良性处理,因此建立的规则模型也具有高精度。 Since the method of the present invention, the prediction model is established rule model, and therefore it has high comprehension; and because the method utilizes a neural network to produce an integrated high precision training data set to create a rule model, which can be regarded as initial data sets denoising, enhancement benign process, so rule model also has high precision.

图3详细说明了图2的步骤14,其作用是利用神经网络集成来产生用于建立规则模型的规则训练数据集L1。 Figure 3 illustrates in detail step 14 of FIG. 2, which role is to use rules to generate the neural network ensemble training data set to create a rule for L1 model. 图3的步骤140是起始状态。 Step 140 of FIG. 3 is the initial state. 步骤141将L1置为空集。 Step 141, L1 is set to the empty set. 步骤142从图2的步骤12产生的初始训练数据集L0中获取一个症状向量及其类别。 The initial step of training data sets from L0 generated in step 142 of FIG. 12 and the vector obtained by a symptom categories. 步骤143为每个类别分别设置一个计数器,这些计数器用来记录有多少个神经网络给出的预测结果是该类别,这里的各类别分别对应了诊断出的具体疾病类别(“没有疾病”也作为一种类别)。 Step 143 for each category are provided a counter, the counter is used to record with a number of neural network predictor is given in this category, where each category corresponding to diagnose the particular disease category ( "no disease" also as one category). 步骤144将所有计数器清零。 Step 144 clears all counters. 步骤145将控制参数k置为1,k是一个大于等于1但小于等于图2中步骤13的N的一个整数值,它用来指示当前考察的神经网络的序号。 Step 145 of the control parameter k is set to 1, k is an integer value of N is not less than 13 to 1 but less than or equal FIG Step 2, which is used to indicate the number of the current investigation neural network. 步骤146取得神经网络集成中第k个神经网络对待诊症状向量给出的预测结果,为叙述方便,称该结果为Fk。 Neural network ensemble step 146 acquired in the k-th neural network diagnosis treat symptoms vector prediction result given for convenience of description, the result is called Fk. 步骤147将Fk所对应的类别的计数器加一。 Step 147 Fk corresponding to a category counter is incremented. 步骤148将k加一。 A step 148 increments k. 步骤149判断k是否小于等于神经网络集成中神经网络的个数,即图2中步骤13的N,如果是则表明还有其他神经网络尚未考察,转到步骤146;否则就执行步骤150。 Step 149 determines whether k is less than equal to the number of neural network ensemble of neural networks, N 13 step 2 in FIG i.e., indicates if there are other neural network has not been investigated, go to step 146; otherwise, step 150 is executed.

图3的步骤150对所有计数器中的值进行比较,找出值最大的计数器,并将其对应的类别作为当前症状向量的新类别;如果有多个计数器中的值均为最大值,则以这些计数器对应的类别中出现机会最大的疾病种类作为当前症状向量的新类别。 Step 150 of FIG. 3 for comparison values ​​of all counters, find the maximum value of the counter, and as a new class of symptoms of the current vector corresponding category; if there are values ​​of the maximum value of the plurality of counters, places the best chance of the emergence of these types of diseases counters corresponding category as the current vector of a new category of symptoms. 步骤151将当前症状向量及其新类别加入L1。 Symptoms step 151 the current vector and new categories added L1. 步骤152判断L0中是否还有未考察的症状向量,如果有则转到步骤142;否则就进入步骤153,即图3的结束状态。 Step 152 determines whether or not there L0 vector examine symptoms, if there is go to step 142; otherwise, proceeds to step 153, i.e., the end of state 3 of FIG.

Claims (2)

  1. 1.一种适用于计算机辅助医疗诊断的预测建模方法,包括通过医学症状检测设备获取待诊对象的症状,然后将症状进行量化得到症状向量[t1,t2,…,tn],其中tn表示第n个症状值,症状向量交给预测模型处理,即可得到预测结果及解释的数字化表示形式,其特征是该方法包括以下步骤:(1)若预测模型未训练好,则执行步骤(2),否则转到步骤(6);(2)利用历史病例产生初始训练数据集;(3)利用初始训练数据集训练出一个神经网络集成;(4)利用神经网络集成对初始训练数据集进行处理以产生规则训练数据集;(5)利用规则学习技术从规则训练数据集中产生规则模型;(6)利用规则模型进行预测并给出结果及解释;(7)结束。 A suitable computer-aided medical diagnosis predictive modeling method, comprising detecting apparatus acquired by the medical condition of the object to be patient symptoms, the symptoms and symptoms resulting quantized vectors [t1, t2, ..., tn], where tn represents n-th syndromes, symptoms prediction vector to the process model can be obtained prediction results and interpretation of digital representation, characterized in that the method comprises the steps of: (1) If the prediction model is not well trained, step (2 ), otherwise, to step (6); (2) generating an initial set of training data using historical cases; (3) with the initial set of training data to train a neural network ensemble; (4) integrated using a neural network training data set initial processed training data set generation rule; (5) rule learning using techniques rule rule model from the training data set; (6) using a reference model to predict results and interpretation given; (7) ends.
  2. 2.根据权利要求1所述的适用于计算机辅助医疗诊断的预测建模方法,其特征是:在(4)中,利用神经网络集成产生用于建立规则模型的规则训练数据集L1的步骤是:(1)将L1置为空集;(2)从初始训练数据集L0中获取一个症状向量及其类别;(3)为每个类别分别设置一个计数器,用来记录神经网络给出的同类别预测结果的数目;(4)将所有计数器清零;(5)将控制参数k置为1,k是一个大于等于1但小于等于神经网络集成中神经网络的个数N;(6)取得神经网络集成中第k个神经网络对待诊症状向量给出的预测结果Fk;(7)将Fk所对应的类别的计数器加1;(8)将k加1;(9)判断k是否小于等于神经网络集成中神经网络的个数N,如果是则表明还有其他神经网络尚未考察,转到步骤(6);否则执行步骤(10);(10)对所有计数器中的值进行比较,找出值最大的计数器,并将其对应的类别作为 According to claim 1, applicable to the prediction methods of computer-assisted medical diagnosis, characterized in that: in (4), the neural network to produce an integrated L1 of step rule training dataset is used to build the model rule : (1) L1 is set to the empty set; (2) obtaining a vector from the initial symptoms and categories in the training data set L0; (3) for each class are provided a counter to record the same neural network analysis the number of class prediction results; and (4) all the counter is cleared; (5) the control parameter k is set to 1, k is greater than or equal to 1 but less than equal to the number N of the neural network integrated neural network; (6) to obtain neural network ensemble prediction result k-th vector of the neural network analysis to treat symptoms diagnosed Fk; (. 7), Fk is the corresponding category counter is incremented; (8) k is incremented by 1; if (9) is determined less than or equal k the number of neural network integrated in a neural network N, it indicates if there are other neural network has not been investigated, go to step (6); if not, step (10); (10) compares the values ​​of all counters, to find the maximum value of the counter, and a corresponding category 前症状向量的新类别;如果有多个计数器中的值均为最大值,则以这些计数器对应的类别中出现机会最大的疾病种类作为当前症状向量的新类别;(11)将当前症状向量及其新类别加入L1;(12)判断L0中是否还有未考察的症状向量,如果有则转到步骤(2);否则进入步骤(13);(13)结束。 New category presymptomatic vector; if the value of the plurality of counters are maximum value, the maximum chance of occurrence of these types of diseases counters places corresponding category as a new category of the current vector symptoms; (11) the current vector and symptoms new category which was added L1; (12) determines whether or not there L0 vector examine symptoms, if there is go to step (2); otherwise, proceed to step (13); (13) ends.
CN 03132141 2003-07-01 2003-07-01 Predictive modelling method application to computer-aided medical diagnosis CN1234092C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 03132141 CN1234092C (en) 2003-07-01 2003-07-01 Predictive modelling method application to computer-aided medical diagnosis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 03132141 CN1234092C (en) 2003-07-01 2003-07-01 Predictive modelling method application to computer-aided medical diagnosis

Publications (2)

Publication Number Publication Date
CN1477581A true true CN1477581A (en) 2004-02-25
CN1234092C CN1234092C (en) 2005-12-28

Family

ID=34154002

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 03132141 CN1234092C (en) 2003-07-01 2003-07-01 Predictive modelling method application to computer-aided medical diagnosis

Country Status (1)

Country Link
CN (1) CN1234092C (en)

Cited By (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100589754C (en) 2006-07-14 2010-02-17 深圳迈瑞生物医疗电子股份有限公司 Electrocardiogram computer-aided diagnosis system
US7769600B2 (en) 1997-03-13 2010-08-03 Clinical Decision Support Disease management system and method
US7780595B2 (en) 2003-05-15 2010-08-24 Clinical Decision Support, Llc Panel diagnostic method and system
US8015138B2 (en) 1993-12-29 2011-09-06 Clinical Decision Support, Llc Computerized medical self-diagnostic and treatment advice system
US8019582B2 (en) 2000-02-14 2011-09-13 Clinical Decision Support, Llc Automated diagnostic system and method
USRE43433E1 (en) 1993-12-29 2012-05-29 Clinical Decision Support, Llc Computerized medical diagnostic and treatment advice system
US8337409B2 (en) 1993-12-29 2012-12-25 Clinical Decision Support Llc Computerized medical diagnostic system utilizing list-based processing
US9005119B2 (en) 1993-12-29 2015-04-14 Clinical Decision Support, Llc Computerized medical diagnostic and treatment advice system including network access
US9081879B2 (en) 2004-10-22 2015-07-14 Clinical Decision Support, Llc Matrix interface for medical diagnostic and treatment advice system and method
CN106202986A (en) * 2016-09-28 2016-12-07 湖南老码信息科技有限责任公司 Amygdalitis prediction method based on incremental neural network model and prediction system
CN106250712A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Ureteral calculus prediction method and prediction system based on incremental neural network model
CN106250715A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Chronic pharyngolaryngitis prediction method and prediction system based on incremental neural network model
CN106250713A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Vesical calculus prediction method and prediction system based on incremental neural network model
CN106250716A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Method and system for neurodermatitis prediction based on incremental type neural network model
CN106339606A (en) * 2016-09-28 2017-01-18 湖南老码信息科技有限责任公司 Alcohol liver prediction method based on incremental nerve network model and alcohol liver prediction system based on incremental nerve network model
CN106339607A (en) * 2016-09-28 2017-01-18 湖南老码信息科技有限责任公司 Rheumatism prediction method and rheumatism prediction system based on incremental nerve network model
CN106339605A (en) * 2016-09-28 2017-01-18 湖南老码信息科技有限责任公司 Colonitis prediction method and colonitis prediction system based on incremental nerve network model
CN106384007A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based hemorrhoids prediction method and prediction system
CN106384013A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based type-II diabetes prediction method and prediction system
CN106384005A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based depression prediction method and prediction system
CN106384008A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based allergic rhinitis prediction method and prediction system
CN106384006A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based hepatitis C prediction method and prediction system
CN106407699A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Coronary heart disease prediction method and prediction system based on incremental neural network model
CN106407693A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Hepatitis B prediction method and prediction system based on incremental neural network model
CN106407694A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Neurasthenia prediction method and prediction system based on incremental neural network model
CN106407696A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Prickly heat prediction method and prediction system based on incremental neural network model
CN106407698A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Vegetative nervous disorder prediction method and prediction system based on incremental neural network model
CN106407700A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Hyperthyroidism prediction method and prediction system based on incremental neural network model
CN106407695A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Anxiety disorder prediction method and prediction system based on incremental neural network model
CN106446553A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Stomach illness prediction method and prediction system based on incremental neural network model
CN106446556A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for epifolliculitis based on incremental type neural network model
CN106446561A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Incremental neural network model based urticaria prediction method and system
CN106446559A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for viral dermatitis based on incremental type neural network model
CN106446549A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for dyspepsia based on incremental type neural network model
CN106446554A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Seborrheic dermatitis prediction method and prediction system based on incremental neural network model
CN106446563A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Incremental neural network model based constipation prediction method and system
CN106446557A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for hepatitis A based on incremental type neural network model
CN106446558A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Diabetes insipidus prediction method based on incremental neural network model and prediction system
CN106446550A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Cold prediction method and system based on incremental neutral network model
CN106446562A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Gastric concretion prediction method and prediction system based on incremental neural network model
CN106485065A (en) * 2016-09-28 2017-03-08 湖南老码信息科技有限责任公司 Chronic bronchitis prediction method and prediction system based on incremental neural network model

Cited By (56)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
USRE43433E1 (en) 1993-12-29 2012-05-29 Clinical Decision Support, Llc Computerized medical diagnostic and treatment advice system
US8337409B2 (en) 1993-12-29 2012-12-25 Clinical Decision Support Llc Computerized medical diagnostic system utilizing list-based processing
US9005119B2 (en) 1993-12-29 2015-04-14 Clinical Decision Support, Llc Computerized medical diagnostic and treatment advice system including network access
USRE43548E1 (en) 1993-12-29 2012-07-24 Clinical Decision Support, Llc Computerized medical diagnostic and treatment advice system
US8015138B2 (en) 1993-12-29 2011-09-06 Clinical Decision Support, Llc Computerized medical self-diagnostic and treatment advice system
US8663104B2 (en) 1997-03-13 2014-03-04 Clinical Decision Support, Llc Disease management system and method including therapeutic alterations permission level
US8727976B2 (en) 1997-03-13 2014-05-20 Clinical Decision Support, Llc Disease management system operating on a network
US8060378B2 (en) 1997-03-13 2011-11-15 Clinical Decision Support, Llc Disease management system and method including question version
US8066636B2 (en) 1997-03-13 2011-11-29 Clinical Decision Support, Llc Disease management system and method including pain code
US8740790B2 (en) 1997-03-13 2014-06-03 Clinical Decision Support, Llc Disease management system and method
US7993267B2 (en) 1997-03-13 2011-08-09 Clinical Decision Support, Llc Disease management system including a no response method
US8727979B2 (en) 1997-03-13 2014-05-20 Clinical Decision Support, Llc Disease management system and method including significant symptom filtering
US7769600B2 (en) 1997-03-13 2010-08-03 Clinical Decision Support Disease management system and method
US8392217B2 (en) 1997-03-13 2013-03-05 Clinical Decision Support, Llc Disease management system and method including preview mode
US8682694B2 (en) 1997-03-13 2014-03-25 Clinical Decision Support, Llc Disease management system and method including permission database
US8628470B1 (en) 1997-03-13 2014-01-14 Clinical Decision Support, Llc Disease management system and method including medication therapy self-management
US8630875B2 (en) 1997-03-13 2014-01-14 Clinical Decision Support, Llc Disease management system and health assessment method
US8019582B2 (en) 2000-02-14 2011-09-13 Clinical Decision Support, Llc Automated diagnostic system and method
US8301467B2 (en) 2003-05-15 2012-10-30 Clinical Decision Support, Llc Panel diagnostic method and system including active and passive strategies
US8055516B2 (en) 2003-05-15 2011-11-08 Clinical Decision Support, Llc Panel diagnostic method and system
US8731968B1 (en) 2003-05-15 2014-05-20 Clinical Decision Support, Llc Panel diagnostic method and system including automated diagnostic analysis
US7780595B2 (en) 2003-05-15 2010-08-24 Clinical Decision Support, Llc Panel diagnostic method and system
US9081879B2 (en) 2004-10-22 2015-07-14 Clinical Decision Support, Llc Matrix interface for medical diagnostic and treatment advice system and method
CN100589754C (en) 2006-07-14 2010-02-17 深圳迈瑞生物医疗电子股份有限公司 Electrocardiogram computer-aided diagnosis system
CN106250716A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Method and system for neurodermatitis prediction based on incremental type neural network model
CN106250712A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Ureteral calculus prediction method and prediction system based on incremental neural network model
CN106250715A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Chronic pharyngolaryngitis prediction method and prediction system based on incremental neural network model
CN106250713A (en) * 2016-09-28 2016-12-21 湖南老码信息科技有限责任公司 Vesical calculus prediction method and prediction system based on incremental neural network model
CN106202986A (en) * 2016-09-28 2016-12-07 湖南老码信息科技有限责任公司 Amygdalitis prediction method based on incremental neural network model and prediction system
CN106339606A (en) * 2016-09-28 2017-01-18 湖南老码信息科技有限责任公司 Alcohol liver prediction method based on incremental nerve network model and alcohol liver prediction system based on incremental nerve network model
CN106339607A (en) * 2016-09-28 2017-01-18 湖南老码信息科技有限责任公司 Rheumatism prediction method and rheumatism prediction system based on incremental nerve network model
CN106339605A (en) * 2016-09-28 2017-01-18 湖南老码信息科技有限责任公司 Colonitis prediction method and colonitis prediction system based on incremental nerve network model
CN106384007A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based hemorrhoids prediction method and prediction system
CN106384013A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based type-II diabetes prediction method and prediction system
CN106384005A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based depression prediction method and prediction system
CN106384008A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based allergic rhinitis prediction method and prediction system
CN106384006A (en) * 2016-09-28 2017-02-08 湖南老码信息科技有限责任公司 Incremental neural network model-based hepatitis C prediction method and prediction system
CN106407699A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Coronary heart disease prediction method and prediction system based on incremental neural network model
CN106407693A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Hepatitis B prediction method and prediction system based on incremental neural network model
CN106407694A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Neurasthenia prediction method and prediction system based on incremental neural network model
CN106407696A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Prickly heat prediction method and prediction system based on incremental neural network model
CN106407698A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Vegetative nervous disorder prediction method and prediction system based on incremental neural network model
CN106407700A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Hyperthyroidism prediction method and prediction system based on incremental neural network model
CN106407695A (en) * 2016-09-28 2017-02-15 湖南老码信息科技有限责任公司 Anxiety disorder prediction method and prediction system based on incremental neural network model
CN106446553A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Stomach illness prediction method and prediction system based on incremental neural network model
CN106446556A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for epifolliculitis based on incremental type neural network model
CN106446561A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Incremental neural network model based urticaria prediction method and system
CN106446559A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for viral dermatitis based on incremental type neural network model
CN106446549A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for dyspepsia based on incremental type neural network model
CN106446554A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Seborrheic dermatitis prediction method and prediction system based on incremental neural network model
CN106446563A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Incremental neural network model based constipation prediction method and system
CN106446557A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Prediction method and prediction system for hepatitis A based on incremental type neural network model
CN106446558A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Diabetes insipidus prediction method based on incremental neural network model and prediction system
CN106446550A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Cold prediction method and system based on incremental neutral network model
CN106446562A (en) * 2016-09-28 2017-02-22 湖南老码信息科技有限责任公司 Gastric concretion prediction method and prediction system based on incremental neural network model
CN106485065A (en) * 2016-09-28 2017-03-08 湖南老码信息科技有限责任公司 Chronic bronchitis prediction method and prediction system based on incremental neural network model

Also Published As

Publication number Publication date Type
CN1234092C (en) 2005-12-28 grant

Similar Documents

Publication Publication Date Title
Saxena et al. Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems
Orellana et al. Dynamic regime marginal structural mean models for estimation of optimal dynamic treatment regimes, part I: main content
Blanche et al. Estimating and comparing time‐dependent areas under receiver operating characteristic curves for censored event times with competing risks
Mirman et al. Statistical and computational models of the visual world paradigm: Growth curves and individual differences
Bauer et al. Conceptualizing and testing random indirect effects and moderated mediation in multilevel models: new procedures and recommendations.
Lee et al. A fuzzy expert system for diabetes decision support application
Dıez et al. Canonical probabilistic models for knowledge engineering
Montoya et al. Two-condition within-participant statistical mediation analysis: A path-analytic framework.
Ngai et al. Rule writing or annotation: Cost-efficient resource usage for base noun phrase chunking
Liu et al. Evolutionary optimization of software quality modeling with multiple repositories
Bahoura Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes
Cook et al. Marginal analysis of incomplete longitudinal binary data: a cautionary note on LOCF imputation
Zhou et al. Examining the potentially confounding effect of class size on the associations between object-oriented metrics and change-proneness
Lee et al. Bayesian analysis of structural equation models with dichotomous variables
Sun et al. Semiparametric regression analysis of longitudinal data with informative observation times
Dominici et al. Meta-analysis of migraine headache treatments: combining information from heterogeneous designs
Chou et al. Economic design of variable sampling intervals T2 control charts using genetic algorithms
McAlinden et al. Validation of the Quality of Life Inventory for patients with anxiety and depression
Beunckens et al. A latent‐class mixture model for incomplete longitudinal Gaussian data
Yi et al. Marginal methods for incomplete longitudinal data arising in clusters
Berger et al. The neurobiological basis of cognition: identification by multi-input, multioutput nonlinear dynamic modeling
Abeyratne et al. Mixed-phase modeling in snore sound analysis
Forbus et al. Self-explanatory simulations: Scaling up to large models
US7356521B2 (en) System and method for automatic molecular diagnosis of ALS based on boosting classification
Calero et al. Method for Obtaining Correct Metrics.

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C14 Grant of patent or utility model
C17 Cessation of patent right