WO2019062186A1 - 糖尿病分析方法、应用服务器和计算机可读存储介质 - Google Patents

糖尿病分析方法、应用服务器和计算机可读存储介质 Download PDF

Info

Publication number
WO2019062186A1
WO2019062186A1 PCT/CN2018/089429 CN2018089429W WO2019062186A1 WO 2019062186 A1 WO2019062186 A1 WO 2019062186A1 CN 2018089429 W CN2018089429 W CN 2018089429W WO 2019062186 A1 WO2019062186 A1 WO 2019062186A1
Authority
WO
WIPO (PCT)
Prior art keywords
diabetes
data
complications
analysis
user
Prior art date
Application number
PCT/CN2018/089429
Other languages
English (en)
French (fr)
Inventor
金晓辉
李菲菲
肖京
徐亮
Original Assignee
平安科技（深圳）有限公司
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
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019062186A1 publication Critical patent/WO2019062186A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • the present application relates to the field of data analysis technologies, and in particular, to a diabetes analysis method, an application server, and a computer readable storage medium.
  • Diabetes is a group of lifelong metabolic diseases characterized by multiple causes of chronic hyperglycemia. Long-term blood sugar, high blood vessels, microvascular damage and endanger the heart, brain, kidney, peripheral nerves, eyes, feet, etc. According to the World Health Organization statistics, diabetes complications up to more than 100, is currently the most known complication disease. More than half of the deaths from diabetes are caused by cardiovascular and cerebrovascular diseases, and 10% are caused by nephropathy. Patients with amputation due to diabetes are 10 to 20 times more likely to be non-diabetic. According to clinical data, 30% to 40% of patients will have at least one complication after 10 years of onset of diabetes, and once the complications are generated, drug treatment is difficult to reverse, so it is emphasized that diabetes complications should be prevented as soon as possible.
  • the present application provides a diabetes analysis method, an application server, and a computer readable storage medium to solve the problem of how to effectively prevent diabetes and other complications.
  • a first aspect of the present application provides a method for analyzing diabetes, the method comprising the steps of:
  • a second aspect of the present application provides an application server including a memory, a processor, and a diabetes analysis system stored on the memory and operable on the processor, the diabetes analysis system being processed The following steps are implemented when the device is executed:
  • a third aspect of the present application provides a computer readable storage medium storing a diabetes analysis system, the enterprise recommendation program being executable by at least one processor to cause the at least one processor to execute the following step:
  • the diabetes analysis method, the application server and the computer readable storage medium proposed by the present application can use big data to find the characteristics and disease information of each dimension of the sample based on a large user sample.
  • the method of correlation analysis the potential relationship between various diseases of different types of people is studied.
  • the probability of diabetes in various users, the probability of other complications of diabetes patients, and the relationship between diabetes and other influencing factors are obtained through the user's illness.
  • help potential diabetic patients prevent early and help diabetics prevent other complications.
  • 1 is a schematic diagram of an optional hardware architecture of an application server of the present application
  • FIG. 2 is a schematic diagram of a program module of a first embodiment of the diabetes analysis system of the present application
  • FIG. 3 is a schematic diagram of a program module of a second embodiment of the diabetes analysis system of the present application.
  • FIG. 4 is a schematic flow chart of a first embodiment of a method for analyzing diabetes in the present application
  • Fig. 5 is a flow chart showing the second embodiment of the diabetes analysis method of the present application.
  • Diabetes analysis system 200 Setting module 201 Acquisition module 202 Analysis module 203 Output module 204 Preprocessing module 205
  • FIG. 1 it is a schematic diagram of an optional hardware architecture of the application server 2 of the present application.
  • the application server 2 may include, but is not limited to, the memory 11, the processor 12, and the network interface 13 being communicably connected to each other through a system bus. It is to be noted that FIG. 2 only shows the application server 2 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the application server 2 may be a computing device such as a rack server, a blade server, a tower server, or a rack server.
  • the application server 2 may be an independent server or a server cluster composed of multiple servers. .
  • the memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (eg, SD or DX memory, etc.), a random access memory (RAM), a static Random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk, and the like.
  • the memory 11 may be an internal storage unit of the application server 2, such as a hard disk or memory of the application server 2.
  • the memory 11 may also be an external storage device of the application server 2, such as a plug-in hard disk equipped on the application server 2, a smart memory card (SMC), and a secure digital number. (Secure Digital, SD) card, flash card, etc.
  • the memory 11 can also include both the internal storage unit of the application server 2 and its external storage device.
  • the memory 11 is generally used to store an operating system and various application software installed in the application server 2, such as a program code of the diabetes analysis system 200. Further, the memory 11 can also be used to temporarily store various types of data that have been output or are to be output.
  • the processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments.
  • the processor 12 is typically used to control the overall operation of the application server 2.
  • the processor 12 is configured to run program code or process data stored in the memory 11, such as running the diabetes analysis system 200 or the like.
  • the network interface 13 may comprise a wireless network interface or a wired network interface, which is typically used to establish a communication connection between the application server 2 and other electronic devices.
  • the present application proposes a diabetes analysis system 200.
  • FIG. 2 it is a program block diagram of the first embodiment of the diabetes analysis system 200 of the present application.
  • the diabetes analysis system 200 includes a series of computer program instructions stored on the memory 11, and when the computer program instructions are executed by the processor 12, the diabetes analysis operation of the embodiments of the present application can be implemented.
  • the diabetes analysis system 200 can be divided into one or more modules based on the particular operations implemented by the various portions of the computer program instructions. For example, in FIG. 3, the diabetes analysis system 200 can be divided into a setup module 201, an acquisition module 202, an analysis module 203, and an output module 204. among them:
  • the setting module 201 is configured to set a sample range, including a user range and a data dimension.
  • the present embodiment needs to utilize big data to search for characteristics of various dimensions of the sample and disease information based on a large user sample, thereby analyzing the potential relationship between various types of diseases of different types of people.
  • the user scope includes a data source and an acquisition time, a city, an age, a gender, and the like.
  • data from all hospitals and insurance companies can be set up to collect data from all male and female users over the age of 18 years in Shenzhen from 2010 to 2015.
  • the data dimensions include population attributes (gender, age, marriage, education, etc.), whether the user has diabetes and complications, health, and non-health factors.
  • health factors include related factors such as physical examination and medication; non-health factors include related factors such as occupation and financial consumption.
  • the obtaining module 202 is configured to acquire corresponding sample data according to the set sample range.
  • data of all the data dimensions corresponding to users of the cities set in the collection time that meet the characteristics of the age, gender, and the like are acquired from the data source.
  • the analysis module 203 is configured to perform correlation analysis on the relationship between each data dimension in the sample data and diabetes or complications.
  • each user's illness is obtained from the sample data, including diabetes and its complications. Whether or not diabetes or complications are used as the right item set of the association rule, and other data dimensions are used as the left item set for association analysis.
  • the high-lift rule is screened from the results, and the corresponding left item set factor is the disease factor of diabetes or complications. Users are classified according to the left item set factor found in the association analysis, including health factors, non-health factors, population attributes, and so on. Further in-depth analysis of each type of user, calculate the probability of diabetes in various types of users, and generate various complications. Compare the proportion of patients with various diseases, find out the pathological relationship between diabetes or complications and different disease factors, and the extent to which different factors affect the user's diabetes or complications.
  • the output module 204 is configured to output a correlation analysis result.
  • the association analysis result includes a related item set and corresponding support degree, confidence, and degree of elevation, and is used to find a relationship between various factors and diabetes or complications, thereby finding a potential disease of diabetes or complications.
  • the corresponding support, confidence, and ascension of the association factor indicate the association between the patient of the category to which the association factor belongs and whether or not there is diabetes or complications.
  • the support of factor i is a%, which represents the proportion of the population containing factor i in the total population;
  • the confidence is b%, indicating that the proportion of people with diabetes in the population containing factor i is b%
  • the degree of lift is c, indicating that the proportion of the above-mentioned population has increased by a factor of c compared to the proportion of diabetic patients in the total population.
  • the degree of strength of factor i as a disease factor for diabetes is explained.
  • This embodiment utilizes a large number of user samples to use the association analysis method to explore the relationship between diabetes (complication) and other dimensional features, rather than simply determining the disease factor of diabetes (complication) according to the pathological relationship. This can more comprehensively mine more potential disease information, and can get the numerical results of the impact of each factor on the disease, can more intuitively compare the importance of different factors.
  • the diabetes analysis system 200 includes a pre-processing module 205 in addition to the setting module 201, the obtaining module 202, the analyzing module 203, and the output module 204 in the first embodiment.
  • the pre-processing module 205 is configured to pre-process the sample data after the obtaining module 202 acquires sample data.
  • the pre-processing includes missing value processing and discretization of continuous variables.
  • the missing data is discarded by default. If you want to keep the missing data, you need to fill in the missing values first.
  • the sample missing values in this embodiment are mainly filled by the following methods:
  • This association rule cannot handle continuous variables, so it is equally or equal-width binned for continuous variables.
  • the age is divided into equal boxes, and in the later stage, several boxes having a smaller amount of data are merged.
  • the rest of the data is uneven due to the uneven distribution of data, so the left-shift phenomenon is serious, so the equal-frequency binning is adopted.
  • the present application also proposes a method for analyzing diabetes.
  • FIG. 4 it is a schematic flow chart of the first embodiment of the diabetes analysis method of the present application.
  • the order of execution of the steps in the flowchart shown in FIG. 4 may be changed according to different requirements, and some steps may be omitted.
  • Step S400 setting a sample range, including a user range and a data dimension.
  • the present embodiment needs to utilize big data to search for characteristics of various dimensions of the sample and disease information based on a large user sample, thereby analyzing the potential relationship between various types of diseases of different types of people.
  • the user scope includes a data source and an acquisition time, a city, an age, a gender, and the like.
  • data from all hospitals and insurance companies can be set up to collect data from all male and female users over the age of 18 years in Shenzhen from 2010 to 2015.
  • the data dimensions include population attributes (gender, age, marriage, education, etc.), whether the user has diabetes and complications, health, and non-health factors.
  • health factors include related factors such as physical examination and medication; non-health factors include related factors such as occupation and financial consumption.
  • Step S402 acquiring corresponding sample data according to the set sample range.
  • data of all the data dimensions corresponding to users of the cities set in the collection time that meet the characteristics of the age, gender, and the like are acquired from the data source.
  • Step S404 correlating and analyzing the relationship between each data dimension in the sample data and diabetes or complications.
  • each user's illness is obtained from the sample data, including diabetes and its complications. Whether or not diabetes or complications are used as the right item set of the association rule, and other data dimensions are used as the left item set for association analysis.
  • the high-lift rule is screened from the results, and the corresponding left item set factor is the disease factor of diabetes or complications. Users are classified according to the left item set factor found in the association analysis, including health factors, non-health factors, and population attributes. Further in-depth analysis of each type of user, calculate the probability of diabetes in various types of users, and generate various complications. Compare the proportion of patients with various diseases, find out the pathological relationship between diabetes or complications and different disease factors, and the extent to which different factors affect the user's diabetes or complications.
  • step S406 the correlation analysis result is output.
  • the association analysis result includes a related item set and corresponding support degree, confidence, and degree of elevation, and is used to find a relationship between various factors and diabetes or complications, thereby finding a potential disease of diabetes or complications.
  • the corresponding support, confidence, and ascension of the association factor indicate the association between the patient of the category to which the association factor belongs and whether or not there is diabetes or complications.
  • the support of factor i is a%, which represents the proportion of the population containing factor i in the total population;
  • the confidence is b%, indicating that the proportion of people with diabetes in the population containing factor i is b%
  • the degree of lift is c, indicating that the proportion of the above-mentioned population has increased by a factor of c compared to the proportion of diabetic patients in the total population.
  • the degree of strength of factor i as a disease factor for diabetes is explained.
  • the diabetes analysis method proposed in this embodiment utilizes a large number of user samples and uses the association analysis method to explore the relationship between diabetes (complication) and other dimensional features, instead of simply determining the diabetes according to the pathological relationship (complication) The disease factor. This can more comprehensively mine more potential disease information, and can get the numerical results of the impact of each factor on the disease, can more intuitively compare the importance of different factors.
  • steps S500-S502 and S506-S508 of the diabetes analysis method are similar to steps S400-S406 of the first embodiment, except that the method further includes step S504.
  • the method includes the following steps:
  • Step S500 setting a sample range, including a user range and a data dimension.
  • the present embodiment needs to utilize big data to search for characteristics of various dimensions of the sample and disease information based on a large user sample, thereby analyzing the potential relationship between various types of diseases of different types of people.
  • the user scope includes a data source and an acquisition time, a city, an age, a gender, and the like.
  • data from all hospitals and insurance companies can be set up to collect data from all male and female users over the age of 18 years in Shenzhen from 2010 to 2015.
  • the data dimensions include population attributes (gender, age, marriage, education, etc.), whether the user has diabetes and complications, health, and non-health factors.
  • health factors include related factors such as physical examination and medication; non-health factors include related factors such as occupation and financial consumption.
  • Step S502 acquiring corresponding sample data according to the set sample range.
  • data of all the data dimensions corresponding to users of the cities set in the collection time that meet the characteristics of the age, gender, and the like are acquired from the data source.
  • Step S504 preprocessing the sample data.
  • the pre-processing includes missing value processing and discretization of continuous variables.
  • the missing data is discarded by default. If you want to keep the missing data, you need to fill in the missing values first.
  • the sample missing values in this embodiment are mainly filled by the following methods:
  • This association rule cannot handle continuous variables, so it is equally or equal-width binned for continuous variables.
  • the age is divided into equal boxes, and in the later stage, several boxes having a smaller amount of data are merged.
  • the rest of the data is uneven due to the uneven distribution of data, so the left-shift phenomenon is serious, so the equal-frequency binning is adopted.
  • Step S506 correlating and analyzing the relationship between each data dimension in the sample data and diabetes or complications.
  • each user's illness is obtained from the sample data, including diabetes and its complications. Whether or not diabetes or complications are used as the right item set of the association rule, and other data dimensions are used as the left item set for association analysis.
  • the high-lift rule is screened from the results, and the corresponding left item set factor is the disease factor of diabetes or complications. Users are classified according to the left item set factor found in the association analysis, including health factors, non-health factors, population attributes, and so on. Further in-depth analysis of each type of user, calculate the probability of diabetes in various types of users, and generate various complications. Compare the proportion of patients with various diseases, find out the pathological relationship between diabetes or complications and different disease factors, and the extent to which different factors affect the user's diabetes or complications.
  • Step S508 outputting the correlation analysis result.
  • the association analysis result includes a related item set and corresponding support degree, confidence, and degree of elevation, and is used to find a relationship between various factors and diabetes or complications, thereby finding a potential disease of diabetes or complications.
  • the corresponding support, confidence, and ascension of the association factor indicate the association between the patient of the category to which the association factor belongs and whether or not there is diabetes or complications.
  • the support of factor i is a%, which represents the proportion of the population containing factor i in the total population;
  • the confidence is b%, indicating that the proportion of people with diabetes in the population containing factor i is b%
  • the degree of lift is c, indicating that the proportion of the above-mentioned population has increased by a factor of c compared to the proportion of diabetic patients in the total population.
  • the degree of strength of factor i as a disease factor for diabetes is explained.
  • the diabetes analysis method proposed in this embodiment can utilize big data and find the characteristics and disease information of each dimension of the sample based on a large user sample. After obtaining the sample data, the sample data is pre-processed to facilitate the subsequent analysis of the potential relationship between various types of diseases in different populations by means of association analysis. Furthermore, the probability of diabetes in various users, the probability of other complications of diabetes patients, and the relationship between diabetes and other influencing factors are obtained through the user's illness. Ultimately help potential diabetic patients prevent early and help diabetics prevent other complications.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

本申请公开了一种糖尿病分析方法，该方法包括：设置样本范围，包括用户范围和数据维度；根据所设置的样本范围，获取相应的样本数据；对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；输出关联分析结果。本申请还提供一种应用服务器及计算机可读存储介质。本申请提供的糖尿病分析方法、应用服务器及计算机可读存储介质能够利用大数据进行关联分析，得到各类不同用户患糖尿病的几率、糖尿病患者产生其他并发症的几率、以及糖尿病与其他影响因素之间的关系，帮助潜在糖尿病及其并发症患者提早预防。

Description

糖尿病分析方法、应用服务器和计算机可读存储介质
本申请基于巴黎公约申明享有2017年9月30日递交的申请号为CN 201710916176.5、名称为“糖尿病分析方法及应用服务器”中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及数据分析技术领域，特别涉及一种糖尿病分析方法、应用服务器和计算机可读存储介质。
背景技术
糖尿病是一组由多病因引起的以慢性高血糖为特征的终身性代谢性疾病。长期血糖增高，大血管、微血管受损并危及心、脑、肾、周围神经、眼睛、足等，据世界卫生组织统计，糖尿病并发症高达100多种，是目前已知并发症最多的一种疾病。糖尿病死亡者有一半以上是心脑血管所致，10％是肾病变所致。因糖尿病截肢的患者是非糖尿病的10～20倍。临床数据显示，糖尿病发病后10年左右，将有30％～40％的患者至少会发生一种并发症，且并发症一旦产生，药物治疗很难逆转，因此强调尽早预防糖尿病并发症。
糖尿病的发病存在三方面因素：遗传、环境因素和生理性老化引起胰岛素抵抗和胰岛素作用不足。根据糖尿病并发症发病的急缓以及病理上的差异，可将其分为急性和慢性两大类。传统医学上，由于并发症的多样化导致并发症的确诊较为复杂，时间开销很大，很容易耽误治疗及预防时间。
发明内容
本申请提供一种糖尿病分析方法、应用服务器和计算机可读存储介质，以解决如何有效预防糖尿病及其他并发症的问题。
本申请第一方面提供一种糖尿病分析方法，该方法包括步骤：
设置样本范围，包括用户范围和数据维度；
根据所设置的样本范围，获取相应的样本数据；
对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；及
输出关联分析结果。
本申请第二方面提供一种应用服务器，所述应用服务器包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的糖尿病分析系统，所述糖尿病分析系统被所述处理器执行时实现如下步骤：
设置样本范围，包括用户范围和数据维度；
根据所设置的样本范围，获取相应的样本数据；
对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；及
输出关联分析结果。
本申请第三方面提供一种计算机可读存储介质，所述计算机可读存储介质存储有糖尿病分析系统，所述企业推荐程序可被至少一个处理器执行，以使所述至少一个处理器执行以下步骤：
设置样本范围，包括用户范围和数据维度；
根据所设置的样本范围，获取相应的样本数据；
对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；及
输出关联分析结果。
相较于现有技术，本申请所提出的糖尿病分析方法、应用服务器及计算机可读存储介质，可以利用大数据，基于庞大的用户样本，寻找样本的各个维度的特征及患病信息。通过关联分析的方法，研究各类不同的人群的各类患病之间的潜在关系。进而通过用户的患病情况得到各类不同用户患糖尿病的几率、糖尿病患者产生其他并发症的几率、以及糖尿病与其他影响因素之间的关系。最终帮助潜在糖尿病患者提早预防，并帮助糖尿病患者预防其他并发症的产生。
附图说明
图1是本申请应用服务器一可选的硬件架构的示意图；
图2是本申请糖尿病分析系统第一实施例的程序模块示意图；
图3是本申请糖尿病分析系统第二实施例的程序模块示意图；
图4是本申请糖尿病分析方法第一实施例的流程示意图；
图5是本申请糖尿病分析方法第二实施例的流程示意图。
附图标记：
应用服务器 2
存储器 11
处理器 12
网络接口 13
糖尿病分析系统 200
设置模块 201
获取模块 202
分析模块 203
输出模块 204
预处理模块 205
具体实施方式
以下结合附图对本申请的原理和特征进行描述，所举实例只用于解释本申请，并非用于限定本申请的范围。
参阅图1所示，是本申请应用服务器2一可选的硬件架构的示意图。
本实施例中，所述应用服务器2可包括，但不仅限于，可通过系统总线相互通信连接存储器11、处理器12、网络接口13。需要指出的是，图2仅示出了具有组件11-13的应用服务器2，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
其中，所述应用服务器2可以是机架式服务器、刀片式服务器、塔式服务器或机柜式服务器等计算设备，该应用服务器2可以是独立的服务器，也可以是多个服务器所组成的服务器集群。
所述存储器11至少包括一种类型的可读存储介质，所述可读存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等。在一些实施例中，所述存储器11可以是所述应用服务器2的内部存储单元，例如该应用服务器2的硬盘或内存。在另一些实施例中，所述存储器11也可以是所述应用服务器2的外部存储设备，例如该应用服务器2上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。当然，所述存储器11还可以既包括所述应用服务器2的内部存储单元也包括其外部存储设备。本实施例中，所述存储器11通常用于存储安装于所述应用服务器2的操作系统和各类应用软件，例如糖尿病分析系统200的程 序代码等。此外，所述存储器11还可以用于暂时地存储已经输出或者将要输出的各类数据。
所述处理器12在一些实施例中可以是中央处理器(Central Processing Unit，CPU)、控制器、微控制器、微处理器、或其他数据处理芯片。该处理器12通常用于控制所述应用服务器2的总体操作。本实施例中，所述处理器12用于运行所述存储器11中存储的程序代码或者处理数据，例如运行所述的糖尿病分析系统200等。
所述网络接口13可包括无线网络接口或有线网络接口，该网络接口13通常用于在所述应用服务器2与其他电子设备之间建立通信连接。
至此，己经详细介绍了本申请相关设备的硬件结构和功能。下面，将基于上述介绍提出本申请的各个实施例。
首先，本申请提出一种糖尿病分析系统200。
参阅图2所示，是本申请糖尿病分析系统200第一实施例的程序模块图。
本实施例中，所述糖尿病分析系统200包括一系列的存储于存储器11上的计算机程序指令，当该计算机程序指令被处理器12执行时，可以实现本申请各实施例的糖尿病分析操作。在一些实施例中，基于该计算机程序指令各部分所实现的特定的操作，糖尿病分析系统200可以被划分为一个或多个模块。例如，在图3中，所述糖尿病分析系统200可以被分割成设置模块201、获取模块202、分析模块203、输出模块204。其中：
所述设置模块201，用于设置样本范围，包括用户范围和数据维度。
具体地，本实施例需要利用大数据，基于庞大的用户样本，寻找样本的各个维度的特征及患病信息，从而分析出各类不同的人群的各类患病之间的潜在关系。
首先，需要设置所采集的样本的范围，所述样本范围包括用户范围和数据维度。其中，所述用户范围包括数据来源及采集时间、城市、年龄、性别等。例如，可以设置从医院和保险公司的数据库中采集2010年至2015年深圳市18岁以上的所有男性及女性用户的数据。所述数据维度包括人口属性(性别、年龄、婚姻、学历等)、用户是否患有糖尿病及并发症、健康以及非健康因子等多个维度。例如，健康因子包括体检、用药等相关因子；非健康因子包括职业、金融消费等相关因子。
所述获取模块202，用于根据所设置的样本范围，获取相应的样本数据。
具体地，根据所述用户范围，从所述数据来源中获取所述采集时间内所设置的城市的符合所述年龄和性别等特征的用户对应的所有所述数据维度的数据。
所述分析模块203，用于对样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析。
具体地，从样本数据中获取各用户患病情况，包括糖尿病及其并发症。将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集进行关联分析。从结果中筛选出高提升度的规则，对应的左项集因子即为糖尿病或并发症的患病因子。按关联分析中找到的左项集因子对用户进行分类，其中包括健康因子、非健康因子、人口属性等。对每一类用户进行进一步深入的分析，计算各类用户患糖尿病几率，产生各种并发症几率。比较各类用户的患病比例，找出糖尿病或并发症与不同的患病因子之间的病理关系，以及不同患病因子对于用户患上糖尿病或并发症的影响的强弱程度。
所述输出模块204，用于输出关联分析结果。
具体地，所述关联分析结果包括关联项集以及相应的支持度、置信度、提升度，用于发现各个因素与糖尿病或并发症之间的关联关系，从而找到糖尿病或并发症潜在的患病因子、以及不同人群的各类患病因子对糖尿病或并发症的影响的强弱关系。
关联因子相应的支持度、置信度、提升度说明了该关联因子所属类别的患者与是否患有糖尿病或并发症的关联关系。例如，因子i的支持度是a％，表示包含因子i的人群在总人群中的占比；置信度是b％，表示包含因子i的人群中患有糖尿病的人群的所占比例为b％；提升度是c，表示上述人群占比相比于总人群中糖尿病患者占比的倍数提升了c倍。说明了因子i作为糖尿病的患病因子的强弱程度。
本实施例利用了大量的用户样本，使用关联分析的方法挖掘糖尿病(并发症)与其他维度特征之间的关系，而不是简单的依照病理关系来确定糖尿病(并发症)的患病因子。这样能更全面的挖掘出更多潜在的患病信息，并能得到每项因子对患病产生的影响程度的数值化结果，能更加直观的比较不同因子的重要性。
参阅图3所示，是本申请糖尿病分析系统200第二实施例的程序模块图。本实施例中，所述的糖尿病分析系统200除了包括第一实施例中的所述设置模块201、获取模块202、分析模块203、输出模块204之外，还包括预处理模块205。
所述预处理模块205用于在所述获取模块202获取样本数据后，对所述样本数据进行预处理。
具体地，所述预处理包括缺失值处理和连续变量的离散化。
在本实施例中，默认将有缺失的数据进行丢弃。如果想保留包含缺失的数据，需要先对缺失值进行填充。本实施例中的样本缺失值主要通过如下方法填充：
a)人口属性和体检指标中涉及到的连续变量用均值填充；
b)金融消费属性中涉及到的连续变量用0填充；
c)各类疾病涉及到的缺失值用0填充，即缺失表示未患病；
d)其他离散维度用-1填充，单独表示缺失类。
该关联规则不能处理连续变量，因此对连续变量进行等频或等宽分箱。例如，本实施例中对年龄进行了等宽分箱，后期又将数据量较小的几个箱进行了合并。其余数据由于数据分布不均匀，左偏现象严重，因此采用等频分箱。
此外，本申请还提出一种糖尿病分析方法。
参阅图4所示，是本申请糖尿病分析方法第一实施例的流程示意图。在本实施例中，根据不同的需求，图4所示的流程图中的步骤的执行顺序可以改变，某些步骤可以省略。
步骤S400，设置样本范围，包括用户范围和数据维度。
具体地，本实施例需要利用大数据，基于庞大的用户样本，寻找样本的各个维度的特征及患病信息，从而分析出各类不同的人群的各类患病之间的潜在关系。
首先，需要设置所采集的样本的范围，所述样本范围包括用户范围和数据维度。其中，所述用户范围包括数据来源及采集时间、城市、年龄、性别等。例如，可以设置从医院和保险公司的数据库中采集2010年至2015年深圳市18岁以上的所有男性及女性用户的数据。所述数据维度包括人口属性(性别、年龄、婚姻、学历等)、用户是否患有糖尿病及并发症、健康以及非健康因子等多个维度。例如，健康因子包括体检、用药等相关因子；非健康因子包括职业、金融消费等相关因子。
步骤S402，根据所设置的样本范围，获取相应的样本数据。
具体地，根据所述用户范围，从所述数据来源中获取所述采集时间内所设置的城市的符合所述年龄和性别等特征的用户对应的所有所述数据维度的数据。
步骤S404，对样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析。
具体地，从样本数据中获取各用户患病情况，包括糖尿病及其并发症。将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集进行关联分析。从结果中筛选出高提升度的规则，对应的左项集因子即为糖尿病或并发症的患病因子。按关联分析中找到的 左项集因子对用户进行分类，其中包括健康因子、非健康因子、人口属性等。对每一类用户进行进一步深入的分析，计算各类用户患糖尿病几率，产生各种并发症几率。比较各类用户的患病比例，找出糖尿病或并发症与不同的患病因子之间的病理关系，以及不同患病因子对于用户患上糖尿病或并发症的影响的强弱程度。
步骤S406，输出关联分析结果。
具体地，所述关联分析结果包括关联项集以及相应的支持度、置信度、提升度，用于发现各个因素与糖尿病或并发症之间的关联关系，从而找到糖尿病或并发症潜在的患病因子、以及不同人群的各类患病因子对糖尿病或并发症的影响的强弱关系。
关联因子相应的支持度、置信度、提升度说明了该关联因子所属类别的患者与是否患有糖尿病或并发症的关联关系。例如，因子i的支持度是a％，表示包含因子i的人群在总人群中的占比；置信度是b％，表示包含因子i的人群中患有糖尿病的人群的所占比例为b％；提升度是c，表示上述人群占比相比于总人群中糖尿病患者占比的倍数提升了c倍。说明了因子i作为糖尿病的患病因子的强弱程度。
本实施例所提出的糖尿病分析方法，利用了大量的用户样本，使用关联分析的方法挖掘糖尿病(并发症)与其他维度特征之间的关系，而不是简单的依照病理关系来确定糖尿病(并发症)的患病因子。这样能更全面的挖掘出更多潜在的患病信息，并能得到每项因子对患病产生的影响程度的数值化结果，能更加直观的比较不同因子的重要性。
如图5所示，是本申请糖尿病分析方法的第二实施例的流程示意图。本实施例中，所述糖尿病分析方法的步骤S500-S502及S506-S508与第一实施例的步骤S400-S406相类似，区别在于该方法还包括步骤S504。
该方法包括以下步骤：
步骤S500，设置样本范围，包括用户范围和数据维度。
具体地，本实施例需要利用大数据，基于庞大的用户样本，寻找样本的各个维度的特征及患病信息，从而分析出各类不同的人群的各类患病之间的潜在关系。
首先，需要设置所采集的样本的范围，所述样本范围包括用户范围和数据维度。其中，所述用户范围包括数据来源及采集时间、城市、年龄、性别等。例如，可以设置从医院和保险公司的数据库中采集2010年至2015年深圳市18岁以上的所有男性及女性用户的数据。所述数据维度包括人口属性(性别、年龄、婚姻、学历等)、用户是否患有糖尿病及并发症、健康以及非健康因子等多个维度。例如，健康因子包 括体检、用药等相关因子；非健康因子包括职业、金融消费等相关因子。
步骤S502，根据所设置的样本范围，获取相应的样本数据。
具体地，根据所述用户范围，从所述数据来源中获取所述采集时间内所设置的城市的符合所述年龄和性别等特征的用户对应的所有所述数据维度的数据。
步骤S504，对所述样本数据进行预处理。
具体地，所述预处理包括缺失值处理和连续变量的离散化。
在本实施例中，默认将有缺失的数据进行丢弃。如果想保留包含缺失的数据，需要先对缺失值进行填充。本实施例中的样本缺失值主要通过如下方法填充：
a)人口属性和体检指标中涉及到的连续变量用均值填充；
b)金融消费属性中涉及到的连续变量用0填充；
c)各类疾病涉及到的缺失值用0填充，即缺失表示未患病；
d)其他离散维度用-1填充，单独表示缺失类。
该关联规则不能处理连续变量，因此对连续变量进行等频或等宽分箱。例如，本实施例中对年龄进行了等宽分箱，后期又将数据量较小的几个箱进行了合并。其余数据由于数据分布不均匀，左偏现象严重，因此采用等频分箱。
步骤S506，对样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析。
具体地，从样本数据中获取各用户患病情况，包括糖尿病及其并发症。将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集进行关联分析。从结果中筛选出高提升度的规则，对应的左项集因子即为糖尿病或并发症的患病因子。按关联分析中找到的左项集因子对用户进行分类，其中包括健康因子、非健康因子、人口属性等。对每一类用户进行进一步深入的分析，计算各类用户患糖尿病几率，产生各种并发症几率。比较各类用户的患病比例，找出糖尿病或并发症与不同的患病因子之间的病理关系，以及不同患病因子对于用户患上糖尿病或并发症的影响的强弱程度。
步骤S508，输出关联分析结果。
具体地，所述关联分析结果包括关联项集以及相应的支持度、置信度、提升度，用于发现各个因素与糖尿病或并发症之间的关联关系，从而找到糖尿病或并发症潜在的患病因子、以及不同人群的各类患病因子对糖尿病或并发症的影响的强弱关系。
关联因子相应的支持度、置信度、提升度说明了该关联因子所属类别的患者与是否患有糖尿病或并发症的关联关系。例如，因子i的支持度是a％，表示包含因子i的人群在总人群中的占比；置信度是b％， 表示包含因子i的人群中患有糖尿病的人群的所占比例为b％；提升度是c，表示上述人群占比相比于总人群中糖尿病患者占比的倍数提升了c倍。说明了因子i作为糖尿病的患病因子的强弱程度。
本实施例所提出的糖尿病分析方法，可以利用大数据，基于庞大的用户样本，寻找样本的各个维度的特征及患病信息。在获取到样本数据后，先对所述样本数据进行预处理，以便于后续通过关联分析的方法，研究各类不同的人群的各类患病之间的潜在关系。进而通过用户的患病情况得到各类不同用户患糖尿病的几率、糖尿病患者产生其他并发症的几率、以及糖尿病与其他影响因素之间的关系。最终帮助潜在糖尿病患者提早预防，并帮助糖尿病患者预防其他并发症的产生。
以上所述仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是在本申请的申请构思下，利用本申请说明书及附图内容所作的等效结构变换，或直接/间接运用在其他相关的技术领域均包括在本申请的专利保护范围内。

Claims (20)

  1. 一种糖尿病分析方法，应用于应用服务器，其特征在于，所述方法包括步骤：
    设置样本范围，包括用户范围和数据维度；
    根据所设置的样本范围，获取相应的样本数据；
    对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；及
    输出关联分析结果。
  2. 如权利要求1所述的糖尿病分析方法，其特征在于，该方法在进行所述关联分析之前还包括步骤：
    对所述样本数据进行预处理，包括缺失值处理和连续变量的离散化。
  3. 如权利要求2所述的糖尿病分析方法，其特征在于，所述用户范围包括数据来源及采集时间、城市、年龄、性别；所述数据维度包括人口属性、用户是否患有糖尿病及并发症、健康以及非健康因子。
  4. 如权利要求2所述的糖尿病分析方法，其特征在于，所述对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析的步骤具体包括：
    从样本数据中获取各用户患病情况，包括糖尿病及其并发症；
    将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集进行关联分析；
    从结果中筛选出高提升度的规则，对应的左项集因子即为糖尿病或并发症的患病因子。
  5. 如权利要求4所述的糖尿病分析方法，其特征在于，所述对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析的步骤还包括：
    按关联分析中找到的左项集因子对用户进行分类；
    对每一类用户进行进一步深入的分析，计算各类用户患糖尿病几率，产生各种并发症几率；
    比较各类用户的患病比例，找出糖尿病或并发症与不同的患病因子之间的病理关系，以及不同患病因子对于用户患上糖尿病或并发症的影响的强弱程度。
  6. 如权利要求2所述的糖尿病分析方法，其特征在于，所述关联分析结果包括关联项集以及相应的支持度、置信度、提升度。
  7. 如权利要求2所述的糖尿病分析方法，其特征在于，所述缺失值处理包括：
    默认将有缺失的数据进行丢弃，若要保留包含缺失的数据，则先对缺失值进行填充；所述缺失值的填充方式包括：
    人口属性和体检指标中涉及到的连续变量用均值填充；
    金融消费属性中涉及到的连续变量用0填充；
    各类疾病涉及到的缺失值用0填充；
    其他离散维度用-1填充。
  8. 如权利要求2所述的糖尿病分析方法，其特征在于，所述连续变量的离散化包括：对连续变量进行等频或等宽分箱。
  9. 一种应用服务器，其特征在于，所述应用服务器包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的糖尿病分析系统，所述糖尿病分析系统被所述处理器执行时实现如下步骤：
    设置样本范围，包括用户范围和数据维度；
    根据所设置的样本范围，获取相应的样本数据；
    对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；及
    输出关联分析结果。
  10. 如权利要求9所述的应用服务器，其特征在于，在进行所述关联分析之前，所述处理器还用于执行所述糖尿病分析系统以实现：
    对所述样本数据进行预处理，包括缺失值处理和连续变量的离散化。
  11. 如权利要求10所述的应用服务器，其特征在于，所述用户范围包括数据来源及采集时间、城市、年龄、性别；所述数据维度包括人口属性、用户是否患有糖尿病及并发症、健康以及非健康因子。
  12. 如权利要求10所述的应用服务器，其特征在于，所述对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析的步骤具体包括：
    从样本数据中获取各用户患病情况，包括糖尿病及其并发症；
    将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度 作为左项集进行关联分析；
    从结果中筛选出高提升度的规则，对应的左项集因子即为糖尿病或并发症的患病因子。
  13. 如权利要求12所述的应用服务器，其特征在于，所述对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析的步骤还包括：
    按关联分析中找到的左项集因子对用户进行分类；
    对每一类用户进行进一步深入的分析，计算各类用户患糖尿病几率，产生各种并发症几率；
    比较各类用户的患病比例，找出糖尿病或并发症与不同的患病因子之间的病理关系，以及不同患病因子对于用户患上糖尿病或并发症的影响的强弱程度。
  14. 如权利要求10所述的应用服务器，其特征在于，所述关联分析结果包括关联项集以及相应的支持度、置信度、提升度。
  15. 如权利要求10所述的应用服务器，其特征在于，所述缺失值处理包括：
    默认将有缺失的数据进行丢弃，若要保留包含缺失的数据，则先对缺失值进行填充；所述缺失值的填充方式包括：
    人口属性和体检指标中涉及到的连续变量用均值填充；
    金融消费属性中涉及到的连续变量用0填充；
    各类疾病涉及到的缺失值用0填充；
    其他离散维度用-1填充。
  16. 如权利要求10所述的应用服务器，其特征在于，所述连续变量的离散化包括：对连续变量进行等频或等宽分箱。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有糖尿病分析系统，所述企业推荐程序可被至少一个处理器执行，以使所述至少一个处理器执行以下步骤：
    设置样本范围，包括用户范围和数据维度；
    根据所设置的样本范围，获取相应的样本数据；
    对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析，其中，将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集；及
    输出关联分析结果。
  18. 如权利要求17所述的计算机可读存储介质，其特征在于，在进行所述关联分析之前，所述至少一个处理器还用于执行所述糖尿病分析系统以实现：
    对所述样本数据进行预处理，包括缺失值处理和连续变量的离散化。
  19. 如权利要求18所述的计算机可读存储介质，其特征在于，所述用户范围包括数据来源及采集时间、城市、年龄、性别；所述数据维度包括人口属性、用户是否患有糖尿病及并发症、健康以及非健康因子。
  20. 如权利要求18所述的计算机可读存储介质，其特征在于，所述对所述样本数据中的各个数据维度与糖尿病或并发症的关系进行关联分析的步骤具体包括：
    从样本数据中获取各用户患病情况，包括糖尿病及其并发症；
    将是否患糖尿病或并发症作为关联规则的右项集，其他数据维度作为左项集进行关联分析；
    从结果中筛选出高提升度的规则，对应的左项集因子即为糖尿病或并发症的患病因子。
PCT/CN2018/089429 2017-09-30 2018-06-01 糖尿病分析方法、应用服务器和计算机可读存储介质 WO2019062186A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710916176.5A CN107871536A (zh) 2017-09-30 2017-09-30 糖尿病分析方法及应用服务器
CN201710916176.5 2017-09-30

Publications (1)

Publication Number Publication Date
WO2019062186A1 true WO2019062186A1 (zh) 2019-04-04

Family

ID=61752970

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/089429 WO2019062186A1 (zh) 2017-09-30 2018-06-01 糖尿病分析方法、应用服务器和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN107871536A (zh)
WO (1) WO2019062186A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107871536A (zh) * 2017-09-30 2018-04-03 平安科技（深圳）有限公司 糖尿病分析方法及应用服务器
CN109872783B (zh) * 2018-12-28 2022-11-29 金力 一种基于大数据的糖尿病文献信息标准数据库集分析方法
CN111091566A (zh) * 2020-02-04 2020-05-01 浙江省人民医院 一种糖尿病并发症视网膜病变数据检测方法
CN111710420B (zh) * 2020-05-15 2024-03-19 深圳先进技术研究院 一种基于电子病历大数据的并发症发病风险预测方法、系统、终端以及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050147987A1 (en) * 2000-09-08 2005-07-07 Applera Corporation (Ny) Polymorphisms in known genes associated with type II diabetes and obesity, methods of detection and uses thereof
CN103534703A (zh) * 2011-05-13 2014-01-22 霍夫曼-拉罗奇有限公司 动态数据收集
CN106796240A (zh) * 2014-07-01 2017-05-31 博瑞创新公司 糖尿病性肾病的早期预测标志物
CN107871536A (zh) * 2017-09-30 2018-04-03 平安科技（深圳）有限公司 糖尿病分析方法及应用服务器

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102483818A (zh) * 2009-04-22 2012-05-30 领头马科技股份有限公司 人工智能辅助的医疗参考系统和方法
CN104809118B (zh) * 2014-01-24 2019-06-25 中国移动通信集团公司 一种健康相关数据处理方法、装置及系统
CN105335804A (zh) * 2014-08-06 2016-02-17 北京计算机技术及应用研究所 一种社区卫生服务系统
CN104715013A (zh) * 2015-01-26 2015-06-17 南京邮电大学 一种基于Hadoop的用户健康数据分析方法和系统
CN105938516A (zh) * 2016-04-12 2016-09-14 宁波大红鹰学院 关联规则算法在血液变与中风关系中的应用方法及装置
CN106383920B (zh) * 2016-11-28 2019-11-12 东南大学 一种基于关联规则的重特大交通事故致因识别方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050147987A1 (en) * 2000-09-08 2005-07-07 Applera Corporation (Ny) Polymorphisms in known genes associated with type II diabetes and obesity, methods of detection and uses thereof
CN103534703A (zh) * 2011-05-13 2014-01-22 霍夫曼-拉罗奇有限公司 动态数据收集
CN106796240A (zh) * 2014-07-01 2017-05-31 博瑞创新公司 糖尿病性肾病的早期预测标志物
CN107871536A (zh) * 2017-09-30 2018-04-03 平安科技（深圳）有限公司 糖尿病分析方法及应用服务器

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
CHENG, HUA: "Research on the Application of Data Mining in Diabetes data", INFORMATION & TECHNOLOGY, 15 January 2014 (2014-01-15), pages 14 - 63 *

Also Published As

Publication number Publication date
CN107871536A (zh) 2018-04-03

Similar Documents

Publication Publication Date Title
Belvederi Murri et al. The symptom network structure of depressive symptoms in late-life: results from a European population study
WO2019062186A1 (zh) 糖尿病分析方法、应用服务器和计算机可读存储介质
Lopez-Duran et al. Modeling neuroendocrine stress reactivity in salivary cortisol: adjusting for peak latency variability
Ta et al. Columbia Open Health Data, clinical concept prevalence and co-occurrence from electronic health records
CN108461110B (zh) 医疗信息处理方法、装置及设备
Hagar et al. Survival analysis with electronic health record data: Experiments with chronic kidney disease
Yuan et al. The efficacy and safety of alpha-1 blockers for benign prostatic hyperplasia: an overview of 15 systematic reviews
US20190214147A1 (en) Systems and methods for mining of medical data
Acampa et al. Warranty period of normal stress myocardial perfusion imaging in diabetic patients: A propensity score analysis
WO2020119098A1 (zh) 一种健康评估方法、装置及计算机可读存储介质
US20170286843A1 (en) Data driven featurization and modeling
US20130294676A1 (en) Diagnostic and Prognostic Histopathology System Using Morphometric Indices
Pinto et al. Obstructive sleep apnea in a rural population in South India: feasibility of health care workers to administer level III sleep study
WO2021139112A1 (zh) 数据降维处理方法、装置、计算机设备和存储介质
JP2021507380A (ja) 基準範囲の生成
Néron et al. Screening for depressive symptoms in patients with unresectable lung cancer
Marques et al. Characteristics and outcomes of heart failure hospitalization before implementation of a heart failure clinic: The PRECIC study
JP6038727B2 (ja) 分析システム及び分析方法
Hung et al. Magnitude of score change for the palliative prognostic index for survival prediction in patients with poor prognostic terminal cancer
Chang et al. Morbidity trajectories as predictors of utilization: multi-year disease patterns in Taiwan's national health insurance program
CN115760656A (zh) 一种医学影像处理方法及系统
Nobel et al. Index of cardiometabolic health: a new method of measuring allostatic load using electronic health records
Chuang et al. Predicting clustered dental implant survival using frailty methods
Pandya et al. Modeling the cost effectiveness of neuroimaging-based treatment of acute wake-up stroke
López-Vilella et al. Creatinine and NT-ProBNP levels could predict the length of hospital stay of patients with decompensated heart failure

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18863188

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18863188

Country of ref document: EP

Kind code of ref document: A1