WO2019153580A1 - 一种基于心电信号的糖尿病病情评估方法及系统 - Google Patents

一种基于心电信号的糖尿病病情评估方法及系统 Download PDF

Info

Publication number
WO2019153580A1
WO2019153580A1 PCT/CN2018/088431 CN2018088431W WO2019153580A1 WO 2019153580 A1 WO2019153580 A1 WO 2019153580A1 CN 2018088431 W CN2018088431 W CN 2018088431W WO 2019153580 A1 WO2019153580 A1 WO 2019153580A1
Authority
WO
WIPO (PCT)
Prior art keywords
diabetes
signal
condition
electrocardiographic signal
electrocardiographic
Prior art date
Application number
PCT/CN2018/088431
Other languages
English (en)
French (fr)
Inventor
王新安
李冉
刘彦伶
赵天夏
李秋平
陈红英
何春舅
马浩
孙贺
Original Assignee
北京大学深圳研究生院
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 北京大学深圳研究生院 filed Critical 北京大学深圳研究生院
Publication of WO2019153580A1 publication Critical patent/WO2019153580A1/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
    • 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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the invention relates to a method for assessing diabetes condition, in particular to a method and system for assessing diabetes condition based on an electrocardiographic signal.
  • Diabetes is a chronic metabolic disease that can be disabling and lethal. Its severity and risk assessment are a concern for people with diabetes and their families. Diabetes is closely related to lifestyle. At present, unless the condition is serious, most of the time patients are in the community and at home, so the control of diabetes depends largely on patient self-management. In addition to regular admission to check glycosylated hemoglobin, liver and kidney function, degree of retinal damage, weight, blood pressure, heart condition, through monitoring means to understand their physical condition, preliminary self-assessment, and timely medical treatment, is an important part of self-management of diabetes patients .
  • the daily health management of diabetic patients mainly depends on self-test blood glucose. By monitoring his own blood sugar, he only evaluates his own blood glucose regulation ability. When he finds that blood sugar regulation cannot be controlled by drugs at home, he is admitted to hospital in time.
  • many diabetic patients also have a variety of cardiovascular risk factors such as hypertension, hyperlipidemia, and hyperuricemia. The more these risk factors, the higher the risk of diabetic complications. Because diabetes can cause damage to many organs such as heart, brain, kidney, eye, nerves, limbs, etc., various chronic complications of diabetes are the main causes of disability and death in diabetic patients.
  • the technical problem mainly solved by the present invention is that the current diabetes condition assessment mainly adopts a blood glucose self-test method, and the detection parameters of the method are single, invasive, poor user experience, and high in cost.
  • the present invention provides a method for assessing diabetes condition based on an electrocardiographic signal, comprising: acquiring an electrocardiogram signal; and obtaining a corresponding diabetes condition evaluation result according to the ECG signal.
  • the present invention also provides a diabetes condition evaluation system based on an electrocardiographic signal, comprising: an electrocardiographic signal acquisition device for collecting an electrocardiogram signal of a subject to be detected; and a processor for performing the method as described above .
  • the invention also provides a computer readable storage medium comprising a program executable by a processor to implement the method as described above.
  • the invention adopts an electrocardiographic signal-based diabetes disease evaluation method and system, which can non-invasively evaluate diabetes disease condition and development trend compared with the prior art, has good user experience, low cost and easy operation, and is convenient for diabetic patients to achieve control disease development. Even delaying the development of the disease.
  • FIG. 1 is a schematic diagram of a diabetes condition assessment system based on an electrocardiographic signal
  • FIG. 2 is a flow chart of a method for assessing diabetes based on an electrocardiographic signal
  • FIG. 3 is a flow chart of a method for establishing a model function corresponding to a characteristic index of an electrocardiographic signal and a diabetic condition.
  • a diabetes condition assessment system based on an electrocardiogram signal includes:
  • ECG signal collecting device A00 used to collect the ECG signal of the person to be detected
  • the processor A01 is configured to obtain a corresponding diabetes condition evaluation result according to the acquired ECG signal.
  • the processor A01 obtains the corresponding diabetes condition evaluation result according to the ECG signal, and calculates one or more characteristic indicators of the ECG signal according to the ECG signal, and obtains the corresponding diabetes according to the characteristic index of the ECG signal.
  • the results of the disease assessment may pre-establish a model function corresponding to the characteristic index of the electrocardiographic signal and the diabetic condition, and input the characteristic index of the electrocardiographic signal into the model function to obtain a corresponding diabetes condition evaluation result.
  • the processor A10 obtains the physiological parameters of the diabetic patient in different stages of the disease, and the ECG signals before the corresponding time points when the physiological parameters are collected; acquires the characteristic indexes of the ECG signals; and sets the characteristic indexes of the ECG signals, And the physiological parameters corresponding to the electrocardiographic signals are used as inputs, and machine learning is performed to obtain a model function corresponding to the characteristic index of the electrocardiographic signal and the diabetic condition.
  • the processor A10 can also obtain the diabetes condition evaluation results corresponding to the multiple time points according to the ECG signals obtained at multiple time points, and record and analyze the evaluation results for evaluating the development trend of the diabetes condition.
  • the processor A10 obtains a corresponding diabetes condition evaluation result based on the electrocardiographic signal, mainly based on the RR interval sequence of the electrocardiographic signal, wherein the RR interval refers to a time interval between adjacent R peaks and R peaks in the ECG signal waveform.
  • the RR interval sequence includes all RR intervals in a segment of the ECG signal.
  • the processor A10 calculates the feature index by the ECG signal, including: performing linear analysis on the pRRx sequence of the ECG signal to obtain one or more linear feature indicators, and/or performing nonlinear analysis to obtain One or more non-linear characteristic indicators.
  • the pRRx sequence of any one of the ECG signals is calculated by calculating a ratio of the number of adjacent RR intervals in the segment of the ECG signal that is greater than the threshold x milliseconds to the number of all RR intervals, and the setting values are different.
  • the threshold x is obtained as a ratio corresponding to each threshold x, and these ratios constitute the pRRx sequence. In this embodiment, the ratio is expressed as a percentage, as shown in equation (1):
  • One or more characteristic indicators can be obtained by performing linear analysis and/or nonlinear analysis based on the pRRx sequence of the electrocardiographic signal.
  • the characteristic indicators obtained by the linear analysis may include: the mean AVRR of the pRRx sequence, the standard deviation SDRR of the pRRx sequence, the root mean square rMSSD of the adjacent pRRx difference in the pRRx sequence, and the standard deviation SDSD of the adjacent pRRx difference in the pRRx sequence. .
  • the available metrics include:
  • the pRRx sequence histogram distribution information entropy S dh is the numerical distribution information entropy of the pRRx sequence
  • pRRx sequence power spectrum histogram distribution information entropy S ph is a discrete Fourier transform of the pRRx sequence to obtain the power spectrum, and then calculate its information entropy according to the numerical distribution of the power spectrum sequence;
  • pRRx sequence power spectrum full-band distribution information entropy S pf is a discrete Fourier transform of the pRRx sequence to obtain the power spectrum in the full frequency band [f s /N, f s /2] (the sampling frequency of the signal is f s The number of sampling points is N).
  • the i-1 sub-points f 1 , f 2 , . . . , f m-1 are inserted, and the full frequency band is divided into i sub-bands. Taking the sum of the power densities in each band as the power density of the band, m power densities are obtained.
  • AVE ( ⁇ ) represents the average, and ⁇ represents the two-point distance.
  • the correlation function is a power type. Since there is no feature length, the distribution is fractal, and there is C( ⁇ ) ⁇ - ⁇ . At this time, the function curve of logC( ⁇ )-log ⁇ is drawn, and linear fitting is performed in the scale-free region to obtain the slope ⁇ .
  • the conversion relationship between the fractal dimension D cf and the slope ⁇ is as shown in equation (7):
  • the ECG signal characteristic index for performing the diabetes condition evaluation result is one or more of the above-mentioned linear and/or non-linear analysis characteristic indexes, or a set of several of them, or may be listed in addition to the present embodiment. Corresponding feature indicators obtained from existing analytical methods.
  • Input device A02 connected to the processor signal for receiving input information of the user.
  • the housing A03 the housing encloses a receiving cavity, and the processor A01 and the input device A02 are at least partially received in the receiving cavity of the housing A03, and the housing A03 is provided with a display area.
  • the display device A04 is connected to the display area and the processor A01 signal, and displays the diabetes condition and/or the diabetes condition trend evaluation result according to the instructions of the input device A02 and the processor A01.
  • Memory A05 Connected to processor A01 for storing programs, diabetes assessment results, and diabetes progression assessment results.
  • a diabetic patient is 65 years old with type 2 diabetes, fasting blood glucose 8.5 millimoles per liter, blood glucose 14.2 millimoles per liter after breakfast, glycated hemoglobin (HbA1c) 8.5%; body mass index 29 (low At 24 is normal), abdominal obesity, blood pressure is 165/100 mm Hg (high blood pressure), triacylglycerol is 4.8 mmol/L, and low-density lipoprotein-cholesterol (LDL-C) is 4.5 mmol/L , high-density lipoprotein-cholesterol (HDL-C) 0.85 mmol / liter (lipid metabolism disorder), blood uric acid was 580 mmol / liter (hyperuricemia), normal fundus, 24-hour urine microalbumin quantitation 210 mg / 24 hours (increased), normal liver function, normal ECG.
  • HbA1c glycated hemoglobin
  • the patient's comprehensive diabetes assessment results in type 2 diabetes and early diabetic nephropathy, accompanied by high-risk conditions of cardiovascular disease.
  • the patient can collect the ECG signal at different times through the ECG signal collecting device A00, and complete the diabetes disease evaluation result and record at the corresponding time point through the A01 processor and the A05 memory, thereby performing the diabetes disease development of the patient.
  • the trend evaluation receiving the patient instruction through the input device A02, with the support of the display device A04, conveniently and accurately obtaining the obtained diabetes condition evaluation result through the display area on the housing A03, and the corresponding diabetes disease development trend evaluation result.
  • the results can be used for self-health management in diabetic patients, including: fully discussing the individualized diabetes disease control goals with the doctor; reviewing the daily diabetes condition monitoring and trend results with the doctor; explaining and communicating the daily diabetes condition with the doctor; according to the diabetes condition And doctors feedback positively change the behavior of daily life, so as to achieve the goal of controlling the development of diabetes, and even delay the development of the disease.
  • the processor A10 adopts the electrocardiographic signal-based diabetes condition evaluation method shown in FIG. 2, which is low in cost, safe and effective, and specifically includes steps B00 to B10, and is specifically described below:
  • step B10 includes: calculating one or more characteristic indicators of the electrocardiographic signal according to the electrocardiographic signal, and obtaining a corresponding diabetes condition evaluation result according to the characteristic index of the electrocardiographic signal.
  • the characteristic index of the electrocardiographic signal and the calculation method of the diabetes condition evaluation result are as described above.
  • the model function of the correspondence between the characteristic index of the electrocardiogram signal and the diabetic condition may be established in advance, and the characteristic index of the ECG signal is set. Enter the model function to get the corresponding diabetes assessment results.
  • the B10 step can be used to establish a model function of the correspondence between the characteristic index of the electrocardiographic signal and the diabetic condition through machine learning, as shown in FIG.
  • the B10 step establishes the above model function, which may include steps B11 to B13, which are specifically described below.
  • the physiological parameters of the diabetic patient at different stages of the disease are acquired in advance, and the ECG signal before the corresponding time point when the physiological parameter is collected.
  • the physiological parameters of the diabetic patient in different stages of the disease are obtained in advance, such as: blood sugar level, body mass index, blood pressure value, cholesterol, blood uric acid, type of disease, stage, number and severity of complications, etc.;
  • the method of physiological parameters may adopt a method with high precision commonly used in the prior art.
  • the time length of the ECG signal required by each sampler is not the same. The actual modeling effect is correct.
  • the ECG signals of different lengths of 1 to 30 minutes are selected.
  • the electrocardiogram signal of the person to be detected obtained in the step B00 is input into the model function, and the diabetes condition evaluation result can be obtained.
  • the diabetes patient assessment result of the same patient at multiple time points can also be obtained according to the above method, and can be recorded in a table and further analyzed to obtain an evaluation result of the patient's diabetes development trend.
  • the program may be stored in a computer readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc.
  • the computer executes the program to implement the above functions.
  • the program is stored in the memory of the device, and when the program in the memory is executed by the processor, all or part of the above functions can be realized.
  • the program may also be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk or a mobile hard disk, and may be saved by downloading or copying.
  • the system is updated in the memory of the local device, or the system of the local device is updated.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本发明公开了一种基于心电信号的糖尿病病情评估方法及系统，通过获取心电信号，及获取对应心电信号的特征指标，并得到心电信号的特征指标与糖尿病病情对应关系的模型函数；通过获取心电信号，计算并根据心电信号的特征指标，通过所述模型函数，得到糖尿病病情评估结果。系统也可以获取多个心电信号，得到多个糖尿病病情评估结果，对这些结果进行记录和分析，获取糖尿病病情发展趋势评估结果，用于糖尿病患者的日常病情监测和控制。相比现有技术，本发明可以通过无创方法评估糖尿病病情及发展趋势，用户体验好、成本低、易操作，便于糖尿病患者实现控制病情发展，甚至于延缓病情发展的目标。

Description

一种基于心电信号的糖尿病病情评估方法及系统 技术领域
本发明涉及糖尿病病情评估方法，具体涉及一种基于心电信号的糖尿病病情评估方法及系统。
背景技术
糖尿病是一种可以致残、致死的慢性代谢性疾病，其病情轻重及风险评估是糖尿病患者及其家人都十分关注的一个问题。糖尿病与生活方式密切相关，目前除非病情严重，多数时间患者是在社区和家中，因此糖尿病的控制很大程度上依靠患者自我管理。除去定期入院检查糖化血红蛋白、肝肾功能、视网膜受损程度、体重、血压、心脏情况，通过监测手段了解自己的身体状况，初步进行自我评估，从而及时就医治疗，是糖尿病患者自我管理的重要环节。
现有技术中，糖尿病患者日常的健康管理主要依赖于自测血糖。通过对自身的血糖进行监测，仅对自身的血糖调节能力进行评估，当发现血糖的调节无法在家中通过药物控制时，及时入院治疗。但是，除了血糖高外，许多糖尿病患者还同时合并高血压、高血脂、高尿酸血症等多种心血管危险因素，这些危险因素越多，糖尿病并发症的风险就越高。因为糖尿病可造成心、脑、肾、眼、神经、肢体等多器官损害，糖尿病的各种慢性并发症是导致糖尿病患者致残和死亡的主要原因。
发明内容
本发明主要解决的技术问题是目前糖尿病病情评估主要是采用血糖自测方法，该方法检测参数单一、有创、用户体验差、成本高。
为解决上述技术问题，本发明提出一种基于心电信号的糖尿病病情评估方法，包括：获取心电信号；根据所述心电信号，获取对应的糖尿病病情评估结果。
另一方面，本发明还提出一种基于心电信号的糖尿病病情评估系统，包括：心电信号采集装置，用于采集待检测者的心电信号；处理器，用 于执行如上所述的方法。
另一方面，本发明还提出一种计算机可读存储介质，包括程序，所述程序能够被处理器执行以实现如上所述的方法。
本发明采用的一种基于心电信号的糖尿病病情评估方法及系统，相比现有技术，可以无创评估糖尿病病情及发展趋势，用户体验好、成本低、易操作，便于糖尿病患者实现控制病情发展，甚至于延缓病情发展的目标。
附图说明
图1为一种基于心电信号的糖尿病病情评估系统示意图；
图2为一种基于心电信号的糖尿病病情评估方法流程图；
图3为一种心电信号的特征指标与糖尿病病情对应关系的模型函数建立方法流程图。
具体实施方式
下面通过具体实施方式结合附图对本发明作进一步详细说明。其中不同实施方式中类似元件采用了相关联的类似的元件标号。在以下的实施方式中，很多细节描述是为了使得本申请能被更好的理解。然而，本领域技术人员可以毫不费力的认识到，其中部分特征在不同情况下是可以省略的，或者可以由其他元件、材料、方法所替代。在某些情况下，本申请相关的一些操作并没有在说明书中显示或者描述，这是为了避免本申请的核心部分被过多的描述所淹没，而对于本领域技术人员而言，详细描述这些相关操作并不是必要的，他们根据说明书中的描述以及本领域的一般技术知识即可完整了解相关操作。
另外，说明书中所描述的特点、操作或者特征可以以任意适当的方式结合形成各种实施方式。同时，方法描述中的各步骤或者动作也可以按照本领域技术人员所能显而易见的方式进行顺序调换或调整。因此，说明书和附图中的各种顺序只是为了清楚描述某一个实施例，并不意味着是必须的顺序，除非另有说明其中某个顺序是必须遵循的。
本文中为部件所编序号本身，例如“第一”、“第二”等，仅用于区分所描述的对象，不具有任何顺序或技术含义。而本申请所说“连接”、 “联接”，如无特别说明，均包括直接和间接连接(联接)。
本发明实施例一：请参照图1，一种基于心电信号的糖尿病病情评估系统包括：
心电信号采集装置A00：用于采集待检测者的心电信号；
处理器A01：用于根据获取的心电信号，获取对应的糖尿病病情评估结果。另一方面，处理器A01根据心电信号，获取对应的糖尿病病情评估结果包括：根据心电信号，计算心电信号的一个或多个特征指标，根据心电信号的特征指标，获取对应的糖尿病病情评估结果。此外，处理器A01可以预先建立心电信号的特征指标与糖尿病病情对应关系的模型函数，将心电信号的特征指标输入模型函数，得到对应的糖尿病病情评估结果。处理器A10通过预先获取不同病情阶段糖尿病患者的生理参数，以及采集所述生理参数时对应的时间点之前的心电信号；获取这些心电信号的特征指标；将这些心电信号的特征指标，以及这些心电信号对应的生理参数作为输入，进行机器学习，得到心电信号的特征指标与糖尿病病情对应关系的模型函数。处理器A10还可以根据获取多个时间点的心电信号，获得对应多个时间点的糖尿病病情评估结果，对这些评估结果进行记录和分析，用于评估糖尿病病情发展趋势。
其中，处理器A10基于心电信号得到对应的糖尿病病情评估结果，主要基于心电信号的RR间隔序列，所述RR间隔是指心电信号波形中相邻的R峰和R峰之间的时间间隔，RR间隔序列包括一段心电信号中的所有RR间隔。
在一实施例中，处理器A10通过心电信号计算特征指标，包括：对心电信号的pRRx序列进行线性分析以得到一个或多个线性的特征指标，和/或进行非线性分析，以得到一个或多个非线性的特征指标。其中任意一段心电信号的pRRx序列通过以下方式计算得到：计算该段心电信号中相邻RR间期之差大于阈值x毫秒的数量与全部RR间期的数量的比值，通过设置值不同的阈值x，得到每一个阈值x对应的比值，这些比值构成了所述pRRx序列。在本实施例中，该比值用百分比表示，如式(1)所示：
Figure PCTCN2018088431-appb-000001
根据所述心电信号的pRRx序列进行线性分析和/或非线性分析，可以得到一个或多个特征指标。
例如，线性分析获得的特征指标可以包括：pRRx序列的均值AVRR、pRRx序列的标准差SDRR、pRRx序列中相邻pRRx差值的均方根rMSSD、pRRx序列中相邻pRRx差值的标准差SDSD。
对每段心电信号的pRRx序列进行非线性分析，采用熵值分析法，即：根据现有技术，对于概率分布函数p(x)的随机变量集A，熵的定义如式(2)所示：
H(A)＝-∑p A(x)logp A(x)         (2)
可以获得的特征指标包括：
(1)pRRx序列直方分布信息熵S dh是对pRRx序列的数值分布信息熵；
(2)pRRx序列功率谱直方分布信息熵S ph是对pRRx序列进行离散傅里叶变换得到功率谱，然后根据功率谱序列的数值分布计算其信息熵；
(3)pRRx序列功率谱全频段分布信息熵S pf是对pRRx序列进行离散傅里叶变换得到功率谱，在全频段[f s/N,f s/2](信号的采样频率为f s，采样点数为N)内插入i-1个分点f 1，f 2，…，f m-1，将全频段分割成i个子频段。把每个频段内的功率密度之和作为该频段的功率密度，则得到m个功率密度。将这i个功率密度归一化得到每个频段出现的概率p i，则∑ ip i＝1，相应的功率谱全频段熵如式(3)所示：
Figure PCTCN2018088431-appb-000002
对每段心电信号的pRRx序列进行非线性分析，也可以采用下面四种分形维数计算分析方法可以得到如下的特征指标：
(1)结构函数法计算所得的分形维数D sf，其中，结构函数法是指对于给定的序列z(x)，定义增量方差为结构函数，其关系为：
Figure PCTCN2018088431-appb-000003
对于若干个标度τ，对序列z(x)的离散值计算出相应的S(τ)，然后画出logS(τ)-logτ的函数曲线，在无标度区进行线性拟合，得到斜率α，则对应分形维数D sf与斜率α的转化关系如式(5)所示：
Figure PCTCN2018088431-appb-000004
(2)相关函数法计算所得的分形维数D cf，其中，相关函数法是指
对于给定的序列z(x)，相关函数C(τ)定义为式(6)所示：
C(τ)＝AVE(z(x+τ)*z(x))，τ＝1,2,3,K,N-1         (6)
其中，AVE(·)表示平均，τ表示两点距离。此时相关函数为幂型，由于不存在特征长度，则分布为分形，有C(τ)ατ -α。这时，画出logC(τ)-logτ的函数曲线，在无标度区进行线性拟合，得到斜率α，则对应分形维数D cf与斜率α的转化关系如式(7)所示：
D cf＝2-α                (7)
(3)变差法计算所得的分形维数D vm，其中，变差法用宽为τ的矩形框首尾相接的将分形曲线覆盖起来，令第i个框内曲线的最大值和最小值之差为H(i)，即为矩形的高度。将所有矩形的高和宽相乘得到总面积S(τ)。改变τ的大小，得到一系列的S(τ)。如式(8)所示：
Figure PCTCN2018088431-appb-000005
画出logN(τ)-logτ的函数曲线，在无标度区进行线性拟合得到斜率α，则对应分形维数D vm与斜率α的转化关系如式(7)所示。
(4)均方根法计算所得的分形维数D rms，其中，均方根法用宽为τ的矩形框首尾相接的将分形曲线覆盖起来，令第i个框内曲线的最大值和最小值之差为H(i)，即为矩形的高度。计算这些矩形高度的均方根值S(τ)。改变τ的大小，得到一系列的S(τ)。画出logS(τ)-logτ的函数曲线，在无标度区进行线性拟合得到斜率α，则对应分形维数D rms与斜率α的转化关系如式(7)所示。
用于进行糖尿病病情评估结果的心电信号特征指标是上述线性和/或非线性分析得到的特征指标中的一个、多个，或者是其中几个的集合，也可以是除本实施例所罗列之外的现有分析方法所得到的相应特征指 标。
输入装置A02：与处理器信号相连，用于接收用户的输入信息。
壳体A03：所述壳体围合形成容纳腔，处理器A01和输入装置A02至少部分地收容于壳体A03的容纳腔中，所述壳体A03上设有一显示区域。
显示装置A04：与显示区域和处理器A01信号相连，并根据输入装置A02和处理器A01的指令显示糖尿病病情和/或糖尿病病情趋势评估结果。
存储器A05：与处理器A01信号相连，用于存储程序、糖尿病病情评估结果和糖尿病病情趋势评估结果。
在一实施例中，一名糖尿病患者65岁，有2型糖尿病，空腹血糖8.5毫摩/升，早餐后2小时血糖14.2毫摩/升，糖化血红蛋白(HbA1c)8.5％；体重指数29(低于24为正常)，腹型肥胖，血压为165/100毫米汞柱(血压高)，三酰甘油为4.8毫摩/升，低密度脂蛋白-胆固醇为(LDL-C)4.5毫摩/升，高密度脂蛋白-胆固醇为(HDL-C)0.85毫摩/升(脂代谢紊乱)，血尿酸为580毫摩/升(高尿酸血症)，眼底正常，24小时尿微量白蛋白定量为210毫克/24小时(增高)，肝功能正常，心电图正常。这位患者综合的糖尿病病情评估结果为2型糖尿病及早期糖尿病肾病，同时伴随心血管病的高危情况。具体在本实施例中，患者可以通过心电信号采集装置A00在不同时间采集心电信号，通过A01处理器和A05存储器，完成对应时间点的糖尿病病情评估结果和记录，从而进行患者糖尿病病情发展的趋势评估，通过输入装置A02接收患者指令，在显示装置A04的支持下，通过壳体A03上的显示区域方便准确的获取所得的糖尿病病情评估结果，以及相应的糖尿病病情发展趋势评估结果。该结果可以用于糖尿病患者进行自我健康管理，包括：与医生充分讨论个体化糖尿病病情控制目标；与医生共同回顾日常糖尿病病情监测和趋势结果；与医生一起解释和交流日常糖尿病病情；根据糖尿病病情和医生反馈积极改变日常生活行为，从而实现控制糖尿病病情发展，甚至于延缓病情发展的目标。
在本实施例中，处理器A10采用了图2所示的基于心电信号的糖尿病病情评估方法，该方法成本低、安全有效，具体包括B00步骤～B10步骤，下面具体说明：
B00：获取多个时间段的心电信号。
B10：根据所述心电信号，获取对应的糖尿病病情评估结果。
在一实施例中，步骤B10包括：根据心电信号，计算心电信号的一个或多个特征指标，根据心电信号的特征指标，获取对应的糖尿病病情评估结果。其中，心电信号的特征指标和糖尿病病情评估结果的计算方法如上所述。
在一实施例中，步骤B10在根据心电信号的特征指标来获取对应糖尿病病情评估结果时，可以预先建立心电信号的特征指标与糖尿病病情对应关系的模型函数，将心电信号的特征指标输入模型函数，得到对应糖尿病病情评估结果。例如，B10步骤可以通过机器学习，来建立心电信号的特征指标与糖尿病病情对应关系的模型函数，请参照图3所示。
如图3所示，B10步骤建立上述模型函数，可以包括B11～B13步骤，下面具体说明。
B11：预先获取不同病情阶段糖尿病患者的生理参数，以及采集所述生理参数时对应的时间点之前的心电信号。其中，所述预先获取不同病情阶段糖尿病患者的生理参数，例如：血糖值、体重指数、血压值、胆固醇、血尿酸、疾病类型、阶段、并发症数量及严重程度等；这个步骤中所述获取生理参数的方法可以采用现有技术中常用的、精准度高的方法，同时，对应每个患者生理参数的获取，需要采集生理参数时间点之前对应的心电信号，由于个体新陈代谢情况存在差异，每个采样者所需的心电信号时间长度并不相同，以实际建模效果为准，本实施例选取1～30分钟不同时间长度的心电信号。
B12：获取这些心电信号的特征指标。
B13：将这些心电信号的特征指标，以及这些心电信号对应的生理参数作为输入，进行机器学习，得到心电信号的特征指标与糖尿病病情对应关系的模型函数。
根据上述步骤得到心电信号的特征指标与糖尿病病情对应关系的模型函数后，再将B00步骤所获取待检测者的心电信号输入该模型函数，即可得到糖尿病病情评估结果。
在一实施例中，还可以根据上述方法得到同一患者在多个时间点的糖尿病病情评估结果，可以进行表格记录以及进一步分析，获得患者糖尿病病情发展趋势的评估结果。
本领域技术人员可以理解，上述实施方式中各种方法的全部或部分功能可以通过硬件的方式实现，也可以通过计算机程序的方式实现。当上述实施方式中全部或部分功能通过计算机程序的方式实现时，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：只读存储器、随机存储器、磁盘、光盘、硬盘等，通过计算机执行该程序以实现上述功能。例如，将程序存储在设备的存储器中，当通过处理器执行存储器中程序，即可实现上述全部或部分功能。另外，当上述实施方式中全部或部分功能通过计算机程序的方式实现时，该程序也可以存储在服务器、另一计算机、磁盘、光盘、闪存盘或移动硬盘等存储介质中，通过下载或复制保存到本地设备的存储器中，或对本地设备的系统进行版本更新，当通过处理器执行存储器中的程序时，即可实现上述实施方式中全部或部分功能。
以上应用了具体个例对本发明进行阐述，只是用于帮助理解本发明，并不用以限制本发明。对于本发明所属技术领域的技术人员，依据本发明的思想，还可以做出若干简单推演、变形或替换。

Claims (10)

  1. 一种基于心电信号的糖尿病病情评估方法，其特征在于，包括：
    获取心电信号；
    根据所述心电信号，获取对应的糖尿病病情评估结果。
  2. 如权利要求1所述方法，其特征在于，所述根据心电信号，获取对应的糖尿病病情评估结果包括：根据心电信号，计算心电信号的一个或多个特征指标，根据心电信号的特征指标，获取对应的糖尿病病情评估结果。
  3. 如权利要求2所述方法，其特征在于，包括：预先建立心电信号的特征指标与糖尿病病情对应关系的模型函数，将心电信号的特征指标输入模型函数，得到对应的糖尿病病情评估结果。
  4. 如权利要求2或3所述方法，其特征在于，心电信号的特征指标，包括：对心电信号的pRRx序列进行线性分析以得到一个或多个线性的特征指标，和/或进行非线性分析，以得到一个或多个非线性的特征指标；其中任意一段心电信号的pRRx序列通过以下方式计算得到：计算该段心电信号中相邻RR间期之差大于阈值x毫秒的数量与全部RR间期的数量的比值，通过设置值不同的阈值x，得到每一个阈值x对应的比值，这些比值构成了所述pRRx序列。
  5. 如权利要求4所述方法，其特征在于，心电信号的特征指标，还包括：
    所述线性分析获得的特征指标：pRRx序列的均值AVRR、pRRx序列的标准差SDRR、pRRx序列中相邻pRRx差值的均方根rMSSD、pRRx序列中相邻pRRx差值的标准差SDSD中的至少一者；和/或，
    所述非线性的特征指标包括对所述pRRx序列进行熵值分析法所得到的特征指标，包括：pRRx序列直方分布信息熵S dh、pRRx序列功率谱直方分布信息熵S ph、pRRx序列功率谱全频段分布信息熵S pf中的至少一者；和/或，所述非线性的特征指标包括所述pRRx序列进行分形维数计算分析所得到的特征指标，包括：结构函数法计算所得的分形维数D sf、相关函数法计算所得的分形维数D cf、变差法计算所得的分形维数D vm、均方根法计算所得的分形维数D rms中的至少一者。
  6. 如权利要求3所述方法，其特征在于，所述预先建立心电信号的特征指标与糖尿病病情对应关系的模型函数，包括：
    预先获取不同病情阶段糖尿病患者的生理参数，以及采集所述生理参数时对应的时间点之前的心电信号；
    获取这些心电信号的特征指标；
    将这些心电信号的特征指标，以及这些心电信号对应的生理参数作为输入，进行机器学习，得到心电信号的特征指标与糖尿病病情对应关系的模型函数。
  7. 如权利要求1所述方法，其特征在于，包括：获取多个时间点的心电信号，可以获得对应多个时间点的糖尿病病情评估结果，对这些评估结果进行记录和分析，可以用于评估糖尿病病情发展趋势。
  8. 一种基于心电信号的糖尿病病情评估系统，其特征在于，包括：
    心电信号采集装置，用于采集待检测者的心电信号；
    处理器，用于执行如权利要求1-7中任一项所述的方法。
  9. 如权利要求8所述系统，其特征在于，还包括：
    输入装置，与处理器信号相连，用于接收用户的输入信息；
    壳体，所述壳体围合形成容纳腔，处理器和输入装置至少部分地收容于壳体的容纳腔中，所述壳体上设有一显示区域；
    显示装置，与显示区域和处理器信号相连，并根据输入装置和处理器的指令将糖尿病病情和/或糖尿病病情趋势评估结果发送到显示区域进行显示；
    存储器，与处理器信号相连，用于存储程序、糖尿病病情评估结果和糖尿病病情趋势评估结果。
  10. 一种计算机可读存储介质，其特征在于，包括程序，所述程序能够被处理器执行以实现如权利要求1-7中任一项所述的方法。
PCT/CN2018/088431 2018-02-06 2018-05-25 一种基于心电信号的糖尿病病情评估方法及系统 WO2019153580A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810119313.7 2018-02-06
CN201810119313.7A CN108461146B (zh) 2018-02-06 2018-02-06 一种基于心电信号的糖尿病病情评估方法及系统

Publications (1)

Publication Number Publication Date
WO2019153580A1 true WO2019153580A1 (zh) 2019-08-15

Family

ID=63239747

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/088431 WO2019153580A1 (zh) 2018-02-06 2018-05-25 一种基于心电信号的糖尿病病情评估方法及系统

Country Status (2)

Country Link
CN (1) CN108461146B (zh)
WO (1) WO2019153580A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110875094B (zh) * 2018-08-31 2024-01-30 福州依影健康科技有限公司 糖尿病的健康生活方式激励方法和系统、及存储设备
CN112741623B (zh) * 2020-12-09 2022-09-27 中国科学院深圳先进技术研究院 一种基于心电的糖化血红蛋白检测系统和方法
CN116491938B (zh) * 2023-06-27 2023-10-03 亿慧云智能科技（深圳）股份有限公司 一种ecg无创血糖测量方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5741211A (en) * 1995-10-26 1998-04-21 Medtronic, Inc. System and method for continuous monitoring of diabetes-related blood constituents
WO2015168652A1 (en) * 2014-05-01 2015-11-05 Worcester Polytechnic Institute Detection and monitoring of atrial fibrillation
CN105380640A (zh) * 2015-10-28 2016-03-09 广东小天才科技有限公司 一种发送求救信号的方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105193431B (zh) * 2015-09-02 2017-12-01 杨静 一种人体精神压力状态分析装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5741211A (en) * 1995-10-26 1998-04-21 Medtronic, Inc. System and method for continuous monitoring of diabetes-related blood constituents
WO2015168652A1 (en) * 2014-05-01 2015-11-05 Worcester Polytechnic Institute Detection and monitoring of atrial fibrillation
CN105380640A (zh) * 2015-10-28 2016-03-09 广东小天才科技有限公司 一种发送求救信号的方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MUSALE, R. ET AL.: "Design and develop an algorithm for a diabetic detection using ECG signal", PROCEEDINGS OF THE IEEE 2017 INTERNATIONAL CONFERENCE ON COMPUTING METHODOLOGIES AND COMMUNICATION, 31 December 2017 (2017-12-31), XP033315249, DOI: 10.1109/ICCMC.2017.8282610 *

Also Published As

Publication number Publication date
CN108461146A (zh) 2018-08-28
CN108461146B (zh) 2019-12-03

Similar Documents

Publication Publication Date Title
US10262111B2 (en) Systems for safe and remote outpatient ECG monitoring
US20200205734A1 (en) Ear-Based Physiological State Monitoring
US9220437B2 (en) Diagnostic classifications of pulse signal waveform data
US20030117296A1 (en) Method and apparatus for multiple patient parameter variability analysis and display
WO2019153580A1 (zh) 一种基于心电信号的糖尿病病情评估方法及系统
CN108652614B (zh) 一种心血管疾病病情评估方法及系统
WO2019153578A1 (zh) 一种基于心电信号的无创血糖检测方法及系统
CN115804573A (zh) 一种睡眠深度量化及干预的方法、系统和装置
CN108403107A (zh) 一种心律失常判别方法及系统
US20110177956A1 (en) Method and system of predicting clinical outcome for a patient with congestive heart failure
WO2019153579A1 (zh) 一种基于心电信号的无气囊血压检测方法及系统
Maestri et al. Reliability of heart rate variability measurements in patients with a history of myocardial infarction
Yamanaka et al. Calibration-free cuffless blood pressure estimation based on a population with a diverse range of age and blood pressure
CN109171694B (zh) 一种基于脉搏信号的糖尿病病情评估方法及系统
Georgieva-Tsaneva et al. Cardio-diagnostic assisting computer system
Cuadros et al. ECG multilead QT interval estimation using support vector machines
Zhou et al. A new functional data‐based biomarker for monitoring cardiovascular behavior
Iqbal et al. Real-time signal processing of data from an ECG
Alramadeen et al. Multi-level multi-channel bio-signal analysis for health telemonitoring
CN116189899B (zh) 一种基于机器学习的急危重症辅助评估系统
Braga et al. A knowledge based home monitoring system for management and rehabilitation of cardiovascular patients
WO2003079894A1 (en) Method of analysis of circadian rhythms
Krluku et al. Detection of uninterpretable ECG signal segments
CN109390054A (zh) 用于推测心房颤动的心跳讯号分析系统、方法及可读媒体
Herry et al. Continuous multiorgan variability monitoring in critically ill patients: complexity science at the bedside

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: 18905034

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18905034

Country of ref document: EP

Kind code of ref document: A1