TWI876945B - Diabetes detection system and detection method thereof - Google Patents

Abstract

A diabetes detection system and a detection method thereof are provided. The diabetes detection system consists of a basic physiological sampling module, a processing module, a matching module, and a database. The basic physiological sampling module is used to sample a person to obtain target physiological data. The processing module electrically couples with the basic physiological sampling module and filters the target physiological data using statistical and signal processing methods to generate processed data. The matching module electrically couples with the processing module and the database. It retrieves symptom data with diabetes characteristics from the database and compares the processed data against the symptom data. When the symptom data matches the processed data, the matching module sends out a notification signal.

Description

Diabetes detection system and detection method thereof

The present invention relates to a detection system, and more particularly to a diabetes detection system and a detection method thereof.

The traditional method of diabetes testing is to use an invasive method to obtain blood to identify whether the subject has symptoms of diabetes (e.g., blood sugar concentration). However, diabetes testing is frequent, which also requires the subject to frequently inflict wounds. For this reason, existing diabetes testing systems use light to illuminate the blood vessels in the skin to detect changes in the blood vessels to identify whether there are signs of diabetes. Although existing diabetes testing systems can achieve "non-invasive" testing, optical detection methods have many noise problems, resulting in inaccurate test results.

Therefore, the inventors of the present invention believe that the above defects can be improved, and have conducted intensive research and applied scientific principles to finally propose the present invention which has a reasonable design and effectively improves the above defects.

The technical problem to be solved by the present invention is to provide a diabetes detection system and a detection method thereof in view of the deficiencies of the prior art.

The present invention discloses a diabetes detection system, including: a basic physiological sampling module, which can be used to sample a person to obtain a target physiological data; a processing module, which is electrically coupled to the basic physiological sampling module, and the processing module filters the target physiological data in at least one of a statistical method and a signal processing method to generate a processed data; and a comparison module and a database, the comparison module is electrically coupled to the processing module and the database, the comparison module obtains a symptom data with diabetes characteristics from the database, and the comparison module compares the processed data with the symptom data, and when the symptom data matches the processed data, the comparison module sends a notification signal.

Preferably, the target physiological data is limited to at least one of a body weight data, a body temperature data, a blood lipid data, and a sound data.

Preferably, the signal processing method performed by the processing module is limited to at least one of low-pass filtering, enhancement, and error correction.

Preferably, the statistical method performed by the processing module is limited to interpolation.

The embodiment of the present invention also discloses a detection method of a diabetes detection system, comprising the following steps: sampling people in an area to obtain a target physiological data; screening a plurality of normal physiological data and at least one diabetic physiological data from a group in the area; using the at least one diabetic physiological data to compare the differences between the normal physiological data to establish a symptom data; filtering the target physiological data by at least one of a statistical method and a signal processing method to generate a processed data; and using the symptom data to compare the processed data, and sending a notification signal when the symptom data matches the processed data.

Preferably, the target physiological data is limited to at least one of a body weight data, a body temperature data, a blood lipid data, and a sound data.

Preferably, the signal processing method performed by the processing module is limited to at least one of low-pass filtering, enhancement, and error correction.

Preferably, the statistical method performed by the processing module is limited to interpolation.

In summary, the diabetes detection system and detection method disclosed in the embodiments of the present invention can accurately identify the symptoms of diabetes in a non-invasive manner through the designs of "the processing module filters the target physiological data in at least one of a statistical manner and a signal processing manner to generate a processed data" and "the comparison module compares the processed data with the symptom data, and when the symptom data matches the processed data, the comparison module sends a notification signal".

To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only used for reference and description and are not used to limit the present invention.

The following is an explanation of the implementation of the "diabetes detection system and its detection method" disclosed in the present invention through specific concrete embodiments. Technical personnel in this field can understand the advantages and effects of the present invention from the contents disclosed in this manual. The present invention can be implemented or applied through other different specific embodiments, and the details in this manual can also be modified and changed in various ways based on different viewpoints and applications without deviating from the concept of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual sizes. Please note in advance. The following implementation will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

It should be understood that, although the terms "first", "second", "third", etc. may be used in this document to describe various components or signals, these components or signals should not be limited by these terms. These terms are mainly used to distinguish one component from another component, or one signal from another signal. In addition, the term "or" used in this document may include any one or more combinations of the related listed items depending on the actual situation.

In addition, in the following description, if it is indicated to refer to a specific figure or as shown in a specific figure, it is only used to emphasize that most of the related content described in the subsequent description appears in the specific figure, but it does not limit the subsequent description to only refer to the specific figure.

[First embodiment]

Referring to FIG. 1 , this embodiment provides a diabetes detection system 100, wherein the diabetes detection system 100 comprises a basic physiological sampling module 1, a processing module 2, a comparison module 3 and a database 4.

As shown in FIG1 , the basic physiological sampling module 1 can be used to sample a person to obtain a target physiological data. The target physiological data can be at least one of a weight data, a body temperature data, a blood lipid data, and a voice data. For example, the subject can wear a physiological data collection device, and the physiological data collection device can obtain the weight data, the body temperature data, the blood lipid data, and the voice data in a non-invasive manner.

The processing module 2 is electrically coupled to the basic physiological sampling module 1, and the processing module 2 filters the target physiological data by at least one of a statistical method and a signal processing method to generate a processed data. In practice, the signal processing method performed by the processing module 2 may be at least one of low-pass filtering, enhancement, and error correction. The statistical method performed by the processing module 2 may be an interpolation method. Accordingly, the processing module 2 can achieve filtering through appropriate statistical methods in combination with signal processing methods, thereby reducing noise, clarifying and improving the obtained information for subsequent use.

Referring again to FIG. 1 , the comparison module 3 is electrically coupled to the processing module 2 and the database 4. The comparison module 3 obtains a symptom data having diabetes characteristics from the database 4, and the comparison module 3 compares the processing data with the symptom data. Accordingly, when the symptom data matches the processing data, the comparison module 3 can send a notification signal to notify the presence of diabetes symptoms.

In practice, the database 4 can be established by sampling people in a region (e.g., a specific country) to obtain a target physiological data (e.g., a sound clip), and screening out a plurality of normal physiological data and at least one diabetic physiological data from a group in the region. Accordingly, the at least one diabetic physiological data is used to compare the differences between the normal physiological data to establish a symptom data.

For example, several male and female participants were recruited from four regions in India, and all participants underwent invasive and accurate diabetes testing to identify non-diabetic patients and diabetic patients (e.g., T2DM). Then, all participants were asked to record a fixed phrase using a smartphone, up to six times a day, for two weeks. For example, the phrase was "Hello, what is your current blood sugar level?". After that, several significant acoustic features were extracted from each recorded phrase, such as fundamental frequency, formant frequency, formant bandwidth, speech rate, etc., and the voice features of non-diabetic patients and diabetic patients were statistically analyzed to determine the differences between the two. Finally, a machine learning model was used to associate the voice features with T2DM status to establish a database (i.e., a prediction model). The comparison module uses the database to compare the target physiological data to see if there are symptoms of diabetes, so as to send a notification signal to a notification device (eg, a computer, a watch, etc.) for the subject or related personnel to view.

Of course, the above example is explained using sound, but the database can include data corresponding to the target physiological data, that is, weight changes, body temperature changes, blood lipid changes, etc., and the establishment method is roughly the same as mentioned above, so it will not be elaborated here.

[Second embodiment]

2 , this embodiment provides a detection method of a diabetes detection system, which can be applied to the diabetes detection system 100 of the first embodiment or any other diabetes detection system 100. The detection method includes steps S101 to S109.

Step S101: sampling people in an area to obtain a target physiological data, wherein the target physiological data is preferably at least one of a weight data, a body temperature data, a blood lipid data, and a voice data.

Step S103: Filter out a plurality of normal physiological data and at least one diabetic physiological data from a population in the region.

Step S105: using the at least one diabetes physiological data to compare the difference between the normal physiological data to establish a symptom data.

Step S107: Filter the target physiological data by at least one of a statistical method and a signal processing method to generate a processed data. In practice, the signal processing method performed by the processing module can be at least one of low-pass filtering, enhancement, and error correction. The statistical method performed by the processing module can be an interpolation method.

Step S109: using the symptom data to compare the processed data, and sending a notification signal when the symptom data matches the processed data.

[Technical Effects of the Embodiments of the Invention]

In summary, the diabetes detection system and detection method disclosed in the embodiments of the present invention can accurately identify the symptoms of diabetes in a non-invasive manner through the designs of "the processing module filters the target physiological data in at least one of a statistical manner and a signal processing manner to generate a processed data" and "the comparison module compares the processed data with the symptom data, and when the symptom data matches the processed data, the comparison module sends a notification signal".

The above disclosed contents are only the preferred feasible embodiments of the present invention, and do not limit the scope of the patent application of the present invention. Therefore, all equivalent technical changes made by using the contents of the description and drawings of the present invention are included in the scope of the patent application of the present invention.

100: Diabetes testing system 1: Basic physiological sampling module 2: Processing module 3: Comparison module 4: Database S101~S109: Steps

FIG1 is a circuit block diagram of the diabetes detection system of the present invention.

FIG. 2 is a schematic diagram of the step flow of the detection method of the present invention.

100: Diabetes detection system

1: Basic physiological sampling module

2: Processing module

3: Comparison module

4: Database

Claims (6)

A diabetes detection system includes: A basic physiological sampling module, which can be used to sample a person to obtain a target physiological data, wherein the target physiological data is limited to a sound data, and the sound data includes a basic frequency, a formant frequency, a formant bandwidth, and a speech rate; A processing module, electrically coupled to the basic physiological sampling module, wherein the processing module filters the target physiological data in a statistical manner and a signal processing manner to generate a processed data; and A comparison module and a database, the comparison module is electrically coupled to the processing module and the database, the comparison module obtains a symptom data with diabetes characteristics from the database, and the comparison module compares the processing data with the symptom data, and when the symptom data matches the processing data, the comparison module sends a diabetes notification signal. A diabetes detection system as described in claim 1, wherein the signal processing method performed by the processing module is limited to at least one of low-pass filtering, enhancement, and error correction. A diabetes detection system as described in claim 1, wherein the statistical method performed by the processing module is limited to interpolation. A detection method of a diabetes detection system includes the following steps: Sampling people in an area to obtain a target physiological data, the target physiological data is limited to a sound data, and the sound data includes basic frequency, formant frequency, formant bandwidth, and speech rate; Filtering a plurality of normal physiological data and at least one diabetic physiological data from a group in the area; Using the at least one diabetic physiological data to compare the difference between each of the normal physiological data to establish a symptom data; Filtering the target physiological data by at least one of a statistical method and a signal processing method to generate a processed data; and Using the symptom data to compare the processed data, and sending a diabetes notification signal when the symptom data matches the processed data. A detection method for a diabetes detection system as described in claim 4, wherein the processed data is limited by a filtering method to at least one of low-pass filtering, enhancement, and error correction. A detection method for a diabetes detection system as described in claim 4, wherein the statistical method for processing data is limited to interpolation method.

Images