Type 2 diabetes detection method, device and system and storage medium

Abstract

The invention discloses a type 2 diabetes mellitus detection method, device and system and a storage medium, and the method comprises the following steps: S1, collecting tongue coating flora of healthy people, prediabetic people and diabetic patients, and constructing a biological sample library; s2, according to the biological sample library and the population basic information, constructing a type 2 diabetes detection early prediction model; wherein the basic information of the crowd comprises gender, age, BMI, waist and hip circumference and diet mode; and S3, inputting the to-be-treated tongue coating flora of the testee into the type 2 diabetes detection early prediction model for diabetes detection. By adopting the technical scheme of the invention, the detection risk of suffering from type 2 diabetes mellitus of people is predicted, and a basis is provided for early prevention of type 2 diabetes mellitus detection.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically relating to a method, device, system, and storage medium for detecting type 2 diabetes based on tongue flora and physiological indicators. Background Technology

[0002] The microbiome is a complex ecosystem composed of various microorganisms, including bacteria, archaea, fungi, viruses, and protozoa. They are widely distributed throughout the human body, including the skin, mouth, intestines, and respiratory tract. The total number of microbiome cells exceeds the number of human cells, and the total number of genes is approximately 150 times that of the human genome, earning it the title of "the second genome." The microbiome works collaboratively with the human body to maintain various physiological functions. Imbalances in the microbiome can trigger diseases through multiple pathways, particularly affecting metabolic functions and insulin sensitivity, leading to insulin resistance—a key factor in the development of type 2 diabetes. The mouth is the entrance to the gastrointestinal tract, and the microorganisms within it are a crucial component in maintaining the balance between health and disease. The soft surfaces of the mouth are covered with a complex biological layer tightly bound to epithelial cells, known as the mucosal protective membrane. Particularly on the dorsal side of the tongue, this membrane is densely covered with microorganisms, known as the "tongue coating." Although the distribution of microbiota varies at different sites in the mouth, research shows that the tongue coating is a potential reservoir of oral microbes. Changes in its microbial composition and abundance can be used to diagnose and monitor disease changes, serving as a "barometer" of human health. The microbiota of the tongue can increase blood sugar by affecting the metabolism of carbohydrates, fats, and proteins in the human body. It can also influence the development of type 2 diabetes by regulating the immune system. Furthermore, it can interact with the gut microbiota through symbiotic and ectopic colonization, jointly affecting the host's energy metabolism, lipid metabolism, and glucose metabolism, thus increasing the risk of type 2 diabetes. Related studies have found that the relative abundance of Proteobacteria and Firmicutes in the tongue microbiota is significantly increased in individuals with type 2 diabetes, while the relative abundance of Actinobacteria and Bacteroidetes is significantly decreased. Among these, Actinobacterium species can serve as biomarkers for the detection of type 2 diabetes.

[0003] Diabetes mellitus is a chronic metabolic disorder characterized by impaired insulin secretion, impaired insulin action, or both. The number of people with diabetes worldwide continues to rise, and the age of onset is trending younger. In 2021, there were approximately 537 million people with diabetes globally, and it is estimated that 90%-95% of cases are type 2 diabetes, significantly increasing the global public health burden.

[0004] Before being diagnosed with type 2 diabetes, patients go through a prediabetes stage. Currently, clinical testing technology mainly focuses on the diagnosis of these two stages, lacking earlier prediction and warning. Summary of the Invention

[0005] To address the problems existing in the prior art, the present invention provides a method, device, system, and storage medium for detecting type 2 diabetes.

[0006] To achieve the above objectives, the present invention provides the following solution: A method for detecting type 2 diabetes includes: Step S1: Collect tongue flora from healthy individuals, individuals with prediabetes, and diabetic patients to construct a biobank. Step S2: Based on the biobank and basic population information, construct an early prediction model for type 2 diabetes detection; the basic population information includes: gender, age, BMI, waist-hip circumference, and dietary patterns. Step S3: Input the tongue flora of the test subjects to be processed into the early prediction model for type 2 diabetes detection for diabetes detection.

[0007] As a preferred option, in step S1, the diversity and distribution characteristics of tongue flora in different populations are obtained by 16S rRNA sequencing, and the marker tongue flora of different populations are identified.

[0008] As a preferred option, in step S2, a Logistic regression analysis model is trained using the biobank and basic population information to construct an early prediction model for type 2 diabetes detection.

[0009] The present invention also provides a type 2 diabetes detection device, comprising: The first processing module is used to collect tongue flora from healthy people, people with prediabetes, and diabetic patients to build a biobank. The second processing module is used to construct an early prediction model for type 2 diabetes detection based on the biobank and basic population information; the basic population information includes: gender, age, BMI, waist-hip circumference, and dietary patterns. The third processing module is used to input the tongue flora of the test subjects into the early prediction model for type 2 diabetes detection for diabetes detection.

[0010] As a preferred method, the first processing module obtains the diversity and distribution characteristics of tongue flora in different populations through 16S rRNA sequencing, and finds the marker tongue flora of different populations.

[0011] As a preferred option, the second processing module trains a Logistic regression analysis model using the biobank and basic population information to construct an early prediction model for type 2 diabetes detection.

[0012] The present invention also provides a type 2 diabetes detection system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program performs a type 2 diabetes detection method when executed by the processor.

[0013] The present invention also provides a storage medium storing a computer program that executes a type 2 diabetes detection method when running.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Based on the tongue flora and combined with physiological indicators, a more convenient and non-invasive detection method can be used to predict the risk of developing type 2 diabetes in the population, providing a basis for earlier prevention of type 2 diabetes. 2. Compared to only physiological indicators such as waist-hip circumference prediction, it has a higher accuracy rate. Compared to existing genetic prediction methods for type 2 diabetes risk assessment, it is non-invasive, convenient, cheaper, more economical, and easier to promote. Attached Figure Description

[0015] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the type 2 diabetes detection method according to Embodiment 2 of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] Example 1 like Figure 1 As shown, the present invention provides a method for detecting type 2 diabetes, comprising: Step S1: Collect tongue flora from healthy individuals, individuals with prediabetes, and diabetic patients to construct a biobank. Step S2: Based on the biobank and basic population information, construct an early prediction model for type 2 diabetes detection; the basic population information includes: gender, age, BMI, waist-hip circumference, and dietary patterns. Step S3: Input the tongue flora of the test subjects to be processed into the early prediction model for type 2 diabetes detection for diabetes detection.

[0020] As one embodiment of the present invention, in step S1, the diversity and distribution characteristics of tongue flora in different populations are obtained by 16S rRNA sequencing, and the marker tongue flora of different populations are found.

[0021] Furthermore, high-throughput sequencing was used to process tongue coating microorganisms, including: DNA Extraction: Total genomic DNA samples were extracted using the OMEGA Soil DNA Kit (D5625-01) (Omega Bio-Tek, Norcross, GA, USA) according to the product instructions and stored at -20°C before further analysis. The concentration and quality of the extracted DNA were measured using a NanoDrop ND-1000 spectrophotometer (Thermo Fisher Scientific, Scientific, Waltham, MA, USA) and agarose gel electrophoresis.

[0022] Microbiome sequencing: PCR amplification of the V3-V4 region of the bacterial 16S rRNA gene was performed using forward primer 338F (5'-ACTCCTACGGGAGGCGCAGCA-3') and reverse primer 806R (5'-GGACTACHVGGGTWTCTAAT-3'). Sample-specific 7-bp barcodes were integrated into the primers for multiplex sequencing. PCR components included 5 μl buffer (5x), 0.25 μl Fast pfu DNA polymerase (5 U / μl), 2 μl (2.5 mM) dNTPs, 1 μl (10 uM) of each forward and reverse primer, 1 μl DNA template, and 14.75 μl ddH2O. Thermal cycling consisted of initial denaturation at 98°C for 5 min, followed by 25 cycles of denaturation at 98°C for 30 s, annealing at 53°C for 30 s, and extension at 72°C for 45 s, with a final extension of 5 min at 72°C. PCR amplicones were purified using Vazyme VAHTS™ DNA Clean Beads (Vazyme, Nanjing, China) and quantified using the Quant-iT PicoGreen dsDNA assay kit (Invitrogen, Carlsbad, CA, USA). After individual quantification, amplicon volumes were pooled and sequenced at paired ends (2 × 250 bp) using the Illlumina NovaSeq platform and NovaSeq 6000SP Reagent Kit (500 cycles).

[0023] Microbial data preparation: The QIIME 2_DADA 2 analysis workflow was used to process and analyze microbial sequences, mainly including primer removal, quality filtering, denoising, splicing, and chimera removal. Specifically: ① The original sequence data was demultiplexed using the demux plugin. ② Primers were cut using the cutadapt plugin. ③ The sequences were quality filtered, denoised, merged, and dechimerized using the DADA2 plugin. ④ Non-singleton amplicon sequence variants (ASVs) were aligned using maft, and a phylogenetic tree was constructed using fasttree2. ⑤ The diversity plugin was used to evaluate α-diversity parameters (Chao1 index, Shannon index) and beta-diversity parameters (Bray Curtisdissimilarity). ⑥ Based on the Greengenes database (Release 13.8, http: / / greengenes.secondgenome.com), 99% of the reference sequences of operational taxonomic units (OTUs) were used. The classify-sklearn naïve Bayes classifier in the feature classifier plugin was used to assign ASVs to taxonomic units to complete species annotation.

[0024] Data Analysis: Microbiome bioinformatics analysis was performed using QIIME2 (2019.4) according to the public tutorial (https: / / docs.qiime2.org / 2019.4 / tutorials / ); LEfSe analysis was used to detect taxa with rich and stable differences between groups; random forest analysis was performed using QIIME2 to distinguish the contribution of samples from different groups to the differences between groups; and marker bacteria for tongue coating in prediabetes and type 2 diabetes were obtained.

[0025] Furthermore, the criteria for the sampled population are divided into: Healthy individuals: Free from acute or chronic diseases such as hypertension, glucose and lipid metabolism disorders, HIV infection, or genetic diseases, as well as any ongoing benign or malignant diseases that may interfere with the research objectives; Oral health: Free from oral diseases such as leukoplakia, erythroplakia, oral lichen planus (OLP), etc.

[0026] For individuals with prediabetes: fasting blood glucose: 6.1–6.9 mmol / L; or 2-hour OGTT blood glucose: 7.8–11.0 mmol / L; or glycated hemoglobin: 5.7%–6.4%.

[0027] Type 2 diabetes screening population: based on the Chinese Diabetes Society's Guidelines for the Prevention and Treatment of Type 2 Diabetes in China (2020 Edition) and the 1999 World Health Organization criteria (FBG ≥ 7 mmol / L and / or 2-hour OGTT ≥ 11.1 mmol / L).

[0028] Furthermore, dietary patterns include: 1. The traditional Eastern diet: primarily plant-based foods, supplemented by animal-based foods.

[0029] 2. The model of economically developed countries: high proportion of animal-based foods.

[0030] 3. Japanese dietary pattern: balanced intake of animal and plant foods, low in oil and salt, and high in seafood.

[0031] 4. Mediterranean diet: based on olive oil and plant-based foods.

[0032] As one embodiment of the present invention, in step S2, a Logistic regression analysis model is trained using a biobank and basic population information to construct an early prediction model for type 2 diabetes detection, which is used to predict the risk of different populations developing type 2 diabetes.

[0033] Furthermore, a predictive model was constructed using multivariate logistic regression analysis. Based on the estimated sample size, at least 300 cases need to be collected for analysis, with 200 cases used for model building and the remaining 100 cases used for model prediction. The specific steps are as follows: 1. Data preparation: Healthy individuals, prediabetes, and type 2 diabetes were assigned values ​​of 1, 2, and 3, respectively.

[0034] 2. Open SPSS software, click the menu bar: Analyze → Regression → Multinomial Logistic, and open the main dialog box. Step 1: Select variables: include healthy people, prediabetes, and type 2 diabetes as dependent variables (ordinal categorical variables), and set healthy people (1) as the reference category. Step 2: Select variables, including categorical variables: gender and dietary pattern in the factors; and continuous variables: age, BMI, waist and hip circumference, and relative abundance of tongue coating marker bacteria in the covariates. Step 3: Design statistics: check: model fit, likelihood ratio test, parameter estimation, classification table, and 95% confidence interval of covariates, and click Continue to return. Step 4: Save the prediction results, including the prediction category and prediction probability; Step 5: Execute the model, obtain the regression coefficients of each factor including tongue coating flora, and construct the prediction model for early type 2 diabetes and type 2 diabetes.

[0035] 3. Model validation: Another 100 cases were used to validate the model and obtain the accuracy, sensitivity and specificity of the prediction model.

[0036] The technical solution of this invention enables the detection of type 2 diabetes through "physiological information - tongue flora collection - flora sequencing - data analysis - risk prediction".

[0037] Example 2 The present invention also provides a type 2 diabetes detection device, comprising: The first processing module is used to collect tongue flora from healthy people, people with prediabetes, and diabetic patients to build a biobank. The second processing module is used to construct an early prediction model for type 2 diabetes detection based on the biobank and basic population information; the basic population information includes: gender, age, BMI, waist-hip circumference, and dietary patterns. The third processing module is used to input the tongue flora of the test subjects into the early prediction model for type 2 diabetes detection for diabetes detection.

[0038] As one embodiment of the present invention, the first processing module obtains the diversity and distribution characteristics of tongue flora in different populations through 16S rRNA sequencing, and finds the marker tongue flora of different populations.

[0039] As one embodiment of the present invention, the second processing module trains a Logistic regression analysis model with the biobank and basic population information to construct an early prediction model for type 2 diabetes detection.

[0040] Example 3 The present invention also provides a type 2 diabetes detection system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program performs a type 2 diabetes detection method when executed by the processor.

[0041] Example 4 The present invention also provides a storage medium storing a computer program that executes a type 2 diabetes detection method when running.

[0042] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for detecting type 2 diabetes, characterized in that, include: Step S1: Collect tongue flora from healthy individuals, individuals with prediabetes, and diabetic patients to construct a biobank. Step S2: Based on the biobank and basic population information, construct an early prediction model for type 2 diabetes detection; the basic population information includes: gender, age, BMI, waist-hip circumference, and dietary patterns. Step S3: Input the tongue flora of the test subjects to be processed into the early prediction model for type 2 diabetes detection for diabetes detection.

2. The method for detecting type 2 diabetes as described in claim 1, characterized in that, In step S1, the diversity and distribution characteristics of tongue flora in different populations are obtained by 16S rRNA sequencing, and the marker tongue flora of different populations are identified.

3. The method for detecting type 2 diabetes as described in claim 2, characterized in that, In step S2, the biobank and basic population information are used to train a Logistic regression analysis model to construct an early prediction model for type 2 diabetes detection.

4. A type 2 diabetes detection device, characterized in that, include: The first processing module is used to collect tongue flora from healthy people, people with prediabetes, and diabetic patients to build a biobank. The second processing module is used to construct an early prediction model for type 2 diabetes detection based on the biobank and basic population information; the basic population information includes: gender, age, BMI, waist-hip circumference, and dietary patterns. The third processing module is used to input the tongue flora of the test subjects into the early prediction model for type 2 diabetes detection for diabetes detection.

5. The type 2 diabetes detection device as described in claim 4, characterized in that, The first processing module obtains the diversity and distribution characteristics of tongue flora in different populations through 16S rRNA sequencing, and identifies the marker tongue flora of different population stages.

6. The type 2 diabetes detection device as described in claim 5, characterized in that, The second processing module trains a Logistic regression analysis model using the biobank and basic population information to construct an early prediction model for type 2 diabetes detection.

7. A type 2 diabetes detection system, characterized in that, include: A memory and a processor, wherein the memory stores a computer program executed by the processor, the computer program performing the type 2 diabetes detection method as described in any one of claims 1-3 when executed by the processor.

8. A storage medium, characterized in that, The storage medium stores a computer program that, when executed, performs the type 2 diabetes detection method as described in any one of claims 1-3.

Images