CN-122025144-A - Neuropsychiatric health risk assessment and grading system based on intestinal microorganisms

CN122025144ACN 122025144 ACN122025144 ACN 122025144ACN-122025144-A

Abstract

The invention provides a neuropsychiatric health risk assessment and grading system based on intestinal microorganisms, and belongs to the technical field of neuropsychiatric health risk assessment. The invention provides a neuropsychiatric health risk assessment system which comprises a data acquisition and processing module, a microorganism species abundance analysis module, a model calculation module and a neuropsychiatric health risk assessment result output module, and further provides a neuropsychiatric health risk classification system, wherein a risk classification module is added on the basis of the neuropsychiatric health risk assessment system. According to the invention, through carrying out integrated analysis on multidimensional microbiome data, the microbial abundance data is converted into objective, quantifiable and graded output neuropsychiatric health results, thereby being beneficial to early identification of high-risk individuals and targeted intervention, providing reliable basis for clinical decision and having good universality and expandability.

Inventors

ZHU FENG
JU YANMEI
GUO RUIJIN
LIN SHUTIAN
QIAO RUIRUI
WANG YIYANG

Assignees

西安交通大学医学院第一附属医院

Dates

Publication Date: 20260512
Application Date: 20260224

Claims (10)

1. The neuropsychiatric health risk assessment system based on the intestinal microorganisms is characterized by comprising a data acquisition and processing module, a microorganism species abundance analysis module, a model calculation module and a neuropsychiatric health risk assessment result output module; The data acquisition and processing module is used for carrying out high-throughput sequencing on the fecal sample to acquire sequencing data, and removing the human gene sequence from the sequencing data to obtain a sample to be detected of the microbial gene sequence; The microorganism species abundance analysis module is used for analyzing a sample to be detected of a microorganism gene sequence to obtain relative abundance data corresponding to intestinal microorganisms in a fecal sample; The model calculation module is used for automatically carrying out state prediction after receiving relative abundance data of microorganism species in the fecal sample by utilizing a machine learning classification model trained by a machine learning algorithm to obtain a prediction probability value P of the neuropsychiatric disease state; The neuropsychiatric health risk assessment result output module is used for calculating a microbial intestinal brain axis health index according to a preset formula according to a predicted probability value P, outputting the microbial intestinal brain axis health index, and assessing the neuropsychiatric health risk, wherein the preset formula is that the microbial intestinal brain axis health index=0- (P-T), and the T is an optimal classification threshold value determined by a maximum Youden index.
2. The neuropsychiatric health risk assessment system of claim 1, wherein the high throughput sequencing comprises metagenomic shotgun sequencing.
3. The neuropsychiatric health risk assessment system of claim 1, wherein human gene sequences are removed from the sequencing data using the tool Bowtie2, referenced to the GRCh38 human genome.
4. The neuropsychiatric health risk assessment system of claim 1, wherein in the model calculation module, the relative abundance data of 1 x 10 -4 or more relative abundance is entered for status prediction.
5. The neuropsychiatric health risk assessment system of claim 1, wherein the machine learning algorithm comprises CatBoost.
6. The neuropsychiatric health risk assessment system of claim 5, wherein the training is performed using standardized pretreatment, quality control, species annotation, and batch effect corrected intestinal microbial species abundance data.
7. The neuropsychiatric health risk assessment system of claim 1, wherein the greater the absolute value of the microbial gut brain axis health index, the higher the neuropsychiatric health risk when the microbial gut brain axis health index is less than 0.
8. A neuropsychiatric health risk classification system based on intestinal microorganisms, comprising the neuropsychiatric health risk assessment system and risk classification module of any one of claims 1-7; the risk classification module is used for classifying the neuropsychiatric health risks according to the microbial intestinal brain axis health index.
9. The neuropsychiatric health risk classification system of claim 8, wherein the risk classification is a health state when the microbial gut brain axis health index is greater than 0, a critical risk state when the microbial gut brain axis health index is equal to 0, and a high risk state when the microbial gut brain axis health index is less than 0.
10. A computer program product comprising a computer program, characterized in that the computer program when executed by a processor runs the neuropsychiatric health risk assessment system of any one of claims 1 to 7 or the neuropsychiatric health risk ranking system of any one of claims 8 to 9.

Description

Neuropsychiatric health risk assessment and grading system based on intestinal microorganisms Technical Field The invention belongs to the technical field of neuropsychiatric health risk assessment, and particularly relates to a neuropsychiatric health risk assessment and grading system based on intestinal microorganisms. Background Neuropsychiatric disorders such as depression, anxiety, autism Spectrum Disorders (ASD), parkinson's Disease (PD), and the like have become a significant public health challenge worldwide. Such diseases have traditionally relied primarily on clinical symptom interviews and scales for diagnosis and assessment, lack of objective, quantitative biological markers, lead to difficulties in early screening, subjectivity in diagnosis, and difficulty in effectively stratification and pre-warning of disease risk. In recent years, with the development of microbiology, the mechanisms by which intestinal microbiota affect central nervous system and neuropsychiatric health through the "gut-brain axis" have been increasingly revealed. The existing research shows that the intestinal microbial composition of the patients with the neuropsychiatric diseases is obviously different from that of healthy people. However, there is currently a lack of objective microbiome-based assessment indicators that can be applied clinically. Most studies remain only at the level of finding the association of microbiome with disease, or only at the point of making a two-way judgment of disease and health, lacking a quantitative tool to convert microbiome features into useful for individual risk stratification and early warning. And the existing analysis method generally depends on complex bioinformatics flow and manual interpretation, is difficult to integrate into a stable and automatic system, and cannot meet the requirements of high throughput, standardization and quick output in clinical application. Therefore, how to convert the intestinal microbiome data into objective, quantifiable and graded output neuropsychiatric health results is important for early assessment of neuropsychiatric health. Disclosure of Invention To solve the problems in the prior art, a first object of the present invention is to provide a neuropsychiatric health risk assessment system based on intestinal microorganisms. The second object of the present invention is also to provide a neuropsychiatric health risk stratification system based on intestinal microorganisms. It is a third object of the present invention to provide a computer program product that converts intestinal microbiome data into objective, quantifiable, scalable output neuropsychiatric health results. In order to achieve the above object, the present invention provides the following technical solutions: The invention provides a neuropsychiatric health risk assessment system based on intestinal microorganisms, which comprises a data acquisition and processing module, a microorganism species abundance analysis module, a model calculation module and a neuropsychiatric health risk assessment result output module, wherein the data acquisition and processing module is used for acquiring and processing the data; The data acquisition and processing module is used for carrying out high-throughput sequencing on the fecal sample to acquire sequencing data, and removing the human gene sequence from the sequencing data to obtain a sample to be detected of the microbial gene sequence; The microorganism species abundance analysis module is used for analyzing a sample to be detected of a microorganism gene sequence to obtain relative abundance data corresponding to intestinal microorganisms in a fecal sample; The model calculation module is used for automatically carrying out state prediction after receiving relative abundance data of microorganism species in the fecal sample by utilizing a machine learning classification model trained by a machine learning algorithm to obtain a prediction probability value P of the neuropsychiatric disease state; The neuropsychiatric health risk assessment result output module is used for calculating a microbial intestinal brain axis health index according to a preset formula according to a predicted probability value P, outputting the microbial intestinal brain axis health index, and assessing the neuropsychiatric health risk, wherein the preset formula is that the microbial intestinal brain axis health index=0- (P-T), and the T is an optimal classification threshold value determined by a maximum Youden index. Preferably, the high throughput sequencing comprises metagenomic shotgun sequencing. Preferably, the human gene sequence is removed from the sequencing data using the tool Bowtie2, reference GRCh38 human genome. Preferably, in the model calculation module, inputting the relative abundance data with the relative abundance being more than or equal to 1×10 -4 for state prediction. Preferably, the machine learning algorithm includes CatBoost. Prefer