Refractory schizophrenia risk prediction method based on machine learning
A technology of schizophrenia and prediction method, which is applied in the field of risk prediction of refractory schizophrenia, and can solve problems such as increasing social burden, delaying treatment timing for schizophrenia patients, psychological distress of patients and their families, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0040] Embodiment 1. A method for constructing a deep learning model of refractory schizophrenia
[0041] This embodiment mainly describes a construction method of a deep learning model for refractory schizophrenia. The construction method of the deep learning model includes two parts: the convolutional neural network model of the SNPs site typing results and the construction of the recurrent neural network.
[0042] The convolutional neural network model of the SNPs site typing result includes: an input layer, a plurality of hidden layers and an output layer, and the hidden layer includes a convolutional layer, and / or a pooling layer, and / or a full connection layer; the input data of the convolution layer is the SNPs site typing result, the convolution layer is at least 1, and the convolution kernel of each convolution layer is at least 2, and the size of the convolution kernel is at least 2, Or 2×2, or 2×2×2, the step size of the convolutional layer is at least 1; the step ...
Embodiment 2
[0060] Embodiment 2. A method for extracting power spectrum features of human brain electrodynamic data
[0061] This embodiment mainly constructs a method for extracting power spectrum features of human brain electrodynamic data, and the extraction method is:
[0062] The power spectrum features of the human brain electrodynamic data are extracted through the power spectrum analysis method, specifically through the following steps:
[0063] Step 0: Obtain the EEG data of the sample population [e i (t), t=1,2,...T], and the EEG data [e i (t), t=1,2,...T] into EEG vector data [v i (t), v i ∈R 3 ,t=1,2,...T]. Then, the EEG vector data is used to construct the model of the RBF neural network: using the dynamic RBF neural network identifier Locally accurate neural network approximation of intrinsic system dynamics of EEG vector data; obtains EEG dynamics data [x i (t),x i ∈R 3 ,t=1,2,…T], specifically: Among them, S(X(t)), S(Y(t)) and S(Z(t)) are all Gaussian radial ba...
Embodiment 3
[0068] Example 3. A method for constructing a logistic regression model for risk assessment of refractory schizophrenia
[0069] This embodiment provides a method for constructing a logistic regression model for risk assessment of refractory schizophrenia, specifically: obtaining the critical diagnostic value of the data characteristics of non-refractory and refractory schizophrenia, obtained by the following method: inclusion N clinically known healthy individuals (N>5000) and M clinically known refractory schizophrenia individuals (M>5000) were used as the test sample population, and the EEG data of the test sample population were collected to obtain EEG dynamic data. Extract the data feature of electroencephalodynamic data by the extraction method of power spectrum feature described in embodiment 3; Then obtain the data characteristic value of the electroencephalodynamic data of all individuals, carry out statistical classification based on probability (He Xianying, Zhao Zhi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com