VTE risk automatic evaluation system based on deep learning
A deep learning, automatic evaluation technology, applied in the field of VTE risk automatic evaluation system, can solve the problems of heavy workload, time-consuming, lack of nursing staff, etc., to reduce workload, improve accuracy, and ensure the effect of accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] like figure 1 As shown, Embodiment 1 of the present disclosure provides an automatic VTE risk assessment system based on deep learning. Based on artificial intelligence technology, it automatically analyzes various aspects of the patient's data in the hospital information system, and automatically fills in several types of VTE commonly seen in the medical field. Risk assessment forms (eg, Caprini, Rogers, Pauda, Wells, etc. assessment forms) to complete the VTE risk assessment.
[0061] Specifically, it includes an unstructured risk index comprehensive analysis module (ie the first analysis module), a structured risk index single analysis module (ie the second analysis module), an unstructured risk index judgment module (ie the first judgment module), Structured risk index judgment module (ie the second judgment module) and risk item judgment module;
[0062] In the "unstructured risk index comprehensive analysis module", based on the patient's information related to...
Embodiment 2
[0162] Embodiment 2 of the present disclosure provides a computer-readable storage medium on which a program is stored, and when the program is executed by a processor, the following steps are implemented:
[0163] According to the preset VTE knowledge map and the first deep learning model, based on the patient's information related to all risk items, obtain the probability that all unstructured risk indicators of the patient are selected;
[0164] According to the preset VTE knowledge map and the second deep learning model, based on the patient's information related to an unstructured risk index, obtain the probability that a patient's unstructured risk index is selected;
[0165] Based on the probability that all unstructured risk indicators of the patient are selected and the probability that a certain unstructured risk indicator of the patient is selected, determine whether the unstructured risk indicator is selected;
[0166] According to the preset VTE knowledge map, det...
Embodiment 3
[0170] Embodiment 3 of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and running on the processor, where the processor implements the following steps when executing the program:
[0171] According to the preset VTE knowledge map and the first deep learning model, based on the patient's information related to all risk items, obtain the probability that all unstructured risk indicators of the patient are selected;
[0172] According to the preset VTE knowledge map and the second deep learning model, based on the patient's information related to an unstructured risk index, obtain the probability that a patient's unstructured risk index is selected;
[0173] Based on the probability that all unstructured risk indicators of the patient are selected and the probability that a certain unstructured risk indicator of the patient is selected, determine whether the unstructured risk indicator is selected;
[0174...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


