Risk Warning Model of Postoperative Delirium and Long-term Cognitive Dysfunction in Elderly Patients Based on Autonomous Evolutionary Neural Network Algorithm
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Postoperative Delirium
- Sponsor
- Xuanwu Hospital, Beijing
- Enrollment
- 10000
- Locations
- 1
- Primary Endpoint
- Screening for risk factors of perioperative cognitive dysfunction
- Status
- Recruiting
- Last Updated
- last year
Overview
Brief Summary
The incidence of postoperative delirium in elderly patients is high, which can lead to long-term postoperative neurocognitive disorders. Its high risk factors are not yet clear. At present, there is a lack of early diagnosis and alarm technology for perioperative neurocognitive disorders, which can not achieve early intervention and effective treatment. By artificial intelligence and autonomously evolutionary neural network algorithm, relying on multi-source clinical big data, we explored the use of Bayesian network to optimize the anesthesia decision-making system in enhanced recovery after surgery, and established risk prediction model for perioperative critical events. It is expected that this method will also help to establish a risk prediction model for postoperative delirium and long-term postoperative neurocognitive disorders. This project plans to collect the perioperative sensitive parameters of anesthesia machine, multi-parameter monitor, EEG monitor,fMRI and HIS system, to explore the evolution process of data characteristics by feature fusion.We also plan to quickly screen key perioperative risk characteristics of postoperative delirium from massive clinical data through feature selection, to explore the high risk factors of long-term postoperative neurocognitive disorders developing from postoperative delirium. Finally, with multi-center intelligent analysis，the risk prediction model of postoperative delirium and long-term postoperative neurocognitive disorders will be constructed.
Detailed Description
This project intends to collect and identify clinical monitoring data of anesthesia machine, multi-parameter monitor and brain function monitor on the basis of the team's previous series of studies on cognitive function protection of elderly patients in perioperative period and the research on tracking and warning of critical illness events and decision support services based on artificial intelligence. HIS clinical data and classified and tracked fMRI imaging data were integrated to form a large data set related to perioperative cognitive function of elderly patients. Based on pNCD clinical diagnostic information and fMRI imaging diagnostic information, a brain adverse event prediction system capable of intelligent extraction of clinical key information and real-time early warning was established by using key technologies such as data quality control, real-time collection and identification of multi-source clinical monitoring data, and artificial intelligence adverse event prediction.
Investigators
Eligibility Criteria
Inclusion Criteria
- •Patients ≥65 years of age who have undergone surgical anesthesia; Sign informed consent
Exclusion Criteria
- •Inability to complete cognitive function assessment; Illiteracy, hearing impairment or visual impairment; He has a history of epilepsy, depression, schizophrenia, Alzheimer's disease and other psychiatric and neurological diseases
Outcomes
Primary Outcomes
Screening for risk factors of perioperative cognitive dysfunction
Time Frame: 2024.4.1-2027.12.31
The feature selection technique in artificial intelligence was used to screen and analyze data from a large dataset of clinical care after fusion The risk factors with the highest probability of PND occurrence can be screened from a large number of characteristics,By screening the risk factors that have the highest correlation with the probability of POD occurrence, combined with the comparison of fMRI imaging data of different groups of large sample size POD patients with long-term conversion to pNCD group and non-PNCD group, the brain network mechanism and perioperative high risk factors of POD conversion to long-term cognitive dysfunction were further explored.
Establish a prediction system for adverse brain function events
Time Frame: 2025.1.1-2027.12.31
The monitoring data of surgical patients contains a large amount of medical information, and the analysis and modeling of the data can provide effective early warning and intervention. The project intends to adopt EEG time-frequency feature extraction and analysis, EEG micro-state analysis, and brain network analysis, and adopt feature fusion technology to fuse various features into unified features of patients. On this basis, a prediction model of adverse brain function events based on domain adaptation algorithm was constructed to realize real-time tracking, early diagnosis and early warning of postoperative delirium and long-term cognitive dysfunction in elderly patients