Cardiovascular acute event early warning method based on reinforcement learning

By combining uncertainty-aware deep networks and security-constrained reinforcement learning, the early warning strategy for acute cardiovascular events is dynamically adjusted, solving the problems of high false alarm rate and high risk of missed alarms in existing technologies, and realizing a more efficient and accurate early warning method.

CN121885181AInactive Publication Date: 2026-04-17TONGLIAO HOSPITAL
0 Cites 0 Cited by

Patent Information

Application Number
CN202511939136.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-22
Publication Date
2026-04-17
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing methods for early warning of acute cardiovascular events are unable to balance individualized early warning triggering timing and assessment frequency, and cannot dynamically balance between false alarms and missed alarms, resulting in a high false alarm rate, a high risk of missed alarms, and low resource utilization efficiency.

Method used

This approach combines uncertainty-aware deep networks and security-constrained reinforcement learning. By outputting risk scores, risk change trends, and predicted uncertainties for the current and future time windows from multiple sources, and combining historical alarm records and individualized risk thresholds, the early warning strategy is dynamically adjusted, including whether to trigger an early warning, the risk threshold, and the assessment time interval.

Benefits of technology

Under the premise of controllable risk of missed alarms, reduce the false alarm rate, improve the lead time and individualization of early warnings, optimize the assessment frequency and resource utilization, and improve the accuracy and reliability of early warnings.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a cardiovascular acute event early warning method based on reinforcement learning, and aims to solve the problems that an early warning scheme is difficult to consider individualized trigger opportunity and evaluation frequency and is difficult to balance false alarm and missed alarm. The method comprises the following steps of: outputting risks, trends and uncertainty of current and future time windows by using multiple heads of an uncertainty perception deep network, constructing a state in combination with historical alarm records, individualized risk thresholds and evaluation time intervals, and inputting the state into a security constraint reinforcement learning network; in the same forward reasoning, whether early warning, threshold value adjustment amount and next evaluation time interval are determined in a combined manner, and a constraint weight updating strategy is adaptively adjusted based on early warning income, false alarm and missed alarm indexes and prediction uncertainty after a real label is obtained. The technical effects of reducing the false alarm rate, optimizing the early warning advance and the evaluation frequency and improving the early warning accuracy and reliability of the cardiovascular acute event on the premise that the missed alarm risk is controllable are achieved.
Need to check novelty before this filing date? Find Prior Art