A deep reinforcement learning-based auxiliary regulation system for dry body weight of hemodialysis patients

Abstract

The invention discloses a dry weight auxiliary adjustment system for hemodialysis patients based on deep reinforcement learning. The system includes a data acquisition module, a data processing module, a strategy learning module and an auxiliary decision-making module; the invention utilizes the deep reinforcement learning technology to construct competitive The deep double-Q network (Dueling DDQN network) of the framework is used as an agent to simulate the process of doctors adjusting the dry weight of hemodialysis patients, and intelligently learn the strategy of adjusting the dry weight of hemodialysis patients. The invention models the dry weight regulation process of hemodialysis patients as a partially observed Markov process, defines respective state space and action space for different dialysis periods, and designs a reward function including long-term survival reward and short-term dialysis side reaction penalty ; Through the interactive learning between the agent and the patient's state, the dry weight adjustment strategy that maximizes the overall reward is obtained, thereby assisting the doctor in the long-term management of the patient's dry weight.

Description

technical field [0001] The invention belongs to the technical field of medical treatment and machine learning, and in particular, relates to an auxiliary adjustment system for dry weight of hemodialysis patients based on deep reinforcement learning. Background technique [0002] Worldwide, the number of patients with end-stage renal disease is increasing significantly. Due to the shortage of donor kidney resources, most patients rely on hemodialysis (hemodialysis) treatment to maintain their lives. The risk of infection, cardiovascular and cerebrovascular diseases in patients with end-stage renal disease is much higher than that of the normal population, and the living conditions are far worse than that of the general population. End-stage renal disease has become a huge burden on the health care system. The main goal of hemodialysis is to correct the composition and volume of body fluids through ultrafiltration (UF) to achieve fluid balance, and dry body weight is a key in...

AI Technical Summary

Problems solved by technology

Therefore, in a high-data-density environment such as clinical practice, clinicians must review a large amount of patient characteristic data to assess or monitor dry weight, resulting in a complex, time-consuming and labor-intensive decision-making process for dry weight

This also makes the effect of hemodialysis treatment closely related to the experience and medical knowledge of the attending doctor, aggravating the imbalance in the distribution of regional medical resources

Images