Ai-based dialysis blood vessel replacement cycle prediction method

The AI-based method for predicting dialysis vessel replacement cycles addresses the limitations of subjective vascular management by using EMR, OCS, and OCR technologies to analyze time-series data, improving dialysis efficiency and patient safety through precise, personalized risk assessment.

WO2026127177A1 Publication Date: 2026-06-18LIVIN AI INC +1
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
LIVIN AI INC
Filing Date
2024-12-12
Publication Date
2026-06-18

AI Technical Summary

⚠Technical Problem

Existing vascular management methods for dialysis patients fail to comprehensively analyze individual biometric data, relying on subjective judgments for determining the timing of vessel replacement, leading to missed early detection of stenosis and occlusion, and resulting in reduced dialysis efficiency and unnecessary medical resource waste.

⚗Method used

An AI-based method utilizing EMR, OCS, and OCR technologies to collect and analyze time-series data, training a prediction model with LSTM and Transformer models to predict dialysis vessel replacement cycles, incorporating real-time data collection and multi-stage risk assessment.

🎯Benefits of technology

Enhances dialysis safety and efficiency by accurately predicting vascular conditions, reducing unnecessary replacements, and optimizing medical resource use through personalized risk assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The present invention relates to an AI-based dialysis blood vessel replacement cycle prediction method for predicting a replacement cycle of a dialysis blood vessel, the method comprising: a data collection step (S10) of collecting a patient's electronic medical record (EMR) information and operation management system (OCS) information data, storing same in an integrated DB, recognizing, in real time, main data displayed on a dialyzer screen by using OCR technology, and storing the corresponding data in the integrated DB; a training data generation step (S20) of generating data by normalizing the data collected in the data collection step (10) in a form suitable for training a prediction model; a training step (S30) of training the prediction model; a data analysis step (S40) of determining statistical characteristics and patterns suitable for predicting the replacement cycle of the dialysis blood vessel; a risk level evaluation step (S50) of setting a threshold value and sequentially applying risk level evaluation models 1, 2, and 3 to evaluate, in a stepwise manner, the necessity for replacement; a prediction step (S60) of calculating a time point at which a main data item reaches a threshold level to predict a time point at which replacement is likely to be required; and an output step (S70) of classifying an output on the basis of a result of the prediction step (S60), visualizing the classified output, and providing the visualized output to medical staff.
Need to check novelty before this filing date? Find Prior Art