A method and system for preparing monodisperse microgels for 3D hepatotoxicity testing, medium

By employing adaptive neural networks and model predictive control methods, combined with electrohydrodynamic principles and an automated platform, the problems of monodispersity and parameter optimization in the preparation of hydrogel microspheres were solved, resulting in an efficient and automated 3D hepatotoxicity testing model.

CN122091015BActive Publication Date: 2026-07-10SUZHOU INST OF BIOMEDICAL ENG & TECH CHINESE ACADEMY OF SCI

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
SUZHOU INST OF BIOMEDICAL ENG & TECH CHINESE ACADEMY OF SCI
Filing Date
2026-04-22
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing hydrogel microsphere preparation technologies suffer from non-uniform size, poor monodispersity, complex parameter optimization, and low efficiency, making it difficult to meet the needs of high-throughput drug screening, and lacking fully automated control throughout the process.

Method used

A method combining adaptive neural networks and model predictive control was adopted to prepare microgel spheres based on electrohydrodynamics principles. An integrated automated platform was used to detect and optimize preparation parameters in real time, achieving fully automated operation of the entire process.

Benefits of technology

It improves the monodispersity and experimental consistency of microgel spheres, enhances the scientific rigor and repeatability of the 3D hepatotoxicity testing model, simplifies the process optimization, and reduces human intervention and operational errors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122091015B_ABST
    Figure CN122091015B_ABST
Patent Text Reader

Abstract

The application discloses a 3D hepatotoxicity test monodisperse microgel preparation method and system and medium, and belongs to the technical field of 3D cell culture and drug screening. The system comprises a preparation module, a statistical analysis module, a material processing module and a control system; the method comprises the following steps: collecting historical data to train an adaptive neural network, and establishing a mapping relationship between control parameters and microgel quality indexes; taking the neural network as a prediction model, and solving optimal control input through a model predictive controller; executing microgel preparation; collecting images in real time to obtain actual particle sizes and variation coefficients and feeding back; using new data for incremental updating of the neural network; and iteratively forming a closed-loop optimization process. The application realizes multi-parameter adaptive optimization through an artificial intelligence algorithm, solves the problem of artificial groping of different hydrogel material parameters, improves the monodispersity and consistency of the microgel, and realizes full-process automation.
Need to check novelty before this filing date? Find Prior Art