相关实验视频
Updated: Sep 9, 2025

Slicing and Culturing Pig Hearts under Physiological Conditions
Published on: March 20, 2020
在心脏毒性评估中多任务学习的专家组合
Edoardo Luca Viganò1, Mateusz Iwan2, Erika Colombo2
1Laboratory of Environmental Toxicology and Chemistry, Department of Environmental Health Sciences, Instituto Di Ricerche Farmacologiche Mario Negri IRCSS, 20156, Milan, Italy. edoardo.vigano@marionegri.it.
人工智能 (AI) 和机器学习 (ML) 通过预测化学心脏毒性来推进毒理学. 多任务神经网络模型在识别潜在的心脏风险方面具有很高的准确性,支持更安全的化学评估.
科学领域:
- 毒理学
- 生物化学
- 生物医学研究
- 人工智能
- 机器学习
背景情况:
- 心血管疾病是全球首要的死亡原因.
- 化学物质如环境污染物,杀虫剂,食品添加剂和药物,
- 传统的毒理学测试耗时,资源密集,缺乏可扩展性.
研究的目的:
- 开发和评估用于预测化学心脏毒性的人工智能模型.
- 在综合测试和评估方法 (IATA) 中探索多任务神经网络的好处.
- 减少对传统体内测试方法的依赖.
主要方法:
- 使用人工智能和机器学习方法.
- 开发了一个多任务神经网络模型,结合了专家混合 (MoE) 架构.
- 在12个心脏毒性终点上训练并验证了该模型.
主要成果:
- 多任务模型的表现优于单任务基线模型.
- 在多种心脏毒性终点上实现了高性能.
- 最好的模型显示了78%的平衡精度,80%的灵敏度和76%的特异性.
结论:
- 一个先进的多任务模型有效预测小分子诱导的心脏毒性机制.
- 该模型提供了广泛的机械覆盖范围和与最先进的方法相美的性能.
- 这种人工智能模型可以在新方法方法 (NAM) 中作为一个有价值的组件来优先考虑化学安全测试.
更多相关视频
08:03Hybrid Cell Analysis System to Assess Structural and Contractile Changes of Human iPSC-Derived Cardiomyocytes for Preclinical Cardiac Risk Evaluation
Published on: October 20, 2022
14:03High-Throughput Cardiotoxicity Screening Using Mature Human Induced Pluripotent Stem Cell-Derived Cardiomyocyte Monolayers
Published on: March 24, 2023
相关概念视频
Multicompartment Models: Overview
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
Pharmacokinetic Models: Comparison and Selection Criterion
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Pharmacokinetic Models: Overview
There are three primary types of models: empirical, compartment, and physiological. Empirical models, with minimal...
Cardiomyopathy V: Interprofessional Care
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
Cardiopulmonary Resuscitation IV: Pharmacological Management