深度学习模型InceptionTime的应用用于预测恶心,吐,腹和便秘,使用胃肠起器活性药物数据库 (GIPADD)
Hephaes Chuen Chau1, Julia Yuen Hang Liu2,3, John Anthony Rudd1,4
1Gut Rhythm R&D (Hong Kong) Limited, Hong Kong, SAR, People's Republic of China.
Scientific reports
|April 16, 2025
概括
预测恶心等药物不良反应 (ADR) 是一个挑战. 这项研究使用深度学习和胃肠鼓动器活动药物数据库 (GIPADD) 来从电生理学数据中准确预测药物诱导的副作用.
科学领域:
- 药理学和毒理学 药理学和毒理学
- 计算生物学 计算生物学
- 生物医学工程 生物医学工程
背景情况:
- 准确的临床前预测药物不良反应 (ADRs),如胃肠道影响,仍然是药物开发中的一个重大挑战.
- 胃肠鼓动器活动药物数据库 (GIPADD) 为药物研究提供了一种新的,大规模的电生理学数据资源.
- 现有的方法很难从复杂的生物信号中可靠地预测ADR.
研究的目的:
- 探索使用来自胃肠组织的原始电生理记录来预测特定药物不良反应 (ADRs) 的可行性.
- 开发和验证一种深度学习模型,用于分析药物对胃肠道心脏起器活动的影响.
- 评估模型对恶心,吐,腹和便秘等常见副作用的预测性能.
主要方法:
- 利用了胃肠鼓动器活动药物数据库 (GIPADD),包含11943个数据集中的172种药物的电生理学概况.
- 应用了最先进的深度学习模型,修改了InceptionTime分类器 (ICT),用于原始电生理记录的时间序列分类.
- 纳入药物度和组织类型作为共变量,并使用负控制和外部验证来确保模型的稳定性.
主要成果:
- 性能最好的模型,一个由五个ICT分类器组成的组合,在预测恶心 (0.87),吐 (0.89),腹 (0.85) 和便秘 (0.91) 方面取得了很高的准确性.
- 通过药物的精度值在0.88到0.99之间,接收器操作特征曲线 (AUROC) 下的区域值达到了0.96,显示出强大的预测能力.
- 在混合标签 (负控) 上训练的模型表现明显较低,证实了ICT分类器识别真正ADR相关特征的能力.
结论:
- 深度学习模型,特别是InceptionTime分类器,可以有效地从原始电生理学数据中预测药物不良反应.
- 结合先进的计算方法,GIPADD提供了一个强大的工具,可以加速临床前药物安全性评估.
- 这种方法具有显著的潜力,可以通过可靠地分析药物对胃肠道功能的影响来改善药物开发管道.
相关概念视频
Assessment of the Gastrointestinal System II: Health Perception Pattern
57
Assessing the gastrointestinal (GI) system is a complex process that begins with collecting subjective data. This data, collected through patient interviews, provides crucial insights into the patient's health history, perception patterns, and lifestyle habits, all contributing significantly to GI health.
Health Perception Patterns
Health perception patterns offer valuable insights into a patient's lifestyle habits and how they may impact their GI health. These patterns include:
Health Perception Patterns
Health perception patterns offer valuable insights into a patient's lifestyle habits and how they may impact their GI health. These patterns include:
57
Assessment of the Gastrointestinal System I: Subjective Data
126
Assessing the gastrointestinal (GI) system is a complex process that begins with collecting subjective data. This data, collected through patient interviews, provides crucial insights into the patient's health history, perception patterns, and lifestyle habits, all contributing significantly to GI health.
Health History
The initial step in assessing the GI system is obtaining a comprehensive health history. This includes inquiring about the patient's history or presence of problems...
Health History
The initial step in assessing the GI system is obtaining a comprehensive health history. This includes inquiring about the patient's history or presence of problems...
126


