DEEP LEARNING AND PHYSIOLOGY BASED APPROACH TO DERIVE AND LINK OBSTRUCTIVE SLEEP APNOEA PHENOTYPES AND SYMPTOMATOLOGY

基于深度学习和生理学的方法来推导和关联阻塞性睡眠呼吸暂停表型和症状

• 批准号: nhmrc : 2001729
• 金额: $ 40.3万
• 依托单位国家: 澳大利亚
• 项目类别: Ideas Grants
• 财政年份: 2021
• 资助国家: 澳大利亚
• 起止时间: 2021-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://researchdata.edu.au/deep-learning-and-and-symptomatology/1779828
• 关键词: DEEP; LEARNING; PHYSIOLOGY; BASED; APPROACH

Obstructive sleep apnoea (OSA) is a highly prevalent nocturnal breathing disorder strongly related to daytime sleepiness, accident risk and reduced quality of life. However, the current severity index, the apnoea-hypopnoea index, poorly predicts daytime sleepiness and vigilance. In this project we elegantly combine physiological insight and artificial intelligence to develop and evaluate novel clinically applicable computational tools for detailed quantification of OSA severity and its symptoms.

阻塞性睡眠呼吸暂停（OSA）是一种高度流行的夜间呼吸障碍，与白天嗜睡、事故风险和生活质量下降密切相关。然而，目前的严重程度指数，呼吸暂停低通气指数，预测白天嗜睡和警觉性差。在这个项目中，我们优雅地结合联合收割机生理洞察力和人工智能，开发和评估新的临床适用的计算工具，详细量化OSA的严重程度及其症状。