Digital Health: Innovative engineering technologies to improve the understanding and management of fatigue

疲劳被认为是一种“最终的共同途径”：一种模糊的临床症状，可由许多不同的疾病和机制引起。我们对疲劳的有限理解部分源于疲劳的主观性和波动性，以及与“疲劳”相关的参数的复杂相互作用，如睡眠、锻炼和情绪。这个项目将研究感官技术，以客观、准确和不引人注意的方式测量疲劳性，作为疲劳的指标。这些测量将与感知数据(活动水平、睡眠、心率和其他)和个人的自我报告相关联。我们将获得有关人类疲劳体验模式的细粒度细节。结果将揭示是否存在明显的、与临床相关的疲劳表型。我们还将使用纵向研究(在几周的时间内密切研究参与者)。到目前为止，纵向疲劳的研究一直受到统计分析方法(如多水平建模)的限制，这些方法无法发现疲劳与相关生活方式因素之间随时间推移而产生的微妙或复杂的关系。我们将使用人工智能算法来帮助分析和分类感知数据、自我报告和定性数据中的这些相关性。

Fatigue is considered as a "final common pathway": a vague clinical symptom that can result from many different diseases and mechanisms. Our limited understanding of fatigue stems, in part, from its subjective and fluctuating nature and its complex interplay of parameters associated with "tiredness" such as sleep, exercise, and mood. This project will investigate sensory technologies to objectively, accurately and unobtrusively measure fatiguability, as an indicator of fatigue. These measurements will be correlated to sensed data (activity levels, sleep, heart rate, and others) and individuals' self-reports. Granular details will be obtained about patterns in the human fatigue experience. The results will reveal whether there could be distinct, clinically relevant fatigue phenotypes. We will also use longitudinal research (studying participants closely over a several week period). To date, longitudinal fatigue research been limited by statistical analysis methods (such as multilevel modelling) which are unable to detect subtle or complex relationships between fatigue and related life-style factors over time. We will use artificial intelligence algorithms to help analyse and classify these correlations within the sensed data, self-reports and qualitative data.