The use of spontaneous language to derive appropriate digital markers has
become an emergent, promising and non-intrusive method to diagnose and monitor
dementia. Here we propose methods to capture language coherence as a
cost-effective, human-interpretable digital marker for monitoring cognitive
changes in people with dementia. We introduce a novel task to learn the
temporal logical consistency of utterances in short transcribed narratives and
investigate a range of neural approaches. We compare such language coherence
patterns between people with dementia and healthy controls and conduct a
longitudinal evaluation against three clinical bio-markers to investigate the
reliability of our proposed digital coherence marker. The coherence marker
shows a significant difference between people with mild cognitive impairment,
those with Alzheimer's Disease and healthy controls. Moreover our analysis
shows high association between the coherence marker and the clinical
bio-markers as well as generalisability potential to other related conditions.

使用自发语言作为适当的数字标记，对诊断和监测痴呆症进行非侵入性方法已成为一种新兴、有前景的方法。本文提出了以捕捉语言连贯性作为一种经济实惠、人类可解读的数字标记，用于监测患有痴呆症的个体的认知变化的方法，并介绍了一项学习短传录叙述中话语的时间逻辑一致性的新任务，并研究了一系列神经方法。通过比较痴呆症患者和健康对照组的语言连贯性模式，并针对三个临床生物标志物进行纵向评估，以调查我们提出的数字连贯性标记的可靠性。连贯性标记在轻度认知障碍、阿尔茨海默病和健康对照组之间表现出显著差异。此外，我们的分析显示连贯性标记与临床生物标志物具有很高的关联性，并具有适用于其他相关疾病的潜力。