Vaden Masrani, Gabriel Murray, Thalia Shoshana Field, and Giuseppe Carenini, Canadian AI 2017: Advances in Artificial Intelligence pp 248-259.
Lexical and acoustic markers in spoken language can be used to detect mild cognitive impairment (MCI), a condition which is often a precursor to dementia and frequently causes some degree of dysphasia. Research to develop such a diagnostic tool for clinicians has been hindered by the scarcity of available data.
This work uses domain adaptation to adapt Alzheimer’s data to improve classification accuracy of MCI. We evaluate two simple domain adaptation algorithms, AUGMENT and CORAL, and show that AUGMENT improves upon all baselines. Additionally we investigate the use of previously unconsidered discourse features and show they are not useful in distinguishing MCI from healthy controls.
Our main positive result is that the AUGUMENT domain adaptation algorithm outperformed all baseline algorithms and improved the F-measure by more than 7% over models trained on MCI data alone.