Beyond the Clinic: Leveraging Speech Acoustics and Phonetics for Cognitive Monitoring in PKU

Phenylketonuria (PKU) is one of the most common genetic metabolic disorders, characterized by the body’s inability to properly metabolize phenylalanine (Phe). Without proper management, elevated Phe levels can lead to cognitive impair- ments, executive dysfunction, and neuropsychiatric symptoms, including anxiety, depression, and attention deficits. Additionally, uncontrolled PKU may result in motor dysfunction, seizures, and white matter abnormalities, further impacting quality of life. Given these risks, regular monitoring is essential to prevent neurological decline and ensure optimal cognitive and behavioral outcomes. This is typically done through finger-prick blood samples, but this method can be invasive and burdensome. As a less intrusive alternative, Ecological Momentary Assessments have been explored in PKU to provide a more detailed and dynamic representation of cognitive fluctuations in daily life. When combined with speech analysis, this approach could offer a more accessible biomarker for cognitive monitoring. In this study, we analyzed 95 speech samples, including spontaneous speech responses and verbal fluency tasks, collected from 20 individuals with PKU across six sessions. Our results show that acoustic and phonetic features extracted from these responses correlate with cognitive assessments (up to r=0.51) and blood Phe levels (r = 0.38). These findings highlight the potential of speech-based biomarkers for assessing cognitive function in PKU and offer a promising non-invasive alternative for disease monitoring