A detection model for cognitive dysfunction based on volatile organic compounds from a large Chinese community cohort

Area of Science:

• Biochemistry
• Medical Diagnostics
• Data Science

Background:

• Cognitive dysfunction (CD) presents a significant public health challenge.
• Early and accurate screening for CD is crucial for timely intervention.
• Current screening methods can be invasive or resource-intensive.

Purpose of the Study:

• To investigate the potential of volatile organic compound (VOC) detection as a non-invasive screening tool for cognitive dysfunction (CD).
• To differentiate between individuals with CD and cognitively normal (CN) individuals using VOC profiles.
• To explore the correlation between VOCs, cognitive status, and plasma neurofilament light chain (NfL) levels.

Main Methods:

• Assessed cognitive function in 1467 participants.
• Detected volatile organic compounds (VOCs) from breath samples.
• Employed six machine learning algorithms for pattern recognition and classification.
• Measured plasma neurofilament light chain (NfL) levels.

Main Results:

• Distinct VOC patterns were identified between CD and CN groups.
• A VOC-based detection model achieved an area under the receiver-operating characteristic curve (AUC) of 0.876.
• Ten specific VOC ions showed significant differences between groups (p < 0.05).
• Three VOCs correlated significantly with plasma NfL levels (p < 0.005).
• A combined VOC and NfL model demonstrated superior discrimination power (AUC = 0.877).

Conclusions:

• Volatile organic compound (VOC) detection in exhaled breath shows promise as a novel screening tool for cognitive dysfunction (CD).
• The integration of VOC analysis with plasma NfL measurement enhances diagnostic accuracy.
• This approach offers a potential non-invasive solution for the challenges in CD screening.