Environmental Personal Exposure Clusters to Investigate Multiple Sclerosis and Amyotrophic Lateral Sclerosis...

Area of Science:

• Environmental Science
• Neurology
• Data Science

Background:

• Prognosis for Multiple Sclerosis (MS) and Amyotrophic Lateral Sclerosis (ALS) is challenging due to limited data and variability.
• Environmental factors are increasingly recognized for their potential to influence disease progression and patient outcomes.

Purpose of the Study:

• To determine if personal environmental exposure data can be categorized into stable patterns for improved neurological disease prognosis.
• To investigate the utility of wearable air quality sensors in capturing patient-specific environmental exposures.

Main Methods:

• A multicenter cohort of 293 MS and ALS patients used Atmotube air quality sensors.
• Volatile Organic Compound (VOC) time series data were normalized and analyzed using Dynamic Time Warping for temporal similarity.
• Hierarchical clustering identified five distinct daily exposure patterns, profiled by sensor data and patient self-reports.

Main Results:

• Five stable daily air quality exposure clusters were identified in MS and ALS patients.
• These clusters correlated with environmental variables (season, humidity, temperature) and patient activities (work status, time outdoors).
• The identified clusters demonstrated potential for interpolating missing sensor data and generating context-aware exposure estimates.

Conclusions:

• Personalized environmental exposure patterns can be reliably identified using wearable sensors.
• These environmental data clusters offer a novel approach to enhance prognostic modeling for neurodegenerative diseases like MS and ALS.
• Integrating environmental data strengthens the understanding of disease trajectories beyond clinical variables.