AI and ML
Sampling a patient’s breath could save lives and emergency room resources
Many people worry about what AI knows, but what about an AI nose that can sniff out what diseases you might be suffering from?
Ainos, an AI and biotech company developing odor technology, is collaborating with National Taiwan University (NTU) to study whether its platform can help diagnose patients by analyzing volatile organic compounds (VOCs) in exhaled breath.
The year-long research effort, which begins in July, will examine people who complain of dyspnea, or shortness of breath, which is said to be one of the most common symptoms seen in emergency departments.
Dyspnea can be a symptom of many diseases, including acute exacerbation of chronic obstructive pulmonary disease (AECOPD) and acute decompensated heart failure (ADHF), each of which requires different treatments.
Ainos and NTU hope to develop and evaluate a VOC-based breathprint analysis system to detect AECOPD and ADHF in patients.
Ainos’ Smell AI platform relies on an AI Nose module with multiple microelectromechanical systems (MEMS) sensors and an integrated digital processor. Ainos said the presence of a detectable gas increases the sensor’s resistance, which is converted into a digital signal that is interpreted in the same way that the human nose interprets scent.
Its interpretation is handled by a proprietary scent language model developed to learn, classify, and contextualize complex scent patterns.
“AI Nose was originally developed with medical diagnostic applications in mind, where non-invasive sensing, accuracy and real-world validation are essential,” said Eddy Tsai, CEO of Ainos.
“This research program brings that experience back to high-value clinical settings and extends our scent AI platform into digital breath intelligence.”
The company isn’t content with the term “digital breath intelligence,” which it must confess is unfamiliar to them, but it positions this work as part of a broader vision to “build odor ID data and odor language model capabilities across healthcare, industrial, and physical AI environments.”
If successful, this study could help create a respiratory print database for dyspnea and support future research in emergency, outpatient, and even home monitoring settings.
This study follows a separate program to test AI Nose in the emergency department of National Taiwan University Hospital. The system is in place to monitor respiratory infections and overcrowding in waiting rooms, treatment areas and observation zones. ®
