New Stretchy, Wearable Throat Sensor Processes and Predicts Health Data Faster

However, interpreting the vast array of data points they gather, such as muscle activity, heart rate, respiratory rate, and speech or swallowing patterns, can be challenging for healthcare providers. To streamline this process, engineering researchers have developed an advanced machine learning platform designed to analyze and accurately predict information collected by wearable devices more efficiently. This technology has been incorporated into a new flexible, wearable throat sensor designed to capture vibrations and electrical muscle impulses in the neck area, thereby monitoring a user's speech and swallowing patterns.

The wearable patch developed at Penn State (University Park, PA, USA) features a composite hydrogel electrode interface. This design ensures the device remains secure and functional on the skin's surface, even during movement, while still providing high-quality signal capture. The hydrogel, an insoluble and flexible material, is convenient to apply and remove. The hydrogel sensor operates by collecting data on vibrations and muscle movements, which is then processed by a machine learning algorithm for detailed analysis. Once the data is analyzed, it's transmitted to a specialized cloud interface, accessible remotely by healthcare professionals.

This innovative algorithm is designed to adapt and learn, meaning that after just one minute of gathering a patient's throat movement data and undergoing three hours of offline training, it can predict patient data with an accuracy exceeding 90%. This capability allows healthcare professionals to make quicker, more informed diagnoses and anticipate the potential effectiveness of treatments.

“Soft, stretchy on-throat devices are needed in the health care market to continuously monitor the muscle and swallowing movements of patients with throat conditions to properly diagnose and treat them,” said principal investigator Huanyu “Larry” Cheng. “The patient data is collected by the patch at different frequencies, depending on the statistic type, such as swallowing, speaking or respiration. The algorithm groups the four frequencies into one streamlined output, which makes the data much more useful for health care providers to quickly look at and judge.”

Related Links:
Penn State