Societe Des Produits Nestle S.a.

Harri Polonen

Juha Pajula

Michael Reuben Jedwab

Juha M Kortelainen

Rajat Mukherjee

A device can screen swallowing safety and swallowing efficiency. The device includes a processor configured to receive accelerometry data, determine a an A-P and S-I signal summed spectrogram from the accelerometry data, and perform one or more of identifying a missing swallow, identifying that the data was clipped from the start, identifying that the data was clipped from the end, or identifying that the data contains noise. The device can have a user interface configured to provide one or more outputs including at least one of audio or graphics based on these identifications. If the data does not contain these signal quality issues, the device can compare the data against preset classification criteria defined for each of swallowing safety and swallowing efficiency and thus classify each of the swallowing events with a swallowing safety classification and a swallowing efficiency classification.

Methods and devices for determining signal quality for a swallowing impairment classification model

A method can classify cervical accelerometry data acquired for a swallowing event to identify a possible swallowing impairment in a candidate. The method can include receiving axis-specific vibrational data for an anterior-posterior (A-P) axis and a superior-inferior (S-I) axis and representative of the swallowing event, for example from an accelerometer operatively coupled to a processing module that is a local or remote computing device. The method can include extracting one or more specific meta-features from the data and then outputting from the processing module a classification of the swallowing event based on the extracted meta-features, for example a first classification indicative of normal swallowing or a second classification indicative of possibly impaired swallowing.

Methods and devices using meta-features extracted from accelerometry signals for swallowing impairment detection

A method classifies vibrational data acquired for a swallowing event to identify a possible swallowing impairment in a candidate. The method includes receiving axis-specific vibrational data for an anterior-posterior (A-P) axis and a superior-inferior (S-I) axis and representative of the swallowing event, for example from a sensor operatively coupled to a processing module that is a local or remote computing device. A portion of the axis-specific vibrational data for the A-P axis can be combined with a portion of the axis-specific vibrational data for the S-I axis on the processing module using one or more of linear combination, squared (power) sum, moving window correlation of the two signals, local minimum or local maximum of the two signals, and trigonometric relation. The method can include outputting from the processing module a classification of the swallowing event based on the combined vibrational data.

Growing community of inventors

Tampere, Finland

Harri Polonen