Dynamic infant oral-motor assessment and feedback
A monitoring device may include a housing with: a first connector that mechanically couples to a baby bottle; and a second connector that mechanically couples to a nipple; a tube having a first opening defined by a first edge proximate to the first connector and a having second opening defined by a second edge proximate to the second connector. Moreover, the housing may include a set of sensors that perform measurements associated with feeding. During operation, the monitoring device may perform the measurements while a baby is performing the feeding, where the measurements are associated with sucking, swallowing and breathing by the baby. Then, the monitoring device may dynamically provide feedback based at least in part on the measurements. For example, the feedback may include: change to the feeding (such as when to dynamically pause the feeding), a change to a size of the nipple or the baby bottle, etc.
1 . A monitoring device, comprising a housing, wherein the housing comprises:
a first connector configured to mechanically couple to a baby bottle;
a second connector configured to mechanically couple to a nipple;
a tube having a first opening defined by a first edge proximate to the first connector and a having second opening defined by a second edge proximate to the second connector; and
a set of sensors configured to perform measurements associated with feeding, wherein the monitoring device is configured to:
perform the measurements while a baby is performing the feeding, wherein the measurements are associated with sucking, swallowing and breathing by the baby, and wherein the set of sensors comprise an acoustic sensor and an inertial measurement unit, a pressure sensor, or both, and the measurements comprise measurements in an acoustic band of frequencies between 50-20,000 Hz; and
dynamically provide feedback based at least in part on a modal decomposition of mel-frequency cepstral coefficients (MFCC) corresponding to at least a portion of the measurements and an output from a pretrained neural network that uses the measurements as an input, wherein the modal decomposition comprises variational mode decomposition (VMD) of at least the portion of the measurements, wherein the feedback comprises: when to dynamically pause the feeding, a change to a flow rate during the feeding, a change to a size of the nipple, a change to a size of the baby bottle, a change to promote stronger sucking by the baby, a change to an anatomical position of the baby during the feeding, a recommendation for a swallowing study, a recommendation for the baby to use a pacifier between instances of the feeding, diagnostic information about a possible tongue-tie, diagnostic information about possible excessive air swallowing into the stomach or a recommendation for additional therapy for the baby.
2 . The monitoring device of claim 1 , wherein the feedback comprises: signals or instructions to guide a feeder to regulate a number of sucks per burst or sequence of swallows, a respiratory rate or a duration of bursts and pauses or time intervals between swallows by adjusting a flow rate dial, an angle of the baby bottle or both.
3 . The monitoring device of claim 1 , wherein at least the portion of the measurements correspond to acoustics of the supra-glottal and sub-glottal vocal tract and the pretrained neural network is configured to distinguish suck and swallow sounds from inspiration and expiration.
4 . The monitoring device of claim 1 , wherein pretrained analysis model comprises a neural network.
5 . The monitoring device of claim 1 , wherein the monitoring device comprises an interface circuit configured to wirelessly communicate with an electronic device, which is separate from the monitoring device; and
wherein the monitoring device is configured to:
provide, addressed to the electronic device, information associated with the measurements; and
may receive the feedback associated with the electronic device.
6 . The monitoring device of claim 1 , wherein the monitoring device is configured to provide the feedback about a quality of the feeding while the baby is feeding.
7 . The monitoring device of claim 1 , wherein the monitoring device comprises an integrated circuit configured to analyze the measurements, determine the feedback, or both.
8 . The monitoring device of claim 1 , wherein the set of sensors comprise: an accelerometer, a light detection and ranging (LiDAR) sensor or an infrared sensor.
9 . The monitoring device of claim 1 , wherein the feedback corresponds to or comprises one or more oral-motor metrics and the one or more oral-motor metrics comprise: tongue kinetics, a force of sucking, a suction and expression pressure, a flow rate, a sucking/swallowing/breathe ratio, micro-gagging, a pressure of lip seal, a pressure of tongue, or a distance from the monitoring device to a top of a fluid level line of the baby bottle.
10 . The monitoring device of claim 1 , wherein the feedback comprises diagnostic information associated with possible feeding/oromotor difficulties.
11 . The monitoring device of claim 10 , wherein the diagnostic information comprises a feeding performance score.
12 . The monitoring device of claim 10 , wherein the diagnostic information comprises: possible developmental delays or possible feeding difficulties.
13 . The monitoring device of claim 12 , wherein the possible feeding difficulties comprise: reflux, colic, or a type of oral-motor functional impairment.
14 . The monitoring device of claim 1 , wherein the feedback comprises one or more feeding quality metrics and the one or more feeding quality metrics comprise: oral pressure, feeding consistency, or a sucking/swallowing/breath rate.
15 . The monitoring device of claim 1 , wherein the feedback comprises a normalized maturity index corresponding to a ratio of a developmental metrics of the baby and a chronological age of the baby.
16 . A non-transitory computer-readable storage medium for use in conjunction with a monitoring device configured to couple to a baby bottle and a nipple, the monitoring device comprising a set of sensors configured to perform measurements associated with feeding, the computer-readable storage medium configured to store program instructions that, when executed by the monitoring device, causes the monitoring device to perform one or more operations comprising:
performing, using the set of sensors, the measurements associated with the feeding while a baby is performing the feeding, wherein the measurements are associated with sucking, swallowing and breathing by the baby, and wherein the set of sensors comprise an acoustic sensor and an inertial measurement unit, a pressure sensor, or both, and the measurements comprise measurements in an acoustic band of frequencies between 50-20,000 Hz; and
dynamically providing feedback based at least in part on a modal decomposition of mel-frequency cepstral coefficients (MFCC) corresponding to at least a portion of the measurements and an output from a pretrained neural network that uses the measurements as an input, wherein the modal decomposition comprises variational mode decomposition (VMD) of at least the portion of the measurements, wherein the feedback comprises: when to dynamically pause the feeding, a change to a flow rate during the feeding, a change to a size of a nipple, a change to a size of a baby bottle, a change to promote stronger sucking by the baby, a change to an anatomical position of the baby during the feeding, a recommendation for a swallowing study, a recommendation for the baby to use a pacifier between instances of the feeding, diagnostic information about a possible tongue-tie, diagnostic information about possible excessive air swallowing into the stomach or a recommendation for additional therapy for the baby.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein at least the portion of the measurements correspond to acoustics of the supra-glottal and sub-glottal vocal tract and the pretrained neural network distinguishes suck and swallow sounds from inspiration and expiration.
18 . A method for providing feedback, comprising:
by a monitoring device coupled to a baby bottle and a nipple, the monitoring device comprising a set of sensors that perform measurements associated with feeding:
performing, using the set of sensors, the measurements associated with the feeding while a baby is performing the feeding, wherein the measurements are associated with sucking, swallowing and breathing by the baby, and wherein the set of sensors comprise an acoustic sensor and an inertial measurement unit, a pressure sensor, or both, and the measurements comprise measurements in an acoustic band of frequencies between 50-20,000 Hz; and
dynamically providing feedback based at least in part on a modal decomposition of mel-frequency cepstral coefficients (MFCC) corresponding to at least a portion of the measurements and an output from a pretrained neural network that uses the measurements as an input, wherein the modal decomposition comprises variational mode decomposition (VMD) of at least the portion of the measurements, wherein the feedback comprises: when to dynamically pause the feeding, a change to a flow rate during the feeding, a change to a size of a nipple, a change to a size of a baby bottle, a change to promote stronger sucking by the baby, a change to an anatomical position of the baby during the feeding, a recommendation for a swallowing study, a recommendation for the baby to use a pacifier between instances of the feeding, diagnostic information about a possible tongue-tie, diagnostic information about possible excessive air swallowing into the stomach or a recommendation for additional therapy for the baby.
19 . The method of claim 18 , wherein at least the portion of the measurements correspond to acoustics of the supra-glottal and sub-glottal vocal tract and the pretrained neural network distinguishes suck and swallow sounds from inspiration and expiration.
20 . The method of claim 18 , wherein the feedback comprises: signals or instructions to guide a feeder to regulate a number of sucks per burst or sequence of swallows, a respiratory rate or a duration of bursts and pauses or time intervals between swallows by adjusting a flow rate dial, an angle of the baby bottle or both.