Related Experiment Video
Updated: Jun 4, 2026
Non-Nutritive Suck Parameters Measurements Using a Custom Pressure Transducer System
Published on: April 19, 2024
Enhancing the assessment of deglutition function in preterm infants with mechano-acoustic analysis and machine
Emily Bordier1, Eric B Ortigoza2
1Applied Clinical Research, School of Health Professions, UT Southwestern Medical Center.
Insights
Mechano-acoustic analysis shows promise for assessing swallowing in preterm infants. Further research is needed to develop machine learning tools for accurate diagnosis of deglutition dysfunction.
Area of Science:
- Neonatal physiology
- Swallowing biomechanics
- Computational diagnostics
Background:
- Clinical indicators for deglutition dysfunction in preterm infants are not well-defined.
- Mechano-acoustic analysis (e.g., cervical auscultation, accelerometry) shows potential for classifying swallow physiology.
- Machine learning (ML) enhances diagnostic performance for complex deglutition data in various populations.
Purpose of the Study:
- To investigate the feasibility and usability of mechano-acoustic analysis combined with ML for identifying indicators of deglutition impairment in preterm infants.
- To improve diagnostic accuracy and clinical prediction of clinical swallow evaluations (CSEs) in this population.
Main Methods:
- A narrative review of studies was conducted using PubMed and Ovid databases.
- No filters were applied to the publication year.
Main Results:
- Twelve relevant records were identified.
- Preliminary studies indicate significant findings in maturational changes of mechano-acoustic deglutition features.
- Research on ML for mechano-acoustic analysis in preterm infants is currently lacking, with no published studies on deglutition dysfunction indicators or normative data for healthy neonates.
Conclusions:
- Mechano-acoustic analysis is a feasible technique for evaluating deglutition in preterm infants.
- Future longitudinal studies need to establish normative values, correlate signals with kinematics, and standardize features to enhance clinical utility.
- Further research is required to assess the diagnostic performance of ML algorithms for improved classification and prediction of deglutition function in preterm infants.
Purpose:
Clinical indicators of deglutition dysfunction within the context of maturation are not well-defined for preterm infants. Mechano-acoustic analysis utilizing cervical auscultation or accelerometry has shown potential for accurate classification of swallow physiology across the life span. Machine learning algorithms increase diagnostic performance and facilitate analysis of more complex deglutition data in adult and pediatric populations. This narrative review will investigate the feasibility and usability of mechano-acoustic analysis combined with machine learning to identify indicators of deglutition impairment in preterm infants to increase diagnostic accuracy and clinical prediction of clinical swallow evaluations (CSEs).
Methods:
Databases searched included PubMed and Ovid. No filters were placed on year of publication.
Results:
Twelve relevant records were retrieved for this review. Preliminary studies investigating maturational changes in mechano-acoustic features of deglutition have yielded significant findings. Research utilizing machine learning to support mechano-acoustic analysis in preterm infants is lacking. There are no published studies investigating indicators of deglutition dysfunction in preterm infants and no normative data for healthy, term non-dysphagic neonates.
Conclusions:
Mechano-acoustic analysis is a feasible technique to investigate deglutition performance in preterm infants. Identification of normative values, temporal correlation of signals with deglutition kinematics, and standardization of relevant features in future longitudinal studies will enhance clinical utility. Further study is needed to determine diagnostic performance of machine learning algorithms to enhance classification and prediction of deglutition function in preterm infants.
