Enhancing the assessment of deglutition function in preterm infants with mechano-acoustic analysis and machine learning: a narrative review.
Emily Bordier, Eric B Ortigoza
Recording and analyzing swallowing sounds and vibrations in preterm infants is based on 12 small studies with no data on how well it detects swallowing problems and no normal reference values.
It is not yet a validated clinical tool.
Key findings
1The entire evidence base consists of 12 records, 11 of which were observational studies with sample sizes from 6 to 155 infants. No study has reported diagnostic performance of this technique in preterm infants.
2No normative mechano-acoustic values have been established for healthy, term, non-dysphagic neonates, and no published study has linked these signals to functional swallowing outcomes in preterm infants.
3A systematic review and meta-analysis of cervical auscultation in adults and children reported sensitivity of 0.91 and specificity of 0.79 for detecting oropharyngeal aspiration, but this has not been validated in preterm infants.
Still to come
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only 12 records were identified, 11 of them observational, with sample sizes as small as 6 infants. No study reported diagnostic performance (sensitivity, specificity) of mechano-acoustic analysis in preterm infants. No normative values exist for healthy, term, non-dysphagic neonates, so there is no baseline to compare against. Recording was limited to a maximum of two minutes, while preterm oral feedings often exceed that duration. All studies required manual segmentation of swallows by investigators, introducing potential bias. No standardization of signal features exists across studies, limiting comparability. Most studies were conducted at or near term equivalence; only one was longitudinal and only one included a power analysis. No studies examined the oral or esophageal domains in preterm infants. Effects of respiratory support, gastroesophageal reflux, and feeding modality (breast vs. bottle) on signal integrity are unknown in this population. A single author performed the search, screening, and data extraction, with no independent verification.
Declared interests
The authors state they have no known conflicts of interest to disclose.
The easy way to misread this
Do not read this review as evidence that mechano-acoustic analysis is ready for clinical use in preterm infants. The review reports no diagnostic accuracy data in this population, no normative values for healthy neonates, and no validated link between these signals and functional swallowing outcomes. The one meta-analysis showing sensitivity of 0.91 and specificity of 0.79 was conducted in adults and children, not preterm infants.
Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →