RESUMEN
Purpose: Strategies for facilitating safe and functional bottle feeding in children with dysphagia include selecting nipples that reduce flow rate, pacing, altered positioning, and thickening liquid consistencies. We aimed to determine the impact of slightly thick liquids on swallowing through retrospective review of a convenience sample of clinical videofluoroscopic swallowing studies (VFSS) from 60 bottle-fed children (21 boys and 39 girls, mean age of 9.9 months) referred due to suspected aspiration. Method: Eligible VFSS exams were those in which the child swallowed both thin and slightly thick barium (40% w/v Varibar barium) using the same nipple. VFSS sequences (i.e., uninterrupted portions of the VFSS recording) were randomly assigned in duplicate for rating by trained raters; discrepancies were resolved by consensus. Parameters measured included number of swallows/sequence, sucks/swallow, swallow and sequence duration, number and timing of penetration or aspiration events, laryngeal vestibule closure integrity, and pharyngeal residue. Chi-square tests, linear mixed-model analyses of variance, and Wilcoxon signed-ranks tests identified consistency effects. Results: There were no aspiration events in these recordings. Slightly thick liquids resulted in significantly fewer penetration events (p < .05), increased sucks/swallow, fewer swallows/sequence, and longer swallow and sequence durations. The number of children with ≥ 1 sequence showing pyriform sinus residue was significantly higher with slightly thick liquids. Conclusions: Slightly thick liquids can be effective in reducing penetration in bottle-fed children with dysphagia. However, slightly thick liquids may also lead to a safety-efficiency trade-off, with increased risk of pyriform sinus residue. Thickening for children with dysphagia should be considered only when other approaches are not effective. Overthickening should be avoided to limit negative impact on swallowing efficiency.
RESUMEN
OBJECTIVES: Misdiagnosis of acute and chronic otitis media in children can result in significant consequences from either undertreatment or overtreatment. Our objective was to develop and train an artificial intelligence algorithm to accurately predict the presence of middle ear effusion in pediatric patients presenting to the operating room for myringotomy and tube placement. METHODS: We trained a neural network to classify images as " normal" (no effusion) or "abnormal" (effusion present) using tympanic membrane images from children taken to the operating room with the intent of performing myringotomy and possible tube placement for recurrent acute otitis media or otitis media with effusion. Model performance was tested on held-out cases and fivefold cross-validation. RESULTS: The mean training time for the neural network model was 76.0 (SD ± 0.01) seconds. Our model approach achieved a mean image classification accuracy of 83.8% (95% confidence interval [CI]: 82.7-84.8). In support of this classification accuracy, the model produced an area under the receiver operating characteristic curve performance of 0.93 (95% CI: 0.91-0.94) and F1-score of 0.80 (95% CI: 0.77-0.82). CONCLUSIONS: Artificial intelligence-assisted diagnosis of acute or chronic otitis media in children may generate value for patients, families, and the health care system by improving point-of-care diagnostic accuracy. With a small training data set composed of intraoperative images obtained at time of tympanostomy tube insertion, our neural network was accurate in predicting the presence of a middle ear effusion in pediatric ear cases. This diagnostic accuracy performance is considerably higher than human-expert otoscopy-based diagnostic performance reported in previous studies.