Time considerations and outcomes in pediatric tracheostomy decannulation.

OBJECTIVE: The study objective is to identify factors that impact the time to decannulation in pediatric patients ages 0 through 18 years who are tracheostomy-dependent. METHODS: This retrospective chart review from January 1, 2005 through December 31, 2020 identified pediatric tracheostomy patients at a single pediatric institution. Data extracted included demographic, socioeconomic factors, and clinical characteristics. Multivariate regression and survival analysis were used to identify factors associated with successful decannulation and decreased time with tracheostomy. RESULTS: Of the 479 tracheostomy-dependent patients identified, 162 (33.8%) were decannulated. Time to decannulation ranged from 0.5 months to 189.2 months with median of 24 months (IQR 12.91-45.71). In the multivariate analysis, patients with bronchopulmonary dysplasia (p = 0.021) and those with Passy-Muir® Valve at discharge (p = 0.015) were significantly associated with decannulation. In contrast, neurologic comorbidities (p = 0.06), presence of gastrostomy tube (p < 0.001), or discharged on a home ventilator (p < 0.001) were associated with indefinite tracheostomy. When adjusting for age, sex, race, ethnicity, and insurance status, for every one month delay in establishment of outpatient otolaryngology care, time to decannulation was delayed by 0.5 months (p = 0.010). For each additional outpatient otolaryngology follow-up visit, time to decannulation increased by 3.36 months (p < 0.001). CONCLUSIONS: Decannulation in pediatric tracheostomy patients is multifactorial. While timely establishment of outpatient care did correlate with quicker decannulation, factors related to medical complexity may have a greater impact on time to decannulation. Our results can help guide institutional decannulation protocols, as well as provide guidance when counseling families regarding tracheostomy expectations.

Deep Learning for Predictive Analysis of Pediatric Otolaryngology Personal Statements: A Pilot Study.

OBJECTIVE: The personal statement is often an underutilized aspect of pediatric otolaryngology fellowship applications. In this pilot study, we use deep learning language models to cluster personal statements and elucidate their relationship to applicant rank position and postfellowship research output. STUDY DESIGN: Retrospective cohort. SETTING: Single pediatric tertiary care center. METHODS: Data and personal statements from 115 applicants to our fellowship program were retrieved from San Francisco Match. BERT (Bidirectional Encoder Representations From Transformers) was used to generate document embeddings for clustering. Regression and machine learning models were used to assess the relationship of personal statements to number of postfellowship publications per year when controlling for publications, board scores, Alpha Omega Alpha status, gender, and residency. RESULTS: Document embeddings of personal statements were found to cluster into 4 distinct groups by K-means clustering: 2 focused on "training/research" and 2 on "personal/patient anecdotes." Training clusters 1 and 2 were associated with an applicant-organization fit by a single pediatric otolaryngology fellowship program on univariate but not multivariate analysis. Models utilizing document embeddings alone were able to equally predict applicant-organization fit (receiver operating characteristic areas under the curve, 0.763 and 0.750 vs 0.419; P values >.05) as compared with models utilizing applicant characteristics and personal statement clusters alone. All predictive models were poor predictors of postfellowship publications per year. CONCLUSION: We demonstrate ability for document embeddings to capture meaningful information in personal statements from pediatric otolaryngology fellowship applicants. A larger study can further differentiate personal statement clusters and assess the predictive potential of document embeddings.

Socioeconomic factors associated with readmission following pediatric tonsillectomy.

OBJECTIVES: We aim to analyze factors associated with readmission after tonsillectomy to understand socioeconomic factors associated with readmission. METHODS: Single institution retrospective study of pediatric patients undergoing tonsillectomy over an 8 year study period, comparing patients who required readmission for bleeding concerns or pain/dehydration to those who did not require readmission. RESULTS: Of the 14,152 tonsillectomy patients, 508 (3.6%) were readmitted with 423 (83.3%) for bleeding concerns and 85 (16.7%) for pain or dehydration. Overall readmission was more likely in age >6 years (OR: 1.61, 95% CI: 1.34-1.92, P < 0.001), while poverty level below 10% (OR: 0.79, 95% CI: 0.66-0.94, P = 0.008) and parental college education above 25% (OR: 0.79, 95% CI: 0.65-0.96, P = 0.016) were associated with lower incidence of overall readmission. For patients readmitted for bleeding concerns, age >6 years (OR 1.66, 95% CI: 1.37-2.02, P < 0.001) was associated with readmission on multivariate analysis. Within the pain/dehydration group, African American race was associated with increased readmission rates, while poverty level below 10% and parental college education above 25% were associated with decreased readmission rates. CONCLUSION: Socioeconomic factors and age play a role in readmission rates following pediatric tonsillectomy.