Application of Statistical Analysis and Machine Learning to Identify Infants' Abnormal Suckling Behavior.

OBJECTIVE: Identify infants with abnormal suckling behavior from simple non-nutritive suckling devices. BACKGROUND: While it is well known breastfeeding is beneficial to the health of both mothers and infants, breastfeeding ceases in 75 percent of mother-child dyads by 6 months. The current standard of care lacks objective measurements to screen infant suckling abnormalities within the first few days of life, a critical time to establish milk supply and successful breastfeeding practices. MATERIALS AND METHODS: A non-nutritive suckling vacuum measurement system, previously developed by the authors, is used to gather data from 91 healthy full-term infants under thirty days old. Non-nutritive suckling was recorded for a duration of sixty seconds. We establish normative data for the mean suck vacuum, maximum suck vacuum, suckling frequency, burst duration, sucks per burst, and vacuum signal shape. We then apply computational methods (Mahalanobis distance, KNN) to detect anomalies in the data to identify infants with abnormal suckling. We finally provide case studies of healthy newborn infants and infants diagnosed with ankyloglossia. RESULTS: In a series of case evaluations, we demonstrate the ability to detect abnormal suckling behavior using statistical analysis and machine learning. We evaluate cases of ankyloglossia to determine how oral dysfunction and surgical interventions affect non-nutritive suckling measurements. CONCLUSIONS: Statistical analysis (Mahalanobis Distance) and machine learning [K nearest neighbor (KNN)] can be viable approaches to rapidly interpret infant suckling measurements. Particularly in practices using the digital suck assessment with a gloved finger, it can provide a more objective, early stage screening method to identify abnormal infant suckling vacuum. This approach for identifying those at risk for breastfeeding complications is crucial to complement complex emerging clinical evaluation technology. CLINICAL IMPACT: By analyzing non-nutritive suckling using computational methods, we demonstrate the ability to detect abnormal and normal behavior in infant suckling that can inform breastfeeding intervention pathways in clinic.Clinical and Translational Impact Statement: The work serves to shed light on the lack of consensus for determining appropriate intervention pathways for infant oral dysfunction. We demonstrate using statistical analysis and machine learning that normal and abnormal infant suckling can be identified and used in determining if surgical intervention is a necessary solution to resolve infant feeding difficulties.

Using the lens of trauma informed care to inform pediatric obesity management.

PURPOSE OF REVIEW: Summarize the evolution of the trauma-informed care (TIC) approach in pediatrics, highlight the importance of using this lens in pediatric obesity management and treating the whole patient and family, and suggest recommendations for providers to incorporate TIC into their practice. RECENT FINDINGS: Implementing TIC in pediatric obesity management is recommended and offers an approach to address trauma-related symptoms associated with obesity. The TIC framework creates a safe, nurturing space to have open conversations with patients and families to promote resilience and reduce stigma related to obesity without re-traumatization. Screening tools may expose symptoms related to trauma, but are limited. Provider training is available and development of TIC related skills may be improved through using the arts and humanities. Success of TIC requires a tailored, integrated healthcare system approach with commitment from all levels. SUMMARY: The TIC approach offers providers skills to uncover trauma-related symptoms and address obesity-related health disparities while reducing stigma. Collaboration across all levels of the healthcare system and community partners is essential. Further research is warranted on the effectives of this approach in pediatric obesity prevention and management.

Non-Nutritive Suckling System for Real-Time Characterization of Intraoral Vacuum Profile in Full Term Neonates.

Infant breastfeeding diagnostics remain subjective due to the absence of instrumentation to objectively measure and understand infant oral motor skills and suckling characteristics. Qualitative diagnostic exams, such as the digital suck assessment which relies upon a clinician's gloved finger inserted into the infant's mouth, produce a diversity of diagnoses and intervention pathways due to their subjective nature. In this paper, we report on the design of a non-nutritive suckling (NNS) system which quantifies and analyzes quantitative intraoral vacuum and sucking patterns of full-term neonates in real time. In our study, we evaluate thirty neonate suckling profiles to demonstrate the technical and clinical feasibility of the system. We successfully extract the mean suck vacuum, maximum suck vacuum, frequency, burst duration, number of sucks per burst, number of sucks per minute, and number of bursts per minute. In addition, we highlight the discovery of three intraoral vacuum profile shapes that are found to be correlated to different levels of suckling characteristics. These results establish a framework for future studies to evaluate oromotor dysfunction that affect the appearance of these signals based on established normal profiles. Ultimately, with the ability to easily and quickly capture intraoral vacuum data, clinicians can more accurately perform suckling assessments to provide timely intervention and assist mothers and infants towards successful breastfeeding outcomes.

Factors associated with COVID-19 vaccine intent among Latino SNAP participants in Southern California.

BACKGROUND: COVID-19 is significantly impacting the health and well-being of the country, particularly for ethnic minority populations and low-income groups. Our goal was to determine COVID-19 vaccination intent in a low-income, Latino population receiving aid from the Supplemental Nutrition Assistance Program (SNAP) in Southern California, and identify contributing factors and concerns. METHODS: A cross-sectional, mixed-methods survey was conducted among participants in the Southern California Nutrition Incentives Program (¡Más Fresco! More Fresh). Only Latino respondents were included in this analysis. Primary outcome was vaccine intent trichotomized into: "definitely/likely yes", "not sure/don't know", and "definitely/likely not." RESULTS: The majority of participants (n = 486) were female (93%), Spanish speaking (74%), with a median age of 40 years (IQR = 13). Approximately half (48%) reported they would get a COVID-19 vaccine, 39% were unsure, and 13% reported "definitely/likely not". In the multivariable multinomial logistic regression model, participants with a household member with a COVID-19 health risk factor were more likely to be unsure about getting the vaccine. Participants who were primarily English speaking, did not receive the influenza vaccine last season, and reported not reading or talking about COVID-19 were more likely to report not intending to receive the vaccine. Many respondents were concerned about "side effects and ingredients", and did not trust the vaccine development process, particularly with how fast it happened. CONCLUSION: Low-income Latinos in Southern California were generally hesitant to get a COVID-19 vaccine. Culturally sensitive vaccine promotion campaigns need to address the concerns of minority populations who experience increased morbidity and mortality from COVID-19.

Office-Based Educational Handout for Influenza Vaccination: A Randomized Controlled Trial.

OBJECTIVES: To assess the impact of a parent educational intervention about influenza disease on child vaccine receipt. METHODS: A convenience sample of parents of children ≥6 months old with a visit at 2 New York City pediatric clinics between August 2016 and March 2017 were randomly assigned (1:1:1) to receive either usual care, an educational handout about influenza disease that was based on local data, or an educational handout about influenza disease that was based on national data. Parents received the handout in the waiting room before their visit. Primary outcomes were child influenza vaccine receipt on the day of the clinic visit and by the end of the season. A multivariable logistic regression was used to assess associations between intervention and vaccination, with adjustment for variables that were significantly different between arms. RESULTS: Parents who received an intervention (versus usual care) had greater odds of child influenza vaccine receipt by the end of the season (74.9% vs 65.4%; adjusted odds ratio 1.68; 95% confidence interval: 1.06-2.67) but not on the day of the clinic visit. Parents who received the national data handout (versus usual care) had greater odds of child influenza vaccine receipt on the day of the clinic visit (59.0% vs 52.6%; adjusted odds ratio 1.79; 95% confidence interval: 1.04-3.08) but not by the end of the season. CONCLUSIONS: Providing an educational intervention in the waiting room before a pediatric provider visit may help increase child influenza vaccine receipt.

The use of technology to promote vaccination: A social ecological model based framework.

Vaccinations are an important and effective cornerstone of preventive medical care. Growing technologic capabilities and use by both patients and providers present critical opportunities to leverage these tools to improve vaccination rates and public health. We propose the Social Ecological Model as a useful theoretical framework to identify areas in which technology has been or may be leveraged to target undervaccination across the individual, interpersonal, organizational, community, and society levels and the ways in which these levels interact.

Early experience with medial femoral tension band plating in idiopathic genu valgum.

PURPOSE: For correction of angular deformity, tension band plating has been proposed as a safe and minimally invasive technique. The purpose of this study was to assess the experiences and report the rate of correction obtained with this procedure in patients with idiopathic genu valgum. METHODS: This study was a retrospective review of 47 valgus deformities of the knee treated with medial hemiepiphysiodesis using a tension band plate. The tibiofemoral angle (TFA) and the anatomic lateral distal femoral angle (aLDFA) were assessed on anteroposterior (AP) radiographs of the lower extremity taken at multiple time intervals. The values were charted to determine the change in orientation of the joint surface over time. Pearson's correlation was used to analyze the correction over time. A subanalysis was performed evaluating the effect of age and the number of plates utilized. RESULTS: A total of 47 deformities in 25 patients were reviewed. The average time of follow-up from index surgery was 12.7 months, with an average correction of 0.96° every 3 months or 3.8° per year. The aLDFA corrected at a faster rate in knees with two plates per hemiepiphysiodesis than those with one plate, 4.2° and 3.3° per year, respectively (P = 0.035). Girls <11 years of age and boys <13 years of age corrected at a rate of 4.5°, while older children corrected at a rate of 3.4° per year (P = 0.39). There were no complications or instrumentation breakages. CONCLUSION: Hemiepiphysiodesis with tension band plating provides an effective and predictable correction of idiopathic genu valgum. Two plates appear to provide a greater rate of correction. There is also a trend toward faster correction in younger patients as well.