Applicability and robustness of an artificial intelligence-based assessment for Greulich and Pyle bone age in a German cohort.

PURPOSE: The determination of bone age (BA) based on the hand and wrist, using the 70-year-old Greulich and Pyle (G&P) atlas, remains a widely employed practice in various institutions today. However, a more recent approach utilizing artificial intelligence (AI) enables automated BA estimation based on the G&P atlas. Nevertheless, AI-based methods encounter limitations when dealing with images that deviate from the standard hand and wrist projections. Generally, the extent to which BA, as determined by the G&P atlas, corresponds to the chronological age (CA) of a contemporary German population remains a subject of continued discourse. This study aims to address two main objectives. Firstly, it seeks to investigate whether the G&P atlas, as applied by the AI software, is still relevant for healthy children in Germany today. Secondly, the study aims to assess the performance of the AI software in handling non-strict posterior-anterior (p. a.) projections of the hand and wrist. MATERIALS AND METHODS: The AI software retrospectively estimated the BA in children who had undergone radiographs of a single hand using posterior-anterior and oblique planes. The primary purpose was to rule out any osseous injuries. The prediction error of BA in relation to CA was calculated for each plane and between the two planes. RESULTS: A total of 1253 patients (aged 3 to 16 years, median age 10.8 years, 55.7 % male) were included in the study. The average error of BA in posterior-anterior projections compared to CA was 3.0 (±â€Š13.7) months for boys and 1.7 (±â€Š13.7) months for girls. Interestingly, the deviation from CA tended to be even slightly lower in oblique projections than in posterior-anterior projections. The mean error in the posterior-anterior projection plane was 2.5 (±â€Š13.7) months, while in the oblique plane it was 1.8 (±â€Š13.9) months (p = 0.01). CONCLUSION: The AI software for BA generally corresponds to the age of the contemporary German population under study, although there is a noticeable prediction error, particularly in younger children. Notably, the software demonstrates robust performance in oblique projections. KEY POINTS: · Bone age, as determined by artificial intelligence, aligns with the chronological age of the contemporary German cohort under study.. · As determined by artificial intelligence, bone age is remarkably robust, even when utilizing oblique X-ray projections..

Increased Incidence of Functional Constipation in Children with a History of Perianal Abscess-A Single-Center Retrospective Cohort Study.

INTRODUCTION: Functional constipation (FC) is a common gastrointestinal disorder affecting up to 30 % of children. Voluntary stool withholding (e.g., after painful defecation) with consecutive harder and larger stools can result in avoidance patterns. Perianal abscesses (PA) are associated with anal pain and painful stooling. We hypothesized that patients with PA have a higher incidence of subsequent FC compared with children without PA. MATERIALS AND METHODS: Between January 2010 and December 2016, we retrospectively analyzed all infants (< 365 days of life) presenting at our institution with PA or unilateral inguinal hernia repair (IH; control group). We screened the clinical charts of these patients for outpatient or inpatient visits due to FC according to ROME IV criteria between 01/2010 and 10/2019. Statistical analysis was done using chi-squared test. RESULTS: We included a total of 37 infants with PA and 118 with IH repair (controls). Mean age at presentation for PA was 3.7 ± 0.5 months compared with 4.2 ± 0.3 months at surgery for IH. In the PA group, 6/37 (16%) developed FC compared with 1/118 (1%) in the control group (p-value < 0.01). Patients with PA presented with FC at a mean age of 22.3 ± 4.6 months. Twenty-three of thirty-seven (62%) of PA patients underwent surgery. The development of FC in the PA group was independent of conservative versus surgical treatment (14 vs. 17%, p >0.05). CONCLUSION: Our study suggests that PA is associated with an increased risk of FC during the further course. Prophylactic stool softening in patients with PA may be considered to prevent subsequent FC.

Esophageal Atresia with or without Tracheoesophageal Fistula (EA/TEF): Association of Different EA/TEF Subtypes with Specific Co-occurring Congenital Anomalies and Implications for Diagnostic Workup.

BACKGROUND: Esophageal atresia with or without tracheoesophageal fistula (EA/TEF) represents the most common developmental malformation of the upper digestive tract. It is classified into six subtypes according to the classification of Vogt, depending on anatomical variation of this malformation. Around 50% of the patients with EA/TEF present additional anomalies, which often influence, next to the EA/TEF subtype, the overall prognosis of EA/TEF newborns. Here, we investigated the association of the different EA/TEF subtypes with co-occurring congenital anomalies in EA/TEF patients and demonstrate their implications for postnatal diagnostic workup. MATERIALS AND METHODS: We investigated 333 patients of a large German multicenter study born between 1980 and 2012. After evaluation of all available clinical records, 235 patients were included in our analysis. We compared our results with existing data. RESULTS: The highest risk for co-occurring anomalies was seen in patients with most common Vogt 3b (p = 0.024), especially for additional gastrointestinal anomalies (p = 0.04). Co-occurring anomalies of the skin were significantly more common in patients with subtype Vogt 2 (p = 0.024). A significant correlation was observed for an impaired neurodevelopmental outcome and EA/TEF Vogt 3a (p = 0.041). Patients with EA/TEF showed a higher risk to present with any additional congenital anomaly compared with the general population (p < 0.001). CONCLUSION: Our results warrant thorough clinical workup for gastrointestinal anomalies especially in patients with Vogt 3b. Moreover, it might be necessary to focus on a thorough aftercare for neurocognitive development in patients with Vogt 3a. The here presented observations need to be confirmed by future studies.