Normal and Abnormal Growth in the Pediatric Patient

Anthropometric assessment: ESPGHAN quality of care survey from paediatric hospitals in 28 European countries

OBJECTIVES

Assessment of anthropometric data is essential for paediatric healthcare. We surveyed the implementation of European Society of Paediatric Gastroenterology, Hepatology and Nutrition (ESPGHAN) evidence-based guidelines and practical recommendations on nutritional care, particularly regarding anthropometric measurements.

METHODS

Paediatric hospitals from 28 European countries provided pseudonymized data through online questionnaires on hospital characteristics and their standards of nutritional care. Practical tasks assessed an unbiased collection and reporting of anthropometric measurements in random patients' files and discharge letters.

RESULTS

Of 114 hospitals (67% academic), 9% have no nutritionist/dietitian available, 18% do not provide standard policy to assess weight and height and 15% lack training for nursing staff for accurate performance. A wall-mounted stadiometer to measure standing height and equipment for sitting weight is unavailable in 9% and 32%, respectively. Infant length is measured by one instead of two healthcare professionals and with a tape instead of a rigid length measuring board in 58% and 15% of hospitals, respectively. The practical tasks reviewed 1414 random patients, thereof 446 younger than 2 years of age. Missing documentation occurred significantly more often for height versus weight and their percentiles in infants ≤2 years versus older children, and in general paediatric versus gastrointestinal patients, with no difference between academic and nonacademic hospitals. Review of documented anthropometric data in discharge letters disclosed that consultants significantly underestimated the deficits in their units compared to documented data.

CONCLUSIONS

The survey revealed significant gaps in performance and documentation of anthropometry in the participating hospitals. A resurvey will assess changes in quality of care over time.

Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained With Healthy Chronological and Greulich-Pyle Ages as Labels

OBJECTIVE

To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model.

MATERIALS AND METHODS

A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model).

RESULTS

Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2.

CONCLUSION

The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

Linear growth in young people with restrictive eating disorders: "Inching" toward consensus

Background

While the assessment of acute medical stability in patients with eating disorders should never be minimized, careful attention toward other specific age-related consequences of malnutrition can improve psychological outcomes and reduce long-term, potentially irreversible medical complications, like linear growth impairment.

Review

While the impact of malnutrition on linear growth is widely recognized, emerging data highlight consensus in several key areas: the time from onset to time of diagnosis, age at illness onset, pubertal stage at illness onset, and adequacy of weight restoration to achieve catch-up growth. This review provides concrete and actionable steps to help providers identify and explore deviations in expected growth and development while prioritizing early and aggressive weight restoration to provide the best opportunity for catch-up linear growth in patients with eating disorders.

Conclusion

The impact of restrictive eating disorders on growth and development cannot be overstated, particularly in pre- and peripubertal patients. While many consequences of malnutrition are reversible, the loss of genetic height potential may prove irreversible without early and aggressive weight restoration.

A Cascade Model with Prior Knowledge for Bone Age Assessment

Bone age is commonly used to reflect growth and development trends in children, predict adult heights, and diagnose endocrine disorders. Nevertheless, the existing automated bone age assessment (BAA) models do not consider the nonlinearity and continuity of hand bone development simultaneously. In addition, most existing BAA models are based on datasets from European and American children and may not be applicable to the developmental characteristics of Chinese children. Thus, this work proposes a cascade model that fuses prior knowledge. Specifically, a novel bone age representation is defined, which incorporates nonlinear and continuous features of skeletal development and is implemented by a cascade model. Moreover, corresponding regions of interest (RoIs) based on RUS-CHN were extracted by YOLO v5 as prior knowledge inputs to the model. In addition, based on MobileNet v2, an improved feature extractor was proposed by introducing the Convolutional Block Attention Module and increasing the receptive field to improve the accuracy of the evaluation. The experimental results show that the mean absolute error (MAE) is 4.44 months and significant correlations with the reference bone age is (r = 0.994, p < 0.01); accuracy is 94.04% for ground truth within ±1 year. Overall, the model design adequately considers hand bone development features and has high accuracy and consistency, and it also has some applicability on public datasets, showing potential for practical and clinical applications.