Background: Children with mucopolysaccharidosis (MPS) generally appear unaffected at birth but may develop multiple clinical manifestations including profound growth impairment as they grow older. Each type of MPS has a variable age at onset and variable rate of progression, however, information regarding growth in Asian children is limited. Methods: This retrospective analysis included 129 Taiwanese patients with MPS (age range, 0.7 to 19.5 years, median age, 7.9 years) from eight medical centers in Taiwan from January 1996 through December 2018. Results: The mean z scores for the first recorded values of height, weight, and body mass index in the patients’ medical records were −4.25, −1.04, and 0.41 for MPS I (n = 9), −2.31, 0.19, and 0.84 for MPS II (n = 49), −0.42, 0.08, and −0.12 for MPS III (n = 27), −6.02, −2.04, and 0.12 for MPS IVA (n = 30), and −4.46, −1.52, and 0.19 for MPS VI (n = 14), respectively. MPS IVA had the lowest mean z scores for both height and weight among all types of MPS, followed by MPS VI, MPS I, MPS II, and MPS III, which showed the mildest growth retardation. Both z scores for height and weight were negatively correlated with increasing age for all types of MPS (p < 0.01). Of 32 patients younger than 5 years of age, 16 (50%), and 23 (72%) had positive z scores of height and weight, respectively. A substantial number of younger patients with MPS I, II, III, and IVA had a positive height z score. The median age at diagnosis was 3.9 years (n = 115). Conclusions: The patients with MPS IVA had the most significant growth retardation among all types of MPS, followed by MPS VI, MPS I, MPS II, and MPS III. The height and weight of the MPS patients younger than 2–5 years of age were higher than those of healthy individuals, however, their growth significantly decelerated in subsequent years. Understanding the growth curve and potential involved in each type of MPS may allow for early diagnosis and timely management of the disease, which may improve the quality of life.

Mucopolysaccharidosis type II (MPS II) is the most frequently occurring MPS in Taiwan, with an incidence of 2.05 per 100,000 live male births, but little is known about clinical characteristics and surgical history in Taiwanese patients. Medical history, demographics, signs and symptoms, and surgical history were analysed in all patients from Taiwanese centres in the Hunter Outcome Survey (HOS; NCT 03292887), a global, multicentre registry that collects real-world data on patients with MPS II. As of January 2016, 61 male Taiwanese patients were enrolled; 49% (24/49) had received at least one infusion of idursulfase. Median (10th, 90th percentiles) ages at signs and symptom onset and at diagnosis were 2.5 (0.2, 5.5) years (n = 55) and 3.5 (1.2, 11.9) years (n = 56), respectively. Hernia, facial features consistent with MPS II and claw hands were the earliest presenting signs and symptoms (median ages of 3.2 [0.4, 12.0] years, 4.3 [1.1, 12.0] years and 4.7 [2.5, 12.2] years [n = 45, 53 and 50], respectively). More than 75% of patients had undergone a surgical procedure, most commonly hernia repair (57% of patients). Median age at first surgery for hernia repair was 4.2 (0.5, 9.8) years (n = 35). Almost one-third (31.1%) of patients had at least one surgical procedure before diagnosis, and of the 20 procedures before diagnosis, 16 were hernia repair. This information from patients in HOS highlights the importance of both medical and surgical history in diagnosing MPS II in Taiwanese patients.

Precocious puberty in girls is defined as the onset of pubertal changes before 8 years of age, and gonadotropin-releasing hormone (GnRH) agonist treatment is available for central precocious puberty (CPP). The gold standard for diagnosing CPP is the GnRH stimulation test. However, the GnRH stimulation test is time-consuming, costly, and requires repeated blood sampling. We aimed to develop an artificial intelligence (AI) prediction model to assist pediatric endocrinologists in decision making regarding the optimal timing to perform the GnRH stimulation test. We reviewed the medical charts of 161 girls who received the GnRH stimulation test from 1 August 2010 to 31 August 2021, and we selected 15 clinically relevant features for machine learning modeling. We chose the models with the highest area under the receiver operating characteristic curve (AUC) to integrate into our computerized physician order entry (CPOE) system. The AUC values for the CPP diagnosis prediction model (LH ≥ 5 IU/L) were 0.884 with logistic regression, 0.912 with random forest, 0.942 with LightGBM, and 0.942 with XGBoost. For the Taiwan National Health Insurance treatment coverage prediction model (LH ≥ 10 IU/L), the AUC values were 0.909, 0.941, 0.934, and 0.881, respectively. In conclusion, our AI predictive system can assist pediatric endocrinologists when they are deciding whether a girl with suspected CPP should receive a GnRH stimulation test. With proper use, this prediction model may possibly avoid unnecessary invasive blood sampling for GnRH stimulation tests.